SEEFOR 16(1): 95-113
Article ID: 2504
DOI: https://doi.org/10.15177/seefor.25-04
REVIEW PAPER
Innovative Approaches to Forest Fire Prevention: Integrating Technology and Ecological Strategies. A Comprehensive Review
Syed Shaheer Hassan1, Guang Yang1*, Sana Tahir2, Haseeb Ahmad2, Muhammad Sabir3, Laila Noor4, Khuzin Dinislam5
(1) Northeast Forestry University, School of Forestry, Heilongjiang Province State Key Laboratory of Forest Protection, Xiang Fang District, CH-150040 Harbin, P.R. China;
(2) Northeast Forestry University, School of Forestry, Heilongjiang Province State Key Laboratory of Tree Genetics and Breeding, Xiang Fang District, CH-150040 Harbin, P.R. China;
(3) Northeast Forestry University, School of Forestry, Key Laboratory of Forest Pathology, CH-150040 Harbin, P.R. China;
(4) University of Peshawar, Department of Botany, KPK Province, 2F4Q+42H, Rahat Abad, PA-25120, Peshawar, Pakistan;
(5) Bashkir State Medical University, Department of Chemistry, Ulitsa Lenina, 3, Ufa, Republic of Bashkortostan, RU-450008, Russia
Citation: Hassan SS, Yang G, Tahir S, Ahmad H, Sabir M, Noor L, Dinislam K, 2025. Innovative Approaches to Forest Fire Prevention: Integrating Technology and Ecological Strategies. A Comprehensive Review. South-east Eur for 16(1): 95-113. https://doi.org/10.15177/seefor.25-04.
Received: 12 Sep 2024; Revised: 13 Dec 2024; Accepted: 05 Feb 2025; Published online: 18 Apr 2025
Cited by: Google Scholar
Abstract
The problems associated with the advancement of technology and the environment are growing more complicated in recent years. Wildfires are one of the most important environmental challenges since they seriously endanger the world's ecosystems. There are many different types of damage done to forests, which result in both climate change and the devastation of terrestrial ecosystems. Consequently, the implementation of efficient strategies for early warning, prevention, the efficacy of ecological methods like fuel management strategies and green fire barriers in preventing wildfires and well-coordinated treatments is necessary to lessen their impact on both people and the environment. This overview examines the development of several technologies from previous years to the present with the purpose of detecting, tracking, and preventing forest fires. It draws attention to the advantages, restrictions, and potential advancements in this field of research. Because of their catastrophic effects on ecosystems and potential consequences on the climate, forest fires have become a major environmental concern. To create more potent plans for preventing and controlling wildfires, our research demonstrated the necessity for significant advancements in ecological methods, technological breakthroughs, and community involvement to strengthen wildfire preservation efforts.
Keywords: wildfire prevention techniques; satellites; AI; drones; ecological strategies; community engagement
INTRODUCTION
The intricacies associated with the widespread adoption of technology and its influence on the environment are growing in modern times. Wildfires present a substantial environmental dilemma as they represent a grave peril to the worldwide biosphere (Carta et al. 2023, Kreider et al. 2024). Given the substantial and diverse hazards posed by forest fires to terrestrial ecosystems and forests, it is imperative to adopt a proactive and timely strategy for their control (MacCarthy et al. 2023). Forest fires cause substantial damage to forested areas and have important ecological, economic, and societal consequences. Forest fires can be a result of both natural and anthropogenic causes (Arienti et al. 2006, Fried et al. 2008, Plucinski 2019, Kreider et al. 2024). Volcanic eruptions, lightning strikes, and spontaneous combustion are among various natural causes. Unregulated agricultural practices, alterations in land utilization, deliberate fire-setting, and negligence are instances of anthropogenic causes. Moreover, climate change amplifies fire conditions, hence heightening the probability and severity of wildfires (Blake et al. 2019, Winker et al. 2024).
The latest data on forest fires confirm our longstanding concerns: forest fires are expanding their reach more extensively compared to two decades ago, resulting in the destruction of at least double the amount of forested areas. In comparison to 2001, forest fires presently result in the annual loss of around 6 million hectares of tree cover (Tyukavina et al. 2022). Moreover, fire has a more prominent role in the depletion of global tree coverage compared to other processes such as mining and forestry. In 2001, fires accounted for around 20% of the whole forest cover loss. Currently, they constitute approximately 33% of the entire loss (MacCarthy et al. 2023). There has been a discernible surge in the incidence of fires in recent years, setting new records. Based on the rankings, it is evident that worldwide forest fires have been increasingly prevalent, with 2020, 2021, and 2023 being classified as the fourth, third, and first most severe years, respectively. In 2023, a land area about the size of Nicaragua, or nearly 12 million hectares, was consumed by fire, exceeding the previous record by approximately 24%. In Canada, almost 65% of the tree cover loss caused by fires in the preceding year may be attributed to catastrophic wildfires. Furthermore, these wildfires accounted for more than 27% of the overall tree cover loss globally (Flannigan et al. 2006, Wang et al. 2017, Hanes et al. 2019, MacCarthy et al. 2023). Climate change is a primary factor contributing to the increase in fire activity. Predictions indicate that severe heat waves will appear more often as global warming persists, with the current likelihood being five times higher compared to 150 years ago. Increased temperatures cause the terrain to become drier, creating optimal conditions for larger and more frequent forest fires (Carta et al. 2023, MacCarthy et al. 2023, Synolakis and Karagiannis 2024).
Recent technical developments have brought new instruments for detection, prediction, and reaction to wildfires, changing the management landscape. The fields of satellite technology and remote sensing are among the most promising for innovation. These technologies give authorities vital information on the health of the vegetation, moisture content, and fire behaviour, allowing them to properly monitor areas that are prone to wildfires. Modern sensors on satellites, like the Visible Infrared Imaging Radiometer Suite (VIIRS) (Schroeder et al. 2024, Setiawan et al. 2024) and the Moderate Resolution Imaging Spectroradiometer (MODIS) (Schroeder et al. 2024, Setiawan et al. 2024), make it easier to identify current fires and evaluate burned areas. This capacity is essential for comprehending the dynamics of fire and developing strategic reactions.
Furthermore, fire management and surveillance have undergone a radical change with the introduction of drones and unmanned aerial vehicles (UAVs) (Alon et al. 2021, Orgeira-Crespo et al. 2024, Wang et al. 2024, Wu et al. 2024). Drones with thermal imaging cameras are able to identify any fire outbreak early on because they can identify heat signatures that are invisible to the human eye. Their capacity to deliver real-time aerial data improves firefighting teams' situational awareness, empowering them to decide on containment tactics and resource allocation with knowledge. One example of how technology might enhance conventional firefighting techniques is the incorporation of drones into fire management operations.
The application of artificial intelligence (AI) (Cilli et al. 2022, Ahmad et al. 2023, Fan et al. 2024) to the forecast and management of wildfires is another noteworthy technological achievement. To identify high-risk locations and forecast fire behaviour, artificial intelligence (AI) algorithms examine enormous datasets, including past fire data, weather patterns, and vegetation conditions. AI can improve the accuracy of fire prediction models by using machine learning techniques, which will enable prompt responses. AI-powered systems, for example, can combine information from multiple sources, like weather stations and satellite photos, to offer thorough insights into changing fire conditions. This all-encompassing strategy helps with resource deployment and evacuation route planning in addition to increasing prediction accuracy.
Along with artificial intelligence, the creation of thermosensitive fire alarms (Doolin and Sitar 2005, Allison et al. 2016, Yu et al. 2021, Lv et al. 2022, Leslie et al. 2024) is a new method of detecting fires. By using materials that are sensitive to temperature changes, these alarms are able to identify sudden spikes in heat and provide early warnings that can stop small fires from growing into bigger catastrophes. In a similar way, autonomous systems and firefighting robots (Bogue 2021, Martinez-Rozas et al. 2021, Oliveira et al. 2021) are becoming important tools for fire management. These robots can operate in dangerous areas, lowering the risk to human firefighters while increasing operating efficiency. They are outfitted with cutting-edge sensors and firefighting abilities.
Technological advancements are important in preventing fires, but ecological solutions are still essential for managing fires sustainably. Prescribed fires and habitat restoration are examples of ecological practices that aid in lowering fuel loads and enhancing ecosystem resilience. These strategies reduce the severity of possible fires and establish firebreaks by carefully controlling vegetation. A comprehensive approach to fire management is facilitated by the fusion of ecological practices and technological advancements, which tackle the short- and long-term causes of wildfires (Brodie et al. 2024, Crockett and Hurteau 2024, Kokosza et al. 2024, Zald et al. 2024).
Furthermore, around 84% of wildfires are initiated by human action, with common causes including campfires, burning debris, and the usage of equipment (Kendell et al. 2023). Fostering a culture of readiness and resilience requires empowering local communities to take part in fire prevention initiatives. The community's ability to respond to wildfires can be greatly improved by educational initiatives that increase public knowledge of fire threats and preventative techniques. Involving the community in fire-safe landscaping and plant management initiatives not only reduces risks but also fosters community cohesion and encourages care of natural resources (Hensley 1975, Frandsen et al. 2011, Paton and Buergelt 2012, Amberson et al. 2023, Fazeli et al. 2024, Hostetter et al. 2024, Palsa et al. 2022).
Creating a thorough framework for preventing forest fires requires the convergence of ecological principles and technical developments. Every strategy works in concert with others to produce a synergistic impact that increases overall efficacy. For example, by identifying regions that need intervention, data gathered through remote sensing might inform ecological management approaches. On the other hand, ecological techniques, which offer insights into fire behaviour and vegetation dynamics, can improve the forecasting power of AI models.
Therefore, a cooperative strategy that makes use of the advantages of both ecology and technology is required due to the complex nature of forest fire prevention. The use of innovative approaches, such as artificial intelligence (AI), drones, remote sensing, thermosensitive alarms, and community involvement, will be essential for reducing the effects of wildfires as the wildfire landscape becomes more complicated. The purpose of this review is to compile advantages and limitations of these cutting-edge strategies in order to highlight their efficacy and potential for use in the future to avoid forest fires.
