Search

Forest fires cause extensive environmental damage, making early detection crucial for protecting both nature and communities. Advanced computer vision techniques can be used to detect smoke and fire. However, accurate detection of smoke and fire in forests is challenging due to different factors such as different smoke shapes, changing light, and similarity of smoke with other smoke-like elements such as clouds. This study explores recent YOLO (You Only Look Once) deep-learning object detection models YOLOv9, YOLOv10, and YOLOv11 for detecting smoke and fire in forest environments. The evaluation focuses on key performance metrics, including precision, recall, F1-score, and mean average precision (mAP), and utilizes two benchmark datasets featuring diverse instances of fire and smoke across different environments. The findings highlight the effectiveness of the small version models of YOLO (YOLOv9t, YOLOv10n, and YOLOv11n) in fire and smoke detection tasks. Among these, YOLOv11n demonstrated the highest performance, achieving a precision of 0.845, a recall of 0.801, a mAP@50 of 0.859, and a mAP@50-95 of 0.558. YOLOv11 versions (YOLOv11n and YOLOv11x) were evaluated and compared against several studies that employed the same datasets. The results show that YOLOv11x delivers promising performance compared to other YOLO variants and models.

To address the demands of efficient forest fire detection and suppression, an adaptive multiple UAV swarm collaborative firefighting strategy considering dynamic forest fire spread and resource constraints was proposed in this paper. The multiple UAV swarm adaptive information-driven collaborative search (MUSAIDCS) algorithm and the resource-limited firefighting model were established. A temperature change-driven adaptive step-length search strategy is proposed to improve the accuracy of the search and detection of fire spots. The critical water flow rate required for fire suppression is calculated to evaluate the firefight performance, and an emergency bidding algorithm is applied to enable multiple UAV swarms collaborative firefighting under limited resources, including different payloads per UAV and swarm number. The comparative simulations for four search strategies indicate that the MUSAIDCS search strategy can significantly reduce task completion time and improve firefighting efficiency compared with the other traditional search strategies. Increasing payload quantity per UAV and swarm number can further enhance task completion efficiency and firefighting effectiveness. This study demonstrates that a resource-constrained collaborative firefighting strategy enables the dynamic allocation of UAV swarm resources under limited conditions and then optimizes firefighting performance within constraints.

The paper addresses the issue of forest fires and critical points in