RESULTS OF RESEARCH
Remote Sensing and Satellite Technology
The field of remote sensing and satellite technologies has made substantial progress in the early identification and surveillance of wildfires. Due to the inadequate time interval between photos, proactive modeling using Landsat satellites has not been effective despite their decades-long deployment. Contemporary technology enables the monitoring of wildfires and the assessment of their expansion every 12 hours through the utilization of satellite imagery (Barber et al. 2024, Fraga et al. 2024, Liz-López et al. 2024, Synolakis and Karagiannis 2024). More often than ever, fire activity, growth, and behaviour are monitored using NASA's Fire Events Data Suite (Barber et al. 2024, Hunter 2024, Riris et al. 2024, Soja 2024). In 2024, the proposed synthetic aperture radar (SAR) constellations in Portugal, Spain, and Greece will provide high-resolution photographs every 4 hours (Garcia et al. 2024). From now on, the following images will provide estimates of how the fire perimeter will change over time. By combining thermal imaging and vegetation data with satellite photography, the accuracy of fire spread predictions can be greatly improved, leading to a transformative impact on the suppression of large-scale wildfires (Collins et al. 2024, Lee et al. 2024, Michaelides et al. 2024, Zhang et al. 2024). Satellite imaging is extensively employed globally for wildfire prevention. Synthetic aperture radar (SAR) devices possess more allure compared to optical and multispectral instruments due to their ability to operate in all weather conditions, both day and night, without being hindered by smoke or clouds in the presence of an active fire (Michaelides et al. 2024, Zhang et al. 2024). Geostationary satellites, such as those operated by the National Oceanic and Atmospheric Administration (NOAA), can track the boundaries of wildfires in real-time by consistently observing a certain area. Thermal infrared sensors are employed to identify heat irregularities associated with active flames. Geostationary satellites offer a notable advantage by providing regular updates, which are crucial for understanding the dynamics of fires and effectively coordinating firefighting efforts (Chen et al. 2024, Dong et al. 2024, Giorgi 2024, Kang and Im 2024). VIIRS (Visible Infrared Imaging Radiometer Suite) and MODIS (Moderate Resolution Imaging Spectroradiometer) (Setiawan et al. 2024, Schroeder et al. 2024) sensors, although carried on separate satellite platforms run by NASA and NOAA, respectively, are instruments that gather data about Earth observation. The MODIS sensor has several spatial resolutions and operates in 36 spectral bands, ranging from 0.4 to 14.4 µm in wavelength. There are three bands: two at 250 meters, five at 500 meters, and 29 at one kilometer. Numerous research projects have made extensive use of this cutting-edge technology. There are 22 spectral bands available with VIIRS, comprising 1 panchromatic day/night band (750 m), 5 imaging resolution bands (I bands, 375 m), and 16 moderate-resolution bands (M bands, 750 m) (Setiawan et al. 2024, Schroeder et al. 2024). The data collected by this technology, which is designed to capture images of the Earth from polar orbits, enables the development of applications for monitoring the Earth's land, atmosphere, cryosphere, and seas. Although they often revisit the same location every several hours, they send detailed information at a reduced rate of occurrence. Due to their short revisit periods, these satellites can rapidly detect and monitor the spread of fires. However, they are particularly valuable for recognizing larger fires and assessing the extent of the damage caused by burns (He et al. 2024, Sivakumar et al. 2024, Zhou et al. 2024). Since the 1980s, there has been extensive usage of the Advanced Very High-Resolution Radiometer (AVHRR) sensor on board NOAA satellites for the detection and monitoring of forest fires. AVHRR is appropriate for a range of fire-related applications due to its daily global coverage at moderate resolution (~1 km) and spectral coverage in the visible, near-infrared, mid-infrared, and thermal infrared (Li et al. 2001, Schiks et al. 2024). Among the main benefits of employing AVHRR for monitoring forest fires are: identifying burning fires – with its heightened sensitivity to fire radiation, mid-infrared channel 3 (3.55-3.93μm) enables the detection of even the smallest sub-pixel fires against a background that is cooler; tracking the spread of the fire – two daily revisits allow for the tracking of the growth and movement of big flames over several days; evaluating regions that were burned – using variations in surface reflectance, the visible and near-infrared channels can be utilized to map the extent of burned areas following a fire. Contextual data and dynamic thresholds are two features of more sophisticated fire detection algorithms. It has also been demonstrated that AVHRR data combined with better resolution sensors such as MODIS improves fire monitoring capabilities. Because of its coarse resolution, AVHRR sometimes detects fires only after they have spread, even though it offers a useful long-term record of worldwide fire activity. AVHRR works best when combined with other ground-based, aerial, and satellite monitoring systems to provide timely early warnings (Kim et al. 2016, Carta et al. 2023, Schiks et al. 2024). Sentinel-2 and WorldView-3 are two examples of satellites that have great spatial resolution (down to 30 cm) and frequent revisit durations (every 5 days for Sentinel-2). They are especially helpful for mapping and detecting small-scale fires locally, which makes it possible to identify flames that polar-orbiting satellites could overlook. Multispectral bands of Sentinel-2 are useful for identifying burn scars and evaluating the condition of the vegetation (James et al. 2023, Alonso et al. 2024, Panđa et al. 2024). Remote sensing and satellite technologies hold significant promise for wildfire prevention due to their ability to monitor fire-prone regions and provide early warnings. Modern satellites, such as those equipped with the Visible Infrared Imaging Radiometer Suite (VIIRS) and Moderate Resolution Imaging Spectroradiometer (MODIS), can detect vegetation stress and track atmospheric conditions conducive to wildfires. By integrating data from these satellites with predictive models, authorities can identify high-risk zones before ignition occurs. For example, synthetic aperture radar (SAR) technology enables consistent observation, unaffected by weather or smoke, making it an invaluable tool for preventive monitoring in vulnerable regions. Table 1 below shows various image sensors and their specifications.
Table 1. Review of the various image sensors used in satellites.
Drones/UAVs
These tools are extremely helpful as they are equipped with high-resolution cameras and thermal image technology. They greatly improve aerial surveillance and real-time data collecting for wildfire management. This feature enables precise access to the dimensions, extent, and dynamics of a fire. Drones provide firefighters with comprehensive visual data, allowing them to make well-informed judgments on the allocation of resources, the selection of evacuation routes, and the development of firefighting methods. Drones can detect areas of intense heat and assess the strength of a fire, which is essential for effectively combating fires and allocating resources (Radu et al. 2019, Alon et al. 2021, Roldán-Gómez et al. 2021). Different types of drones as shown in Table 2 are used for firefighting, i.e. DJI Mavic 3 Thermal, DJI Matrice 300 RTK, and DJI Matrice 30T (Alon et al. 2021, Wu et al. 2024). The Zen Muse H20N camera is specially attached with Matrice 300 RTK drone, with its advanced imaging features which include dual thermal cameras, a laser rangefinder, and starlight sensors for low light. H20N is appropriate for a wide range of uses, including surveillance, search and rescue missions (Bhattarai and Lucieer 2024). These drones are also used for carrying firefighting equipment such as fire extinguisher balls (Valmiki et al. 2024, Wang et al. 2024). Drones are crucial for conducting search and rescue operations during wildfires, as well as for monitoring and observing the fires. Thermal cameras equipped on drones can detect heat signatures, facilitating the identification and assessment of stranded individuals. This capability enables rescue teams to effectively prioritize their actions and perhaps save lives in situations with limited sight caused by smoke or darkness. Drones are not only useful for determining the magnitude, precise location, spread, and behaviour of fires, but they are also effective in reducing the extent of fires during their early phases (Orgeira-Crespo et al. 2024, Wu et al. 2024). Drones are an essential instrument for conducting post-fire evaluations in the aftermath of a wildfire. By utilizing airborne imagery, they may acquire thorough documentation of the fire's impact on infrastructure, vegetation, and structures in the affected areas. This data facilitates a more comprehensive view on the extent of the damage and provides valuable insights for the development of future fire management strategies. Recovery planning, insurance claims, and post-fire investigations are all crucial aspects (Wang et al. 2024). These are also cost-effective alternatives to traditional firefighting methods (Orgeira-Crespo et al. 2024, Wang et al. 2024, Wu et al. 2024). Drones equipped with thermal imaging cameras can serve as on-demand surveillance tools, mapping fuel loads and identifying areas of concern in real time. Their flexibility allows for frequent, localized assessments, which complement satellite data by providing higher-resolution imagery for targeted interventions. For instance, drones can map the effectiveness of green fire barriers or assess the success of controlled burns, enabling continuous improvement in fire prevention measures.
Table 2. Review of the various types and specifications of drones used in wildfire fighting.
AI in Wildfire Prediction
The AI data-driven approach (Haney 2019) constructs prediction models by leveraging extensive datasets, including historical fire data, meteorological data, and topographical parameters. The Fire Aid program in Türkiye employs machine learning algorithms to assess more than 400 factors from 14 datasets, enabling the anticipation of wildfires with a precision rate of 80% up to 24 hours in advance. Due to its predictive powers, authorities can proactively plan and implement preventive measures, significantly reducing the likelihood of injury and enhancing public safety (Sayad et al. 2019, Giannakidou et al. 2024, Okoro et al. 2024). Predicting fire behaviour, considering variables such as weather patterns and fuel moisture levels is essential for efficient deployment of resources and planning evacuations. Real-time monitoring and detection artificial intelligence systems have the capability to examine satellite imagery and aerial data in order to identify areas of intense heat caused by fires and continuously observe how fires are spreading and behaving (Czyczula Rudjord et al. 2022). AI combines data from multiple sources, including remote sensors and meteorological stations, to give a complete understanding of wildfire situations. This helps emergency responders make well-informed choices (Jaafari et al. 2019, Sayad et al. 2019, Carta et al. 2023). Artificial intelligence enhances the efficiency of allocating resources in wildfire scenarios. AI algorithms can enhance the allocation of firefighting resources by assessing up-to-date data and guiding them towards areas with the highest demand for assistance. This competence is crucial for minimizing reaction time and enhancing the effectiveness of firefighting operations. Artificial intelligence-powered early warning systems are crucial for effectively managing wildfires. These devices can rapidly alert authorities about the initiation of a wildfire by evaluating data from sensors and satellites. Swift detection is crucial in order to initiate early measures that can prevent fires from escalating (Jaafari et al. 2019, Sayad et al. 2019, Czyczula Rudjord et al. 2022, Carta et al. 2023, Boroujeni et al. 2024). Enhancing wildfire control capabilities can be achieved by integrating AI with other technologies such as smoke sensors, drones, and imaging satellites. While satellite systems analyze broader patterns and trends in fire behaviour, drones equipped with artificial intelligence (AI) capabilities can provide focused monitoring and detection. This comprehensive approach improves overall management methods and offers a more advanced comprehension of wildfire dynamics (Boroujeni et al. 2024).
AI-driven systems further enhance preventive strategies by analyzing large datasets to predict wildfire behaviour and identify risk factors. Machine learning models, such as FireNet, process historical fire data alongside meteorological inputs to forecast potential fire outbreaks. These forecasts allow for pre-emptive action, such as deploying resources to high-risk areas or conducting controlled burns to reduce fuel loads. Behavioural modeling with AI can also simulate human evacuation scenarios, improving preparedness and minimizing casualties.
Table 3 shows various AI models used in wildfire prediction and prevention. Convolutional neural network systems (CNNs) are incredibly powerful image analysis tools, especially when it comes to the identification of wildfires using satellite imagery and aerial photographs. CNNs can automatically learn spatial hierarchies of features, which negates the need for manual feature extraction and allows them to identify complex patterns directly from raw data. CNNs can also learn from the data, which leads to significantly improved accuracy in image classification tasks, such as the identification of wildfires, often outperforming conventional detection methods. CNNs also operate well in unpredictable contexts, continuing to function even in the presence of unknown data. Applications like wildfire detection, where conditions might vary greatly and real-time analysis is necessary for efficient response and control, depend heavily on this robustness. CNNs are an effective method for detecting wildfires because they may improve forecast accuracy and dependability in the demanding and dynamic conditions by utilizing their strengths in image processing (Zhang et al. 2019, Ahmad et al. 2023, Marjani et al. 2024). Wildfire prevention and control is becoming more and more dependent on the application of recurrent neural networks (RNNs). Especially in conjunction with other machine learning approaches, RNNs offer robust tools for assessing wildfire risk data and enhancing detection strategies (Kremens et al. 2010, Liang et al. 2019, Perumal and Van Zyl 2020, Marjani et al. 2024). According to WEF (https://www.weforum.org/agenda/2023/09/ai-model-prevent-wildfires/) researchers from Finland's Aalto University developed the Fire CNN model, which is one noteworthy advancement. This model predicts locations at high risk for wildfires by analyzing weather data and satellite imagery using both convolutional neural networks (CNNs) and radial neural networks (RNNs). By simulating several land management techniques, such as turning shrubland into swamp forests and blocking drainage canals, the model has the ability to minimize wildfire occurrences by up to 76%. The use of hybrid artificial intelligence (Bui et al. 2016, Jaafari et al. 2019, Marjani and Mesgari 2023, Marjani et al. 2024) models is growing in the prevention and management of wildfires. These models combine different machine learning approaches to improve operational efficiency and predictive accuracy. These models analyze complicated datasets linked to wildfire risks and behaviours by combining several techniques, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and neuro-fuzzy systems. The application of explainable AI (XAI) in wildfire control is growing as a means of improving the interpretability of machine learning algorithms that forecast fire dangers. XAI assists in identifying important variables that influence the likelihood of wildfires, such as vegetation types and meteorological conditions, by revealing how models create predictions. A study that used a random forest model using Shapley values, for example, showed that it could detect high wildfire occurrence areas with 81.3% accuracy. It also highlighted important factors such as the Fire Weather Index and Normalized Difference Vegetation Index. Because of this openness, forest managers are better equipped to decide on fire control tactics, which eventually help to prevent and lessen wildfire disasters (Cilli et al. 2022, Ahmad et al. 2023, Fan et al. 2024).
Table 3. Review of the various AI models.
Thermosensitive Fire Alarms
There has been a lot of discussion about how early-stage fire-warning systems (EFWSs) are better at spotting fire conditions that develop before they explode. Significant improvements in EFWSs over the past few years have raised the possibility of more time for evacuation in order to lessen the continuous risk of unintentional fires in our daily life (Lv et al. 2022, Li et al. 2022). Thermosensitive alarms, a recent innovation in early-stage fire warning systems, sense temperature changes to signal fire before combustion takes place. These alerts can offer vitally important extra time for evacuation and response in order to save lives, as well as assistance in implementing early firefighting measures in order to avert fire catastrophes (Li et al. 2022, Carta et al. 2023). While traditional smoke detectors may fail due to false alarms caused by dust or steam, thermosensitive fire alarms are more innovative to early fire detection. Some key advancements associated with thermosensitive fire alarms are reduced false alarms (Yu et al. 2021, Lv et al. 2022), real time monitoring and alerts (Lv et al. 2022), wireless communication (Liu et al. 2022, Carta et al. 2023, Alkhatib et al. 2024) and heat detection mechanism (Yu et al. 2021, Li et al. 2022, Alkhatib et al. 2024). Different thermosensitive fire alarms, their specifications and limitations can be seen in Table 4.
Table 4. Different thermosensitive fire alarms used in wildfire prevention.
Firefighting Robots and Autonomous Systems
Human firefighters rely on firefighting robots developed in Japan to help them with dangerous and challenging tasks. Since these robots are well-equipped with a variety of sensors and firefighting devices, they can function in dangerous conditions like highly intense wildfires and toxic smoke (Guruprasad et al. 2020, Arora et al. 2023). Numerous firefighting robots are built to function independently. They can traverse over areas damaged by fires using sensors and algorithms, and they can collect and transmit data in real time, including temperature readings, smoke densities, and video feeds. These robots have fire suppression tools including foam dispensers, water cannons, and fire extinguishers installed. These robots can navigate challenging environments that are impossible for human firefighters to access, like rubble, steep inclines, and small places, thanks to advanced mobility technologies. Firefighters could remotely operate certain robots to facilitate coordinated efforts during rescue and firefighting operations (Guruprasad et al. 2020, Arora et al. 2023, Li et al. 2023, Talavera et al. 2023). Table 5 given below shows different types of firefighting robots and their specifications.
Table 5. Type and specifications of firefighting robots.
Case Studies of Forest-Ecological Techniques
Various contemporary ecological methods are employed to mitigate forest fires. Prescribed or controlled burns are deliberate, closely monitored low-intensity fires initiated with the aim of mitigating the risk of wildfires by minimizing the presence of hazardous fuels, such as dead vegetation and underbrush. This strategy can mitigate the challenges faced by firefighters in controlling wildfires by revitalizing ecosystems, promoting the establishment of fire-adapted species, and modifying future fire behaviour (Brodie et al. 2024, Krishnambika et al. 2024, Wang et al. 2024). Strategically implemented sections, referred to as "fuel breaks", disrupt the uninterrupted expansion of combustible vegetation and effectively reduce or extinguish fires. Implementing practices such as tree thinning, undergrowth clearance, and the protection of open spaces around infrastructure and communities in areas prone to high-risk situations are effective methods for their construction. Fuel stops provide firefighters with additional time to respond and protect vulnerable areas (Krishnambika et al. 2024, Wang et al. 2024). Implementing a deliberate tree spacing and thinning approach can effectively mitigate excessive growth and impede the progression of wildfires. Forest managers engage in brush clearing and tree spacing activities based on projected canopy dimensions in order to establish defensible areas, as excessive growth of trees, shrubs, and other plants can be susceptible to combustion. As a result, fires have a reduced likelihood of spreading and may be extinguished more rapidly (Brodie et al. 2024, Crockett and Hurteau 2024, Kokosza et al. 2024, Zald et al. 2024). Ensuring the prevention of wildfires necessitates the presence of forests that are in good health and possess the ability to recover quickly. By introducing tree species that possess greater resistance to disease, drought, and fire, forests become less susceptible to devastating fires. Research by Sharon Hood et al. provides a comprehensive assessment of the many tree species in the Northern Rockies, focusing on their ability to adapt and regenerate in the aftermath of fires. The research emphasizes that particular species, such as ponderosa pine and western larch, exhibit exceptional fire resistance due to their large root systems and thick bark (Hood et al. 2018). According to (Alberta Government. 2012 aug 03) deciduous trees like trembling aspen can act as natural firebreaks, slowing fire spread due to their higher moisture content and different structural properties. Moreover, encouraging variety and avoiding monocultures increases the overall resilience of ecosystems (Shuhui et al. 2024, Speck and Speck 2024, Rhodes 2024). The utilization of livestock, specifically sheep and goats, for planned grazing can effectively mitigate the usage of detrimental fuels. Ruminants devour the vegetation such as grasses and bushes which is capable of igniting fires (Batcheler et al. 2024, Karp et al. 2024, Kerns and Day 2024, Schachtschneider et al. 2024). Mechanical methods, such as masticators and mulching machines, are used to decrease the density of plants and establish defensive areas (Calderon et al. 2024, Harrower 2024). Utilization of litter layer to grow mushrooms has also been found as a key factor to prevent wildfires, since fungal spread on the litter layer has several benefits such as nutritional cycling (Wade and Lundsford 1990, Adams and Neumann 2023), soil structure improvement (Hopkins et al. 2021, Adams and Neumann 2023), fire resilience (Hopkins et al. 2021, Espinosa et al. 2023), pest and pathogen control (Espinosa et al. 2023). Some studies used fertilizers on litter layer and achieved some outstanding results which are very effective in wildfire prevention such as: accelerated decomposition, promoting beneficial microbial activities, nutrient enrichment, improved soil quality and encouraging vegetation cover (Ferreira et al. 2015, Girona-García et al. 2021, Agbeshie et al. 2022, Song et al. 2022, Adams and Neumann 2023). Strategically positioned patches of vegetation that are resistant to fire are referred to as "green fire barriers" or "green firebreaks". They are employed to hinder or postpone the propagation of wildfires, especially when they are in proximity to buildings and other structures. Compared to traditional firebreaks, they are a more ecologically sustainable choice since they do not eliminate all organic matter until they reach mineral soil (Warnell et al. 2023). The primary goal of green fire barriers is to disrupt the continuity of flammable vegetation, thus reducing the severity of a fire. Planting low-flammability species can effectively decrease the amount of flammable material, thus slowing down the spread of flames. Studies have demonstrated that places with well-managed green firebreaks exhibit reduced severity and aggression of fires when compared to untreated areas (Li et al. 2024, Murray et al. 2024, Wang et al. 2024). Green fire barriers that employ indigenous plants with minimal flammability also promote biodiversity. By safeguarding indigenous plant species and providing habitats for wildlife, these barriers can contribute to the preservation of ecological balance. Strategically planting a diverse range of species can help to replace invasive plants that may increase the likelihood of fire (Weir et al. 2012, Ascoli et al. 2023, Warnell et al. 2023). Green fire barriers, particularly when positioned along topographic contours, can mitigate erosion and enhance soil stability. Fire activity can exacerbate the risk of erosion following intense rainfall, and vegetation roots play a crucial role in soil stabilization. This ecological advantage is particularly noteworthy in areas where wildfires frequently result in soil degradation (Warnell et al. 2023). These barriers offer protection to residents in places where urban areas meet wilderness areas. These barriers serve to safeguard homes from approaching flames by creating a protective boundary around residential zones. Moreover, they can provide firemen with a fortified zone to effectively combat flames, hence enhancing safety for both civilians and emergency personnel. The field data presented by Cui et al. (2019) demonstrate the efficacy of green firebreaks in putting out large, intense fires. The authors show the potential of these barriers as a biodiversity-friendly fire management approach by highlighting lessons learned from their implementation in China. Another researcher (Wang et al. 2024) also suggested using green fire barriers because of their ability to reduce wildfires. To improve these barriers' ability to guard against wildfires, it highlights how crucial it is to choose the right species.
Figure 1.Ecological techniques.
Community Engagement and Education
Active community participation and education are necessary for promoting wildfire-safe behaviours and enhancing community resilience against fire dangers. This involves implementing initiatives to enhance public consciousness and executing successful community-driven endeavours (Elsworth et al. 2009). Community education: it is imperative to provide people with knowledge about the hazards of wildfires and the proactive measures they can use to mitigate those hazards. By implementing instructional programs, community members are more proficient in understanding fire safety protocols and recognizing the importance of promptly identifying and taking action in the event of a potential fire (Hensley 1975, Ryan et al. 2020, Palsa et al. 2022, Campbell et al. 2024). Promote a culture of preparedness: awareness initiatives play a crucial role in fostering a culture of preparedness and active engagement in fire safety measures by increasing community members' understanding of their responsibilities. This involves dispelling myths about wildfires and providing accurate information to empower residents to make informed decisions (Hensley 1975, Frandsen et al. 2011, Paton and Buergelt 2012, Palsa et al. 2022, Amberson et al. 2023, Fazeli et al. 2024, Hostetter et al. 2024). Encourage collaboration: effective campaigns often involve partnerships among community members, non-profit organizations, and local government institutions. Collaboration can enhance the efficient utilization of resources and offer tailored fire protection strategies to address the specific requirements of different communities (Hensley 1975, Palsa et al. 2022, Azevedo et al. 2024, Campbell et al. 2024, Hostetter et al. 2024, Shahi 2024).
Figure 2.Community engagement.
Case Studies of Effective Community-Led Fire Safety Programs
Several successful community-led initiatives have demonstrated the significance of education and engagement in mitigating wildfires. Community workshops: utilizing interactive workshops has been effective in engaging residents and instilling in them a sense of satisfaction in their preparedness for wildfires. These programs often include presentations and interactive fire safety demonstrations, which promote community engagement (Eriksen 2013, Elliott 2022, Palsa et al. 2022, Vázquez-Varela et al. 2022, Elliott et al. 2023, Dobrich 2024). School programs can ensure that students are cognizant of the hazards of fire and equipped with the knowledge to mitigate them by incorporating fire safety instructions into the curriculum. This approach promotes the engagement of the younger population in advocating for safety protocols inside their households, while simultaneously providing them with knowledge and information (Eriksen 2013, Elliott 2022, Elliott et al. 2023). Neighbourhood watch programs: initiatives aimed at bolstering neighbourhood watch organizations to enhance community awareness and preparedness. These activities enhance response capabilities and community relationships by promoting neighbour vigilance, sharing information about fire threats, and participating in safety drills (Eriksen 2013, Elliott 2022, Palsa et al. 2022, Elliott et al. 2023, Dobrich 2024). Feedback mechanisms: soliciting community feedback on fire services and educational efforts facilitates the adaptation of plans to align with regional needs. This collaborative approach leads to the development of more efficient emergency response and fire prevention techniques (Eriksen 2013, Elliott et al. 2023,). The utilization of technology, such as social media and smartphone applications, has become imperative to disseminate fire safety messages to the broader population (Dobrich 2024, Isabella 2024). These technologies contribute to community engagement and awareness by delivering prompt information on fire incidents, offering safety guidance and giving educational resources (Eriksen 2013, Elliott et al. 2023, Wessinger 2024).
Integration of Technology, Land Management, and Community Education in Wildfire Prevention
Wildfire prevention requires a comprehensive approach that brings together technological advancements, ecological land management practices, and active community education. Modern technologies such as remote sensing, AI-driven models, and drones have transformed how wildfires are detected and managed. For example, satellite imaging identifies high-risk zones based on vegetation density, enabling targeted interventions like controlled burns or grazing (Carta et al. 2023). AI models analyze historical fire data to guide the strategic placement of green fire barriers and ecological buffers, while drones equipped with thermal sensors provide real-time monitoring of fuel loads, allowing for precise actions like tree thinning or undergrowth clearance (Wang et al. 2024). These tools not only detect risks but also inform about actionable land management strategies, creating a more proactive approach to wildfire prevention.
The successful adoption of these technologies hinges on an informed and engaged community. Educational initiatives, such as workshops, can teach residents how to use mobile wildfire detection apps and AI-driven alert systems (Elsworth et al. 2009). Involving communities in deploying and maintaining technologies, such as drones and early warning systems, fosters ownership and increases their effectiveness. Furthermore, mobile platforms can offer real-time fire risk updates while educating users on preventive measures and response strategies (Campbell et al. 2024). Empowering communities with technological knowledge ensures their active participation in wildfire prevention and strengthens overall resilience.
Community education programs can also integrate with land management practices to enhance ecological resilience. Citizen science initiatives enable local populations to monitor vegetation health and report high-risk areas using accessible platforms like smartphone apps (Frandsen et al. 2011). Training programs can focus on creating defensible spaces, managing fire-resistant vegetation, and implementing green fire barriers (Paton and Buergelt 2012). Collaborative fire drills involving community members, firefighters, and technology operators simulate real-world scenarios, improving preparedness and coordination. These efforts not only raise awareness but also ensure the long-term sustainability of ecological interventions.
By combining technology, land management, and community education, wildfire prevention becomes more effective. This integration creates a multiplier effect, reducing ecosystem and community vulnerability while optimizing resource allocation through data-driven insights (Brodie et al. 2024). Moreover, fostering community ownership promotes the adoption and sustainability of preventive measures. A cohesive strategy that links these elements offers a robust and sustainable pathway to mitigating the increasing risks of wildfires (Azevedo et al. 2024).
DISCUSSION
Drones and satellite monitoring systems are only two instances of advanced wildfire control technology that need substantial financial investments. Acquiring, running, and upkeeping these systems can be excessively costly, particularly for smaller organizations or communities with limited financial resources. The presence of this financial obstacle may restrict the efficacy of these devices in places with a high level of risk and impede their widespread acceptance (Webb et al. 2016, Fernández-Blanco et al. 2022). Technologies such as satellite imaging and remote sensing depend on optimal climatic conditions. Malfunctions in these systems, caused by factors like smoke, cloud cover, or atmospheric interference, can lead to delays in both detection and response. Moreover, the reliability of sensors and monitoring equipment can be affected by wear and tear, requiring frequent maintenance and calibration to ensure optimal performance (Esmzadeh 2024). The incorporation of artificial intelligence and machine learning (Czyczula Rudjord et al. 2022) in the control of wildfires produces copious volumes of data that require examination and interpretation (Gonzalez and Ghermandi 2024, Wang et al. 2024). The abundance of data can overwhelm decision-makers, hindering their ability to promptly derive practical insights. Furthermore, the influence of environmental elements and the complexity of fire behaviour might provide challenges to predictive modeling, potentially leading to imprecise estimates and erroneous actions (Neger et al. 2024). As wildfire prevention systems become increasingly interconnected, they are exposed to cybersecurity vulnerabilities. Cybercriminals can disrupt or disable fire detection systems, putting safety standards at risk and perhaps causing catastrophic consequences. Robust cybersecurity protections are essential; however, their implementation can pose challenges (Domínguez et al. 2017, McDermott et al. 2020). Dependence on contemporary technology has the danger of causing communities and fire management personnel to become self-satisfied. Excessive dependence on automated technologies can result in a deficiency of situational awareness and readiness, both of which are crucial in the case of a fire. Education and training remain crucial to ensure that individuals possess the necessary knowledge and skills to respond effectively, especially in the context of technology usage ( Ali et al. 2024, Arango et al. 2024, Chen et al. 2024, Dong et al. 2024, Giorgi 2024, Kang and Im 2024, Tsujiguchi and Coraiola 2024, Silva et al. 2024).
For ecological practices to remain effective, regular maintenance is often required. Regular maintenance and vigilant monitoring are necessary for fuel breaks and green fire barriers to prevent the proliferation of flammable vegetation (Brodie et al. 2024, Krishnambika et al. 2024, Wang et al. 2024). These barriers may lose their effectiveness without regular maintenance, which could make it easier for flames to spread. Environmental factors (Drews et al. 2014) can affect how effective ecological strategies are. For example, certain climatic conditions (such as humidity and wind speed) are necessary for the safe execution of controlled burns (Davis et al. 2024). Uncontrolled burns can result from unfavourable conditions, which could increase rather than decrease the risk of fire (Davis et al. 2024). The effectiveness of ecological fire protection methods may be diminished by the introduction of invasive or non-native species. Invasive plants have the potential to replace native species, leading to an overall increase in flammability in a region and negating the benefits of efforts to minimize fuel (Wang et al. 2024). Managing these invasive species requires additional planning and allocation of resources. An obstacle that could impede progress is the community's endorsement of strategies such as controlled burns. Concerns about the potential for controlled burns to become uncontrollable and the impact on air quality may cause individuals to exercise caution when considering fire management measures. The public must be educated about the benefits and necessary safety measures of these technologies for them to be effectively implemented (Davis et al. 2024, Wang et al. 2024). Implementing and maintaining ecological technology can be financially burdensome, particularly for smaller towns or areas with little financial resources. There is a possibility that certain locations may not completely embrace these fire prevention strategies because of the costs associated with their design, implementation, and maintenance. Fire behaviour can be influenced by various elements, including vegetation type, soil moisture, and topography. The biological dynamics of forests are complex. Due to the complexity of the situation, accurately predicting the outcome of ecological processes can be difficult. Adapting strategies to specific ecosystems requires a thorough comprehension and examination, which may not always be readily available (Davis et al. 2024, Purnomo et al. 2024, Wang et al. 2024, Xu et al. 2024).
Obtaining reliable funding and resources is essential for engaging communities in wildfire prevention efforts, while it can be difficult to acquire them. Numerous municipalities encounter challenges in allocating sufficient funds for ongoing training, education, and mitigation endeavours, particularly smaller ones or those with limited financial resources. The lack of continuous support may undermine the effectiveness and long-term sustainability of engagement initiatives (Copes-Gerbitz et al. 2022, Palsa et al. 2022). Community involvement projects may face challenges due to institutional and cultural barriers. Implementing collaborative tactics can be challenging due to inflexible bureaucratic structures, segmented decision-making processes, and a lack of coordination among agencies and stakeholders. Moreover, the lack of trust between communities and authorities, together with cultural disparities, could hinder the ability to effectively act (Copes-Gerbitz et al. 2022, Mojir et al. 2023). Engaging a diverse range of stakeholders, including local communities, government agencies, landowners, organizations, and indigenous groups, could pose challenges. Managing a diverse range of interests, priorities, and opinions throughout decision-making procedures can be challenging and time-consuming. Although eliminating power inequalities and ensuring fair representation are crucial, they can sometimes be complex and challenging to achieve (Palsa et al. 2022). A significant portion of the population may lack full awareness regarding the hazards presented by wildfires or the critical importance of their involvement in preventive measures. Lack of awareness and information might lead to resistance or indifference towards participation. Effective educational projects require substantial resources and sustained effort to enhance awareness and promote active engagement (Palsa et al. 2022, Mojir et al. 2023). Assessing the importance and effectiveness of community involvement and educational programs can pose challenges. Quantifying the enduring effects of mitigating the risk of wildfires is challenging, and it could require several years to witness discernible enhancements. A lack of adequate measures and assessment mechanisms can make it difficult to justify the continuous spending on these activities (Copes-Gerbitz et al. 2022, Palsa et al. 2022, Mojir et al. 2023). Engaging diverse audiences, including underprivileged communities, non-native speakers, and hard-to-reach groups, can pose challenges. Some populations may not respond well to traditional outreach techniques. Adapting engagement strategies to suit the specific needs and preferences of different groups requires a greater investment of time, financial resources, and expertise. To overcome these challenges, as shown in Table 6, it is necessary to have a comprehensive plan that encompasses continuous funding, institutional support, collaborative decision-making, targeted educational initiatives, and innovative engagement methods tailored to the specific area conditions. Communities can enhance their resilience and proactively participate in initiatives aimed at wildfire prevention by addressing these challenges.
Table 6. Limitations and benefits of modern techniques.
SUGGESTED AREAS FOR FUTURE RESEARCH AND DEVELOPMENT
Advancements in wildfire management strategies present several promising directions for further research and practical enhancement. To effectively mitigate wildfire risks, future efforts must integrate technology, ecological knowledge, and community engagement into cohesive frameworks. These initiatives should be supported by practical solutions and robust policymaking to address wildfire challenges holistically.
The adoption of remote sensing technology is vital for real-time monitoring of fire-prone regions. Future research should focus on enhancing space-based detection systems and equipping drones with advanced sensors to provide timely alerts and detailed assessments of fire dynamics. These technologies can significantly improve response times and optimize resource allocation for efficient fire management (Clements et al. 2011, Ciumasu et al. 2013, Pastor et al. 2020, Hötte and Jee 2022).
Developing smart sensor networks is another priority. Networks of intelligent sensors capable of continuously monitoring ambient temperature, humidity and wind speed can enhance situational awareness and improve decision-making during fire incidents. This scalable solution can greatly improve on-the-ground firefighting strategies (Clements et al. 2011, Ciumasu et al. 2013, Pastor et al. 2020, Hötte and Jee 2022)
Refining AI algorithms is essential for advancing wildfire behaviour prediction models. Research should aim to increase the accuracy of machine learning models by incorporating diverse datasets, including historical fire data and environmental factors. Additionally, behavioural modeling should be explored to simulate human responses in wildfire scenarios, aiding in evacuation planning and improving preparedness efforts (Clements et al. 2011, Ciumasu et al. 2013, Pastor et al. 2020, Hötte and Jee 2022)
Community engagement remains a critical element in wildfire prevention. Future efforts should investigate effective strategies for leveraging social media and technology to raise awareness of wildfire risks and promote preventive measures. High-priority initiatives should include educating residents on constructing defensible spaces and adhering to fire safety standards. Long-term educational programs, such as integrating wildfire lessons into school curricula, can foster a safety-oriented mindset in younger generations. These programs should be evaluated to measure their impact on improving community resilience and preparedness (Campbell et al. 2024, Hostetter et al. 2024, Sukawi et al. 2024).
Sustainable land management practices must balance ecological and economic considerations. Research should focus on analyzing the role of controlled burns and other fuel reduction measures in enhancing ecosystem health while reducing wildfire risks. Additionally, assessing the economic feasibility of these practices by exploring market opportunities for biomass and other forest products derived from fuel management operations will ensure long-term sustainability (Wang et al. 2024, Woolsey et al. 2024).
Transdisciplinary research initiatives are critical for fostering collaboration among disciplines such as forestry, meteorology, ecology, and fire science. Such multidisciplinary approaches can result in comprehensive fire management plans that address the complex factors influencing wildfire behaviour (Wang et al. 2024, Woolsey et al. 2024).
Furthermore, encouraging public-private partnerships can stimulate innovation in fire prevention technologies and promote resource sharing among government entities, non-profit organisations, and private enterprises. These partnerships can play a significant role in developing and implementing effective fire safety protocols (Barrett et al. 2024, Golleru 2024, Zulkarnaini et al. 2024).
The role of policy-making cannot be overstated in ensuring the integration of these strategies into actionable frameworks. Research should prioritize advocating for policies that promote sustainable land use and community-driven fire safety measures. Incorporating fire safety into broader land-use planning processes and evaluating the effectiveness of existing policies will help identify gaps and provide opportunities for improvement. Future policies must be adaptive, incorporating recommendations from this review to address the evolving dynamics of wildfire risks (Barrett et al. 2024, Shahi 2024, Sukawi et al. 2024, Zulkarnaini et al. 2024).
By addressing these research areas, future studies can significantly enhance wildfire prevention techniques, ensuring resilience and practical solutions to meet escalating wildfire risks. Supported by strong policies and collaborative efforts among stakeholders, these advancements will create a sustainable and effective framework for wildfire management.
Figure 3. Suggested future research and development.
Author Contributions
Syed Shaheer Hassan and Guang Yang designed the article. Muhammad Sabir, Laila Noor, Haseeb Ahmad and Syed Shaheer Hassan wrote the research paper and interpreted the findings. Syed Shaheer Hassan, Sana Tahir and Guang Yang made corrections to the draft. All the authors have read the work and given their endorsement.
Funding
The National Key Research and Development Program of China (2022YFC3003104).
Conflicts of Interest
The authors declare no conflict of interest.
REFERENCES
Adams MA, Neumann M, 2023. Litter accumulation and fire risks show direct and indirect climate-dependence at continental scale. Nat Commun 14: 1515. https://doi.org/10.1038/s41467-023-37166-9.
Agbeshie AA, Abugre S, Atta-Darkwa T, Awuah R, 2022. A review of the effects of forest fire on soil properties. J Forestry Res 33: 1419-1441. https://doi.org/10.1007/s11676-022-01475-4.
Ahmad K, Khan MS, Ahmed F, Driss M, Boulila W, Alazeb A, Alsulami M, Alshehri MS, Ghadi YY Ahmad J, 2023. FireXnet: an explainable AI-based tailored deep learning model for wildfire detection on resource-constrained devices. Fire Ecol 19(1): 1-19. https://doi.org/10.1186/s42408-023-00216-0.
Alberta Government, 2012. How different tree species impact the spread of wildfire. Available online: https://www1.agric.gov.ab.ca/$department/deptdocs.nsf/ba3468a2a8681f69872569d60073fde1/791acf3f5b90d47187257f6400814ac3/$FILE/tree-species-impact-wildfire-aug03-2012.pdf (5 June 2024).
Ali MF, Jayakody DNK, Muthuchidambaranathan P, 2024. Revolutionizing Firefighting: UAV-Based Optical Communication Systems for Wildfires. Photonics 11: 656. https://doi.org/10.3390/photonics11070656.
Alkhatib A, Jaber K, Alzo’by H, Abdallah M, Salah M, 2024. Exploring Progress in Forest Fire Detection, Prediction, and Behavior: An In-Depth Survey. International Journal of Computing and Digital Systems 15: 789-800.
Allison RS, Johnston JM, Craig G, Jennings S, 2016. Airborne Optical and Thermal Remote Sensing for Wildfire Detection and Monitoring. Sensors 16(8): 1310. https://doi.org/10.3390/s16081310.
Alon O, Rabinovich S, Fyodorov C, Cauchard JR, 2021. Drones in firefighting: A user-centered design perspective. In: Proceedings of the 23rd International Conference on Mobile Human-Computer Interaction (MobileHCI '21), Toulouse, France, 27 September – 1 October 2025. Association for Computing Machinery, New York, USA, 1–11. https://doi.org/10.1145/3447526.3472030.
Alonso L, Rodríguez-Dorna A, Picos J, Costas F, Armesto J, 2024. Automatic differentiation of Eucalyptus species through Sentinel-2 images, Worldview-3 images and LiDAR data. ISPRS J Photogramm 207: 264-281. https://doi.org/10.1016/j.isprsjprs.2023.12.010.
Alrabia A, Alsweleh F,Ghadanfer H, 2020. Fire Fighting Robot (Chernobyl Bot). American University of Kuwait, Salmiya, Kuwait. Available online: https://dspace.auk.edu.kw/handle/11675/8060.
Amberson T, Heagele T, Wyte-Lake T, Couig MP, Bell S A, Mammen MJ, Wells V, Castner J, 2023. Social support, educational, and behavioral modification interventions for improving household disaster preparedness in the general community-dwelling population: a systematic review and meta-analysis. Frontiers in Public Health 11: 1257714. https://doi.org/10.3389/fpubh.2023.1257714.
Arango E, Jiménez P, Nogal M, Sousa HS, Stewart MG, Matos JC, 2024. Enhancing infrastructure resilience in wildfire management to face extreme events: Insights from the Iberian Peninsula. Climate Risk Management 44: 100595. https://doi.org/10.1016/j.crm.2024.100595.
Arienti MC, Cumming SG, Boutin S, 2006. Empirical models of forest fire initial attack success probabilities: the effects of fuels, anthropogenic linear features, fire weather, and management. Can J Forest Res 36: 3155-3166. https://doi.org/10.1139/x06-188.
Arora K, Kumar H, Singh RR, 2023. Autonomous Fire Fighting Robot. In: 2023 International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), Ghaziabad, India, 20-21 April 2023. IEEE, Piscataway, USA, 431-435. https://doi.org/10.1109/CICTN57981.2023.10140705.
Ascoli D, Plana E, Oggioni SD, Tomao A, Colonico M, Corona P, Giannino F, Moreno M, Xanthopoulos G, Kaoukis K, 2023. Fire-smart solutions for sustainable wildfire risk prevention: Bottom-up initiatives meet top-down policies under EU green deal. Int J Disast Risk Re 92: 103715. https://doi.org/10.1016/j.ijdrr.2023.103715.
Azevedo J, Neves S, Santos IN, 2024. Broadcasting Resilience: Developing Wildfire Readiness Through Student-Driven Radio Programs. In: Proceedings of the ISCRAM Conference, Münster, Germany, 25-29 May 2024. ISCRAM, Brussels, Belgium. https://doi.org/10.59297/gsdxk714.
Barber QE, Jain P, Whitman E, Thompson DK, Guindon L, Parks SA, Wang X, Hethcoat MG, Parisien MA, 2024. The Canadian Fire Spread Dataset. Sci Data 11: 764. https://doi.org/10.1038/s41597-024-03436-4.
Barrett K, Economics H, Cohen J, Pyne S and Quarles S, 2024. Redefining the Urban Wildfire Problem in the West. Headwaters Economics, Bozeman, USA. Available online: https://headwaterseconomics.org/natural-hazards/redefining-the-urban-wildfire-problem-in-the-west/.
Batcheler M, Smith MM, Swanson ME, Ostrom M, Carpenter-Boggs L, 2024. Assessing silvopasture management as a strategy to reduce fuel loads and mitigate wildfire risk. Sci Rep 14: 5954. https://doi.org/10.1038/s41598-024-56104-3.
Bhattarai D, Lucieer A, 2024. Optimising camera and flight settings for ultrafine resolution mapping of artificial night-time lights using an unoccupied aerial system. Drone Systems and Applications 12: 1-11. https://doi.org/10.1139/dsa-2023-0086.
Blake R, Jacob K, Yohe G, Zimmerman R, Manley D, Solecki W, Rosenzweig C, 2019. New York City Panel on Climate Change 2019 Report Chapter 8: Indicators and Monitoring. Ann NY Acad Sci 1439: 230-279. https://doi:10.1111/nyas.14014.
Bogue R, 2021. The role of robots in firefighting. Ind Robot 48: 174-178. https://doi.org/10.1108/IR-10-2020-0222.
Boroujeni SPH, Razi A, Khoshdel S, Afghah F, Coen JL, O’Neill L, Fule P, Watts A, Kokolakis NMT, Vamvoudakis K G, 2024. A comprehensive survey of research towards AI-enabled unmanned aerial systems in pre-, active-, and post-wildfire management. Inform Fusion 108: 102369. https://doi.org/10.1016/j.inffus.2024.102369.
Brodie EG, Knapp EE, Brooks WR, Drury SA, Ritchie MW, 2024. Forest thinning and prescribed burning treatments reduce wildfire severity and buffer the impacts of severe fire weather. Fire Ecol 20: 17. https://doi.org/10.1186/s42408-023-00241-z.
Bui DT, Pradhan B, Nampak H, Bui QT, Tran QA, Nguyen QP, 2016. Hybrid artificial intelligence approach based on neural fuzzy inference model and metaheuristic optimization for flood susceptibilitgy modeling in a high-frequency tropical cyclone area using GIS. J Hydrol 540: 317-330. https://doi.org/10.1016/j.jhydrol.2016.06.027.
Calderon NB, Rickey M, Baptista K, Bardsley O, Snowhook J, 2024. Eco-Cultural Restoration of Mouralherwaqh: Site Description and Invasive Species Treatment Plan in King Salmon, California. Cal Poly Humboldt, Arcata, USA. Available online: https://digitalcommons.humboldt.edu/capstone/20.
Campbell SL, Brady JJ, Anderson CC, Ziou M, Sinclair D, Johnston FH, Jones PJ, 2024. Community education on the health impacts of bushfires: Evaluation of an online pilot short course in Tasmania, Australia. Int J Disast Risk Re 101: 104227. https://doi.org/10.1016/j.ijdrr.2023.104227.
Carta F, Zidda C, Putzu M, Loru D, Anedda M, Giusto D, 2023. Advancements in Forest Fire Prevention: A Comprehensive Survey. Sensors 23: 6635. https://doi.org/10.3390/s23146635.
Chen X, Ding H, Li J, Wang L, Li L, Xi M, Zhao L, Shi Z, Liu Z, 2024. Remote sensing retrieval of aerosol types in China using geostationary satellite. Atmos Res 299: 107150. https://doi.org/10.1016/j.atmosres.2023.107150.
Cilli R, Elia M, D'Este M, Giannico V, Amoroso N, Lombardi A, Pantaleo E, Monaco A, Sanesi G, Tangaro S, Bellotti R, Lafortezza R, 2022. Explainable artificial intelligence (XAI) detects wildfire occurrence in the Mediterranean countries of Southern Europe. Sci Rep 12: 16349. https://doi.org/10.1038/s41598-022-20347-9.
Ciumasu IM, Costica M, Secu CV, Gurjar BR, Ojha CSP, 2013. Adapting to Climate Change: Technologies, Perceptions, Education, and Perspectives. In: Surampalli RY, Zhang TC, Ojhba CSP, Gurjar B, Tyagi RD, Kao CM (eds) Climate Change Modeling, Mitigation, and Adaptation. ASCE, Reston, USA, 496-518. https://doi.org/10.1061/9780784412718.ch18.
Clements R, Haggar J, Quezada A, Torres J, 2011. Technologies for Climate Change Adaptation –Agriculture Sector. In: Zhu X (ed) TNA Guidebook Series. UNEP Risø Centre, Roskilde, Denmark. Available online: https://tech-action.unepccc.org/wp-content/uploads/sites/2/2019/05/tna-guidebook-adaptationagriculture.pdf.
Collins L, Guindon L, Lloyd C, Taylor S, White S, 2024. Fractional cover mapping of wildland-urban interface fuels using Landsat, Sentinel 1 and PALSAR imagery. Remote Sens Environ 308: 114189. https://doi.org/10.1016/j.rse.2024.114189.
Copes-Gerbitz K, Dickson-Hoyle S, Ravensbergen SL, Hagerman SM, Daniels LD, Coutu J, 2022. Community engagement with proactive wildfire management in British Columbia, Canada: perceptions, preferences, and barriers to action. Frontiers in Forests and Global Change 5: 829125. https://doi.org/10.3389/ffgc.2022.829125.
Crockett JL, Hurteau MD, 2024. Climate limits vegetation green-up more than slope, soil erodibility, and immediate precipitation following high-severity wildfire. Fire Ecol 20: 41. https://doi.org/10.1186/s42408-024-00264-0.
Cui X, Alam MA, Perry GL, Paterson AM, Wyse SV, Curran TJ, 2019. Green firebreaks as a management tool for wildfires: Lessons from China. J Environ Manage 233: 329-336. https://doi.org/10.1016/j.jenvman.2018.12.043.
Curran TJ, Perry GL, Wyse SV, Alam MA, 2017. Managing fire and biodiversity in the wildland-urban interface: A role for green firebreaks. Fire 1(1): 3. https://doi.org/10.3390/fire1010003.
Czyczula Rudjord Z, Reid MJ, Schwermer CU, Lin Y, 2022. Laboratory development of an AI system for the real-time monitoring of water quality and detection of anomalies arising from chemical contamination. Water 14(16): 2588. https://doi.org/10.3390/w14162588.
Davis KT, Peeler J, Fargione J, Haugo RD, Metlen KL, Robles MD, Woolley T, 2024. Tamm review: A meta-analysis of thinning, prescribed fire, and wildfire effects on subsequent wildfire severity in conifer dominated forests of the Western US. Forest Ecol Manag 561: 121885. https://doi.org/10.1016/j.foreco.2024.121885.
Dhiman A, Shah N, Adhikari P, Kumbhar S, Dhanjal IS, Mehendale N, 2020. Fire fighter robot with deep learning and machine vision. SSRN Electronic Journal. Available online: https://dx.doi.org/10.2139/ssrn.3633609.
Dobrich EOR, 2024. Perspectives on Advancing Gender and Environmental Justice: Implications and Applications of a Conceptual Model for Supporting Women’s Environmental Leadership. Journal of Academic Perspectives 2024(3): 130-154. https://www.journalofacademicperspectives.com/back-issues/volume-2024/volume-2024-no-3/.
Domínguez M, Prada MA, Reguera P, Fuertes JJ, Alonso S, Morán A, 2017. Cybersecurity training in control systems using real equipment. IFAC-Papers Online 50(1): 12179-12184. https://doi.org/10.1016/j.ifacol.2017.08.2151.
Dong Z, Zhao F, Wang G, Tian Y, Li H, 2024. A Deep Learning Framework: Predicting Fire Radiative Power from the Combination of Polar-Orbiting and Geostationary Satellite Data During Wildfire Spread. IEEE J Sel Top Appl 17: 10827–10841. https://doi.org/10.1109/JSTARS.2024.3403146.
Doolin DM, Sitar N, 2005. Wireless sensors for wildfire monitoring. In: Proc. of SPIE Symposium on Smart Structures and Materials, San Diego, USA, 7-10 March 2005. SPIE, Bellingham, USA, 477-484.
Drews FA, Musters A, Siebeneck LK, Cova TJ, 2014. Environmental factors that influence wildfire protective-action recommendations. International Journal of Emergency Management 10: 153-168. https://doi.org/10.1504/IJEM.2014.066187.
Dufek J, Xiao X, Murphy R, 2017. Visual pose stabilization of tethered small unmanned aerial system to assist drowning victim recovery. In: 2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR), Shanghai, China, 11-13 October 2017. IEEE, Piscataway, USA, 116-122. https://doi.org/10.1109/SSRR.2017.8088149.
Elliott TM, 2022. Learning from wildfire: understanding the social dimensions of community response. MSc Thesis, School of Environment and Sustainability, Saskatoon, Canada, 188.
Elliott TM, Reed MG, Fletcher A J, 2023. Learning from wildfire: co-creating knowledge using an intersectional feminist standpoint methodology. Frontiers in Environmental Science 11: 1249598. https://doi.org/10.3389/fenvs.2023.1249598.
Elsworth G, Gilbert J, Rhodes A, Goodman H, 2009. Community safety programs for bushfire: what do they achieve, and how? Australian Journal of Emergency Management 24(2): 17-25. https://search.informit.org/doi/10.3316/ielapa.878221554870110.
Eriksen C, 2013. Gender and wildfire: Landscapes of uncertainty. 1st Edition. Routledge, Abingdon-on-Thames, UK. https://doi.org/10.4324/9781315779508.
Esmzadeh M, 2024. Innovative Approaches to Bushfire Management and Recovery. EarthArXiv Preprint. Available online: https://doi.org/10.31223/X5X12W.
Espinosa J, Dejene T, Guijarro M, Cerdá X, Madrigal J, Martín-Pinto P, 2023. Fungal diversity and community composition responses to the reintroduction of fire in a non-managed Mediterranean shrubland ecosystem. Forest Ecosystems 10: 100110. https://doi.org/10.1016/j.fecs.2023.100110.
Fan D, Biswas A, Ahrens J P, 2024. Explainable AI Integrated Feature Engineering for Wildfire Prediction. arXiv preprint: 2404.01487. Available online: https://doi.org/10.48550/arXiv.2404.01487.
Fazeli S, Haghani M, Mojtahedi M, Rashidi TH, 2024. The role of individual preparedness and behavioural training in natural hazards: A scoping review. Int J Disast Risk Re 105: 104379. https://doi.org/10.1016/j.ijdrr.2024.104379.
Fernández-Blanco CR, Górriz-Mifsud E, Prokofieva I, Muys B, Parra C, 2022. Blazing the trail: Social innovation supporting wildfire-resilient territories in Catalonia (Spain). Forest Policy Econ 138: 102719. https://doi.org/10.1016/j.forpol.2022.102719.
Ferreira AJD, Alegre SP, Coelho COA, Shakesby RA, Páscoa FM, Ferreira CSS, Keizer JJ, Ritsema C, 2015. Strategies to prevent forest fires and techniques to reverse degradation processes in burned areas. Catena 128: 224-237. https://doi.org/10.1016/j.catena.2014.09.002.
Flannigan MD, Amiro BD, Logan KA, Stocks BJ, Wotton BM, 2006. Forest fires and climate change in the 21 st century. Mitig Adapt Strat Glob Change 11: 847-859. https://doi.org/10.1007/s11027-005-9020-7.
Fraga E, Cortés A, Margalef T, Hernández P, Carrillo C, 2024. Cloud-based urgent computing for forest fire spread prediction. Environ Modell Soft 177: 106057. https://doi.org/10.1016/j.envsoft.2024.106057.
Frandsen M, Paton D, Sakariassen K, 2011. Fostering community bushfire preparedness through engagement and empowerment. The Australian Journal of Emergency Management 26(2): 23-30. https://search.informit.org/doi/10.3316/ielapa.140692861394554.
Fried JS, Gilless JK, Riley WJ, Moody TJ, Simon de Blas C, Hayhoe K, Moritz M, Stephens S, Torn M, 2008. Predicting the effect of climate change on wildfire behavior and initial attack success. Climate Change 87: 251-264. https://doi.org/10.1007/s10584-007-9360-2.
Garcia LP, Furano G, Ghiglione M, Zancan V, Imbembo E, Ilioudis C, Clemente C, Trucco P, 2024. Advancements in on-board processing of synthetic aperture radar (SAR) data: enhancing efficiency and real-time capabilities. IEEE J Sel Top Appl 17: 16625-16645 https://doi.org/10.1109/JSTARS.2024.3406155.
Giannakidou S, Radoglou-Grammatikis P, Lagkas T, Argyriou V, Goudos S, Markakis EK, Sarigiannidis P, 2024. Leveraging the power of internet of things and artificial intelligence in forest fire prevention, detection, and restoration: A comprehensive survey. Internet of Things 26: 101171. https://doi.org/10.1016/j.iot.2024.101171.
Giorgi D, 2024. Design of a satellite-based solution to the wildfires problem in the Mediterranean region. MSc Thesis. Polytechnic University of Turin, Turin, Italy, 111.
Girona-García A, Vieira DC, Silva J, Fernández C, Robichaud PR, Keizer JJ, 2021. Effectiveness of post-fire soil erosion mitigation treatments: A systematic review and meta-analysis. Earth-Sci Rev 217: 103611. https://doi.org/10.1016/j.earscirev.2021.103611.
Golleru MSSY, 2024. Advancing Wildfire Mitigation Through Public-Private Partnership- A Game Theoretic Framework. MSc Thesis, State University of Buffalo, New York, USA.
Gonzalez S, Ghermandi L, 2024. How to define the wildland-urban interface? Methods and limitations: towards a unified protocol. Frontiers in Environmental Science 11: 1284631. https://doi.org/10.3389/fenvs.2023.1284631.
Guruprasad L, Yashwanth M, Prasad PV, Shreekara B, 2020. Autonomous Fire Fighting Robot. International Journal of Research in Engineering, Science and Management 3(7): 393-396. https://journal.ijresm.com/index.php/ijresm/article/view/106.
Hanes CC, Wang X, Jain P, Parisien MA, Little JM, Flannigan MD, 2019. Fire-regime changes in Canada over the last half century. Can J Forest Res 49(3): 256-269. https://doi.org/10.1139/cjfr-2018-0293.
Haney BS, 2019. AI patents: A data driven approach. Chi-Kent J Intell Prop 19: 407. https://scholarship.kentlaw.iit.edu/ckjip/vol19/iss3/6/.
Harrower J, 2024. Mount Veeder Fire Safe Council VTP # 2024-03: Project Specific Analysis to the CalVTP PEIR. Frontier Resource Management, Napa, USA. Available online: https://bof.fire.ca.gov/media/riwnxxoe/psa-mvfsc-vtp-2024-03.pdf.
He K, Shen X, Anagnostou EN, 2024. A global forest burn severity dataset from Landsat imagery (2003–2016). Earth Syst Sci Data 16: 3061-3081. https://doi.org/10.5194/essd-16-3061-2024.
Hensley J, 1975. Fire Marshal orders stairwell (1974-1975). Eastern Progress 53(20): 1. Available online: https://encompass.eku.edu/progress_1974-75/20/.
Hood S, Abrahamson I, Cansler CA, 2018. Fire resistance and regeneration characteristics of Northern Rockies tree species. Missoula Fire Sciences Laboratory, Missoula, USA. Available online: https://nrfirescience.org/resource/18268.
Hopkins JR, Semenova-Nelsen T, Sikes BA, 2021. Fungal community structure and seasonal trajectories respond similarly to fire across pyrophilic ecosystems. FEMS Microbiol Ecol 97: fiaa219. https://doi.org/10.1093/femsec/fiaa219.
Hostetter H, Naser M, Randall K, Murray-Tuite P, 2024. Evacuation preparedness and intellectual disability: Insights from a university fire drill. Journal of Building Engineering 84: 108578. https://doi.org/10.1016/j.jobe.2024.108578.
Hötte K, Jee SJ, 2022. Knowledge for a warmer world: A patent analysis of climate change adaptation technologies. Technol Forecast Soc 183: 121879. https://doi.org/10.1016/j.techfore.2022.121879.
Hunter JD, 2024. Assessing Engine Hot Fire Data for Human Spaceflight Applications. In: 71st JANNAF Propulsion Meeting (JPM), Oklahoma City, USA, 6-10 May 2024. JDOC, Columbia, USA. https://ntrs.nasa.gov/citations/20240003636.
Isabella G, 2024. Foraging In Times of Crises: A Feminist Exploration of Narratives of Nature, Identity, and Environmental Engagement in the Practice of Foraging in the Swedish Context. MSc Thesis. Centre for Gender Research, Uppsala, Sweden, 148.
Jaafari A, Zenner EK, Panahi M, Shahabi H, 2019. Hybrid artificial intelligence models based on a neuro-fuzzy system and metaheuristic optimization algorithms for spatial prediction of wildfire probability. Agr Forest Meteorol 266-267: 198-207. https://doi.org/10.1016/j.agrformet.2018.12.015.
James GL, Ansaf RB, Al Samahi SS, Parker RD, Cutler JM, Gachette RV, Ansaf BI, 2023. An efficient wildfire detection system for ai-embedded applications using satellite imagery. Fire 6: 169. https://doi.org/10.3390/fire6040169.
Kang Y, Im J, 2024. Mitigating underestimation of fire emissions from the Advanced Himawari Imager: A machine learning and multi-satellite ensemble approach. Int J Appl Earth Obs 128: 103784. https://doi.org/10.1016/j.jag.2024.103784.
Karp AT, Koerner SE, Hempson GP, Abraham JO, Anderson TM, Bond WJ, Burkepile DE, Fillion EN, Goheen JR, Guyton JA, 2024. Grazing herbivores reduce herbaceous biomass and fire activity across African savannas. Ecol Lett 27(6): e14450. https://doi.org/10.1111/ele.14450.
Kendell A, Galloway A, Milligan C, 2023. The Path of Flames: Understanding and Responding to Fatal Wildfires. 1st Edition. CRC Press, Boca Raton, USA. https://doi.org/10.4324/9781003168010.
Kerns BK, Day MA, 2024. Long‐term frequent fire and cattle grazing alter dry forest understory vegetation. Ecol Appl 34(5): e2972. https://doi.org/10.1002/eap.2972.
Kim S, Lee W, Park YS, Lee HW, Lee YT, 2016. Forest fire monitoring system based on aerial image. In: 2016 3rd International Conference on Information and Communication Technologies for Disaster Management (ICT-DM), Vienna, Austria, 13-15 December 2016. IEEE, Piscataway, USA, 1-6. https://doi.org/10.1109/ICT-DM.2016.7857214.
Kokosza A, Wrede H, Gonzalez Esparza D, Makowski M, Liu D, Michels DL, Pirk S, Palubicki W, 2024. Scintilla: Simulating Combustible Vegetation for Wildfires. ACM Trans Graph 43(4): 1-21. https://doi.org/10.1145/3658192.
Kreider MR, Higuera PE, Parks SA, Rice WL, White N, Larson AJ, 2024. Fire suppression makes wildfires more severe and accentuates impacts of climate change and fuel accumulation. Nat Commun 15: 2412. https://doi.org/10.1038/s41467-024-46702-0.
Kremens RL, Smith AM, Dickinson MB, 2010. Fire metrology: current and future directions in physics-based measurements. Fire Ecol 6: 13-35. https://doi.org/10.4996/fireecology.0601013.
Krishnambika N, Chandra G, Thiyaharajan M, Dimri BM, 2024. Can Forest Fire Cognizance Garner Community Support for Fire Prevention? Evidence from the Sal Forest of Northern India. Hum Ecol 52: 579-589. https://doi.org/10.1007/s10745-024-00518-0.
Lee K, Kim D, Chung D, Lee S, 2024. Application of Optimal Scheduling for Synthetic Aperture Radar Satellite Constellation: Multi-Imaging Mission in High-Density Regional Area. Aerospace 11(4): 280. https://doi.org/10.3390/aerospace11040280.
Leslie P, Follansbee J, Watson T, Jordan S, Wiley L, Jacobs E, Driggers R, 2024. Imaging sensor band comparison for situation awareness in wildfires. Appl Optics 63(20): 5244-5255. https://doi.org/10.1364/AO.521771.
Li S, Yun J, Feng C, Gao Y, Yang J, Sun G, Zhang D, 2023. An indoor autonomous inspection and firefighting robot based on slam and flame image recognition. Fire 6(3): 93. https://doi.org/10.3390/fire6030093.
Li X, Vázquez-López A, Sánchez del Río Sáez J, Wang DY, 2022. Recent advances on early-stage fire-warning systems: mechanism, performance, and perspective. Nano-Micro Lett 14: 197. https://doi.org/10.1007/s40820-022-00938-x.
Li Y, Hua J, Zhao G, Yin J, 2024. Design and Simulation of Front-End Actuators for Fire Barrier Opening Equipment. In: 2024 International Conference on Electrical Drives, Power Electronics & Engineering (EDPEE), Athens, Greece, 27-29 February 2024. IEEE, Piscataway, USA 1006-1010. https://doi.org/10.1109/EDPEE61724.2024.00192.
Li Z, Kaufman YJ, Ichoku C, Fraser R, Trishchenko A, Giglio L, Jin J, Yu X, 2001. A review of AVHRR-based active fire detection algorithms: Principles, limitations, and recommendations. In: Ahern F, Goldammer JG, Justice C (eds) Global and Regional Vegetation Fire Monitoring from Space, Planning and Coordinated International Effort. SPB Academic Publishing, The Hague, The Netherlands, 199-225.
Liang H, Zhang M, Wang H, 2019. A neural network model for wildfire scale prediction using meteorological factors. IEEE Access 7: 176746-176755. https://doi.org/10.1109/ACCESS.2019.2957837.
Liu Q, Li X, Zhang H, Ren J, Yang S, Cao L, Liang J, Ling S, 2022. Intellisense silk fibroin ionotronic batteries for wildfire detection and alarm. Nano Energy 101: 107630. https://doi.org/10.1016/j.nanoen.2022.107630.
Liz-López H, Huertas-Tato J, Pérez-Aracil J, Casanova-Mateo C, Sanz-Justo J, Camacho D, 2024. Spain on Fire: A novel wildfire risk assessment model based on image satellite processing and atmospheric information. Knowl-Based Syst 283: 111198. https://doi.org/10.1016/j.knosys.2023.111198.
Lv LY, Cao CF, Qu YX, Zhang GD, Zhao L, Cao K, Song P, Tang LC, 2022. Smart fire-warning materials and sensors: Design principle, performances, and applications. Mat Sci Eng R 150: 100690. https://doi.org/10.1016/j.mser.2022.100690.
MacCarthy J, Richter J, Tyukavina S, Weisse M and Harris N, 2023. The latest data confirms: Forest fires are getting worse. World Resources Institute, Washington, USA. Available online: https://www.wri.org/insights/global-trends-forest-fires.
Marjani M, Mesgari M, 2023. The large-scale wildfire spread prediction using a multi-kernel convolutional neural network. ISPRS Ann Photogramm Remote Sens Spatial Inf Sci 10(4): 483-488. https://doi.org/10.5194/isprs-annals-X-4-W1-2022-483-2023.
Marjani M, Mahdianpari M, Mohammadimanesh F, 2024. CNN-BiLSTM: A Novel Deep Learning Model for Near-Real-Time Daily Wildfire Spread Prediction. Remote Sens 16(8): 1467. https://doi.org/10.3390/rs16081467.
Martinez-Rozas S, Rey R, Alejo D, Acedo D, Cobano JA, Rodriguez-Ramos A, Campoy P, Merino L, Caballero F, 2021. Skyeye team at mbzirc 2020: A team of aerial and ground robots for gps-denied autonomous fire extinguishing in an urban building scenario. arXiv: 2104.01834. https://doi.org/10.48550/arXiv.2104.01834.
McDermott TE, Doty JD, O'Brien JG, Eppinger CR, Becejac T, 2020. Cybersecurity for Distance Relay Protection. Pacific Northwest National Laboratory, Richland, USA. https://doi.org/10.2172/1602545.
Michaelides RJ, Siegfried MR, Lovekin J, Berry K, Dugan B, Roth DL, 2024. Wildfire Progression Time Series Mapping with Interferometric Synthetic Aperture Radar (InSAR). IEEE Geosci Remote S 21: 1-5 https://doi.org/10.1109/LGRS.2024.3365994.
Mojir KY, Maceviciute E, Gatial E, Balogh Z, 2023. Citizen Engagement in wildfire management: needs, challenges, methods and framework. In: Proceedings of the 20th International ISCRAM Conference, Omaha, USA, 28-31 May 2025. ISCRAM, Brussels, Belgium, 761-772. https://doi.org/10.59297%2FDGPE8556.
Momeni M, Al-e SMJM, 2024. Collaboration of thermal sensors and drones in fighting wildfires; Mathematical model and heuristic approach. Internet of Things 26: 101168. https://doi.org/10.1016/j.iot.2024.101168.
Murray L, Castillo T, Carrasco J, Weintraub A, Weber R, de Diego IM, González JR, García-Gonzalo J, 2024. Advancing Forest Fire Prevention: Deep Reinforcement Learning for Effective Firebreak Placement. arXiv: 2404.08523. https://doi.org/10.48550/arXiv.2404.08523.
Neger C, Ponce-Calderón LP, de Lourdes Manzo-Delgado L, López-Madrid MA, 2024. Integrated fire management in a tropical biosphere reserve: Achievements and challenges. Int J Disast Risk Re 106: 104447. https://doi.org/10.1016/j.ijdrr.2024.104447.
Okoro SC, Lopez A, Unuriode A, 2024. A Synergistic Approach to Wildfire Prevention and Management Using AI, ML, and 5G Technology in the United States. arXiv: 2403.14657. https://doi.org/10.48550/arXiv.2403.14657.
Oliveira LF, Moreira AP , Silva MF, 2021. Advances in forest robotics: A state-of-the-art survey. Robotics 10: 53. https://doi.org/10.3390/robotics10020053.
Orgeira-Crespo P, Rey G, Ulloa C, Aguado-Agelet F, 2024. Unmanned Aerial Vehicles (UAVs) in Firefighting. In: Carou D, Sartal A, Davim JP (eds). 1st Edition. Springer Cham, Cham, Switzerland, 23-53. https://doi.org/10.1007/978-3-031-55571-8_2.
Palsa E, Bauer M, Evers C, Hamilton M, Nielsen-Pincus M, 2022. Engagement in local and collaborative wildfire risk mitigation planning across the western US—Evaluating participation and diversity in Community Wildfire Protection Plans. PLoS one 17(2): e0263757. https://doi.org/10.1371/journal.pone.0263757.
Panđa L, Radočaj D, Milošević R, 2024. Methods of Land Cover Classification Using Worldview-3 Satellite Images in Land Management. Tehnički glasnik 18(1): 142-147. https://doi.org/10.31803/tg-20221006135311.
Pastor E, Muñoz JA, Caballero D, Àgueda A, Dalmau F, Planas E, 2020. Wildland–urban interface fires in Spain: summary of the policy framework and recommendations for improvement. Fire Technol 56: 1831-1851. https://doi.org/10.1007/s10694-019-00883-z.
Paton D, Buergelt PT, 2012. Community Engagement and Wildfire Preparedness: The influence of community diversity. In: Paton D, Tedim F (eds) Wildfire and community: facilitating preparedness and resilience. Charles C. Thomas Publisher, Springfield, USA, 241-259.
Perumal R, Van Zyl TL, 2020. Comparison of recurrent neural network architectures for wildfire spread modelling. 2020 International SAUPEC/RobMech/PRASA Conference, Cape Town, South Africa, 29-31 January 2020. IEEE, Piscataway, USA, 1-6. https://doi.org/10.1109/SAUPEC/RobMech/PRASA48453.2020.9078028.
Plucinski MP, 2019. Fighting flames and forging firelines: Wildfire suppression effectiveness at the fire edge. Curr Forestry Rep 5: 1-19. https://doi.org/10.1007/s40725-019-00084-5.
Popović Z, Bojović S, Marković M, Cerdà A, 2021. Tree species flammability based on plant traits: A synthesis. Sci Total Environ 800: 149625. https://doi.org/10.1016/j.scitotenv.2021.149625.
Purnomo H, Puspitaloka D, Okarda B, Andrianto A, Qomar N, Sutikno S, Muhammad A, Basuki I, Jalil A, Prasetyo P, 2024. Community-based fire prevention and peatland restoration in Indonesia: A participatory action research approach. Environmental Development 50: 100971. https://doi.org/10.1016/j.envdev.2024.100971.
Radu VT, Kristensen AS, Mehmood S, 2019. Use of drones for firefighting operations. MSc Thesis. Aalborg University, Esbjerg, Denmark.
Rhodes CJ, 2024. Trees—Protectors against a Changing Climate. Ecological Civilization 1(2): 10002. https://doi.org/10.35534/ecolciviliz.2024.10002.
Riris H, Kauffman T, Falkowski M, Shuman J, Boland J, Martin MM, Lefer B, Seablom M, 2024. NASA’s Technology Development Program for Wildfire Science, Management, and Disaster Mitigation. In: IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 7-12 July 2024. IEEE, Piscataway, USA, 2365-2368. https://doi.org/10.1109/IGARSS53475.2024.10640639.
Roldán-Gómez JJ, González-Gironda E, Barrientos A, 2021. A survey on robotic technologies for forest firefighting: Applying drone swarms to improve firefighters’ efficiency and safety. Appl Sci 11(1): 363. https://doi.org/10.3390/app11010363.
Ryan B, Johnston KA, Taylor M, McAndrew R, 2020. Community engagement for disaster preparedness: A systematic literature review. Int J Disast Risk Re 49: 101655. https://doi.org/10.1016/j.ijdrr.2020.101655.
Sawant M, Pagar R, Zutshi D, Sadhukhan S, 2020. Fire detection and controlling robot using IoT. Advances in Machine Learning and Computational Intelligence: 567-577. https://doi.org/10.1007/978-981-15-5243-4_52.
Sayad YO, Mousannif H, Al Moatassime H, 2019. Predictive modeling of wildfires: A new dataset and machine learning approach. Fire Safety J 104: 130-146. https://doi.org/10.1016/j.firesaf.2019.01.006.
Schachtschneider CL, Strand EK, Launchbaugh KL, Jensen S, 2024. Targeted Cattle Grazing to Alter Fuels and Reduce Fire Behavior Metrics in Shrub-Grasslands. Rangeland Ecol Manag 96: 105-116. https://doi.org/10.1016/j.rama.2024.05.010.
Schiks TJ, Wotton BM, Martell DL, 2024. Remote Sensing Active Fire Detection Tools Support Growth Reconstruction for Large Boreal Wildfires. Fire 7(1): 26. https://doi.org/10.3390/fire7010026.
Schroeder W, Giglio L, Hall J, 2024. Collection 2 Visible Infrared Imaging Radiometer Suite (VIIRS): 375-m Active Fire Product User’s Guide. Version 1.0. NASA, Washington, USA.
Setiawan Y, Kustiyo K, Hudjimartsu SA, Purwanto J, Rovani R, Tosiani A, Usman AB, Kartika T, Indriasari N, Prasetyo LB, 2024. Evaluating Visible–Infrared Imaging Radiometer Suite Imagery for Developing Near-Real-Time Nationwide Vegetation Cover Monitoring in Indonesia. Remote Sens 16: 1958. https://doi.org/10.3390/rs16111958.
Shahi SB, 2024. Engagement of Armed Police Force, Nepal in Community-Based Disaster Management. MSc Thesis, Faculty of Humanities and Social Sciences, Kathmandu, Nepal. https://doi.org/10.13140/RG.2.2.19718.59204.
Shuhui L, Yan W, Zhidong S, Jien C, Dengyu Y, Yueyue H, Yitang J, Zhichao L, 2024. Fire resistance of 15 main economic tree species in Liangshan Prefecture, Sichuan, China. Chinese Journal of Applied Ecology 35(1): 203-211. https://doi.org/10.13287/j.1001-9332.202401.003.
Silva PS, Rodrigues JA, Nogueira J, Moura LC, Enout A, Cuiabália C, DaCamara CC, Pereira AA, Libonati R, 2024. Joining forces to fight wildfires: Science and management in a protected area of Pantanal, Brazil. Environ Sci Policy 159: 103818. https://doi.org/10.1016/j.envsci.2024.103818.
Sivakumar VL, Raju A, Sundaram A, 2024. Study of Forest Fire Severity through Normalized Burn Ratio Analysis using Remote Sensing. E3S Web of Conf 491: 01027. https://doi.org/10.1051/e3sconf/202449101027.
Soja A, 2024. Overview of the NASA Earth Action Strategies Wildland Fire Initiative. In: 7th International Fire Behavior and Fuels Conference, Tralee, Ireland, 15-19 April 2024. NASA, Washington, USAa.
Song Z, Wang X, Liu Y, Luo Y, Li Z, 2022. Allocation strategies of carbon, nitrogen, and phosphorus at species and community levels with recovery after wildfire. Front Plant Sci 13: 850353. https://doi.org/10.3389/fpls.2022.850353.
Speck O, Speck T, 2024. Is a Forest Fire a Natural Disaster? Investigating the Fire Tolerance of Various Tree Species—An Educational Module. Biomimetics 9(2): 114. https://doi.org/10.3390/biomimetics9020114.
Sukawi S, Hardiman G, Rukayah RS, 2024. Fire disaster preparedness in urban kampongs (Case study of Kampong Kulitan Semarang). AIP Conf Proc 2838(1): 040006. https://doi.org/10.1063/5.0184915.
Synolakis CE, Karagiannis GM, 2024. Wildfire risk management in the era of climate change. PNAS Nexus 3(5): pgae151. https://doi.org/10.1093/pnasnexus/pgae151.
Talavera NF, Roldán‐Gómez JJ, Martín F, Rodriguez‐Sanchez M, 2023. An autonomous ground robot to support firefighters' interventions in indoor emergencies. J Field Robot 40(3): 614-625. https://doi.org/10.1002/rob.22150.
Tephila MB, Aswini P, Abhinandhan S, Arjun K, 2022. Deep Learning and Machine Vision based Robot for Fire Detection and Control. In: 2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India, 21-23 September 2022. IEEE, Piscataway, USA, 965-970. https://doi.org/10.1109/ICIRCA54612.2022.9985698.
Tsujiguchi F, Coraiola DM, 2024. Mass Reforestation: Combining Tech and Nature to Fight Climate Change. Sustainability Stories. Sustainability Stories: 149-157. https://doi.org/10.1007/978-3-031-52300-7_17.
Tyukavina A, Potapov P, Hansen MC, Pickens AH, Stehman SV, Turubanova S, Parker D, Zalles V, Lima A, Kommareddy I, 2022. Global trends of forest loss due to fire from 2001 to 2019. Frontiers in Remote Sensing 3: 825190. https://doi.org/10.3389/frsen.2022.825190.
Valmiki S, Chavan M, Jolada S, Ladde M, Mateen M, 2024. Fire Fighting Drone Using Fire Extinguisher Ball. Journal of Scientific Research and Technology 2(7): 27-36.
Vázquez-Varela C, Martínez-Navarro J M and Abad-González L, 2022. Traditional fire knowledge: a thematic synthesis approach. Fire 5(2): 47. https://doi.org/10.3390/fire5020047.
Wade D D and Lundsford J, 1990. Fire as a forest management tool: prescribed burning in the southern United States. Unasylva 41(162): 28-38.
Wang H, Zhang K, Qin Z, Gao W, Wang Z, 2024. Refining Ecological Techniques for Forest Fire Prevention and Evaluating Their Diverse Benefits. Fire 7(4): 129. https://doi.org/10.3390/fire7040129.
Wang J, Guo H, Zhang N, Hou W, 2024. Research on key technologies of fire fighting UAV. In: Proceedings Volume 12978, Fourth International Conference on Geology, Mapping, and Remote Sensing (ICGMRS 2023), Wuhan, China, 14-16 April 2023. SPIE, Bellingham, USA, 263-270. https://doi.org/10.1117/12.3020862.
Wang X, Parisien MA, Taylor SW, Candau JN, Stralberg D, Marshall GA, Little JM, Flannigan MD, 2017. Projected changes in daily fire spread across Canada over the next century. Environ Res Lett 12: 025005. https://doi.org/10.1088/1748-9326/aa5835.
Wang Y, Gao F, Li M, 2024. Probabilistic Path Planning for UAVs in Forest Fire Monitoring: Enhancing Patrol Efficiency through Risk Assessment. Fire 7(7): 254. https://doi.org/10.3390/fire7070254.
Warnell K, Mason S, Siegle A, Merritt M, Olander L, 2023. Fact Sheet: Green Firebreaks, Nature-Based Solutions Roadmap Project. Nicholas Institute for Energy, Environment & Sustainability, Durham, USA. Available online: www.nicholasinstitute.duke.edu/roadmap.
Webb H, Burnap P, Procter R, Rana O, Stahl BC, Williams M, Housley W, Edwards A, Jirotka M, 2016. Digital wildfires: Propagation, verification, regulation, and responsible innovation. ACM Trans Inf Syst (TOIS) 34(3): 1-23. https://doi.org/10.1145/2893478.
Weir JR, Bidwell TG, Stevens R, Mustain J, 2012. Firebreaks for prescribed burning. Oklahoma State University, Stillwater, USA. Available online: http://osufacts.okstate.edu.
Wessinger C, 2024. Attempting to educate journalists about the role of cult essentialism in the Branch Davidian-federal agents conflict. In: Thomas A, Graham-Hyde E (eds) 'Cult' rhetoric in the 21st century: deconstructing the study of new religious movements. Bloomsbury Academic, New York: USA, 190.
Winker R, Payton A, Brown E, McDermott E, Freedman JH, Lenhardt C, Eaves LA, Fry RC, Rager JE, 2024. Wildfires and climate justice: future wildfire events predicted to disproportionally impact socioeconomically vulnerable communities in North Carolina. Frontiers in Public Health 12: 1339700. https://doi.org/10.3389/fpubh.2024.1339700.
Woolsey GA, Tinkham WT, Battaglia MA, Hoffman CM, 2024. Constraints on Mechanical Fuel Reduction Treatments in United States Forest Service Wildfire Crisis Strategy Priority Landscapes. J Forest 122(4): 335-351. https://doi.org/10.1093/jofore/fvae012.
Wu RY, Xie XC, Zheng YJ, 2024. Firefighting Drone Configuration and Scheduling for Wildfire Based on Loss Estimation and Minimization. Drones 8(1): 17. https://doi.org/10.3390/drones8010017.
Xu X, Zeng N, Li M, Liu Y, Li Q, 2024. Enhancing Fire Resilience in High-Tech Electronic Plants for Sustainable Development: Combining System Composition with Organizational Management. Sustainability 16(4): 1501. https://doi.org/10.3390/su16041501.
Yu B, Yang W, Li J, Xie W, Jin H, Liu R, Wang H, Zhuang X, Qi B and Liu S, 2021. Heat-triggered high-performance thermocells enable a self-powered forest fire alarm. J Mater Chem A 46: 26119-26126.
Zald HS, May CJ, Gray AN, North MP, Hurteau MD, 2024. Thinning and prescribed burning increase shade-tolerant conifer regeneration in a fire excluded mixed-conifer forest. Forest Ecol Manag 551: 121531. https://doi.org/10.1016/j.foreco.2023.121531.
Zhang G, Wang M, Liu K, 2019. Forest fire susceptibility modeling using a convolutional neural network for Yunnan province of China. Int J Disast Risk Sc 10: 386-403. https://doi.org/10.1007/s13753-019-00233-1.
Zhang P, Hu X, Ban Y, Nascetti A, Gong M, 2024. Assessing Sentinel-2, Sentinel-1, and ALOS-2 PALSAR-2 Data for Large-Scale Wildfire-Burned Area Mapping: Insights from the 2017–2019 Canada Wildfires. Remote Sens 16(3): 556. https://doi.org/10.3390/rs16030556.
Zhou X, Yue Q, Li KF, Fishbein E, Chen X, Tan L, Newman S, Fetzer E, Yung Y L, 2024. Characterizing fire and fire atmospheric states from space using collocated hyperspectral infrared sounding and narrow-band imagery. Remote Sens Environ 312: 114318. https://doi.org/10.1016/j.rse.2024.114318.
Zulkarnaini Z, Nasution M S, Meiwanda G, Istihat Y and Bedasari H, 2024. Peatland Management Policy: How to Build a Good Public-Private Partnership? Jurnal Ilmiah Peuradeun 12(1): 315-332. https://doi.org/10.26811/peuradeun.v12i1.985 .
© 2025 by the Croatian Forest Research Institute. This is an Open Access paper distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0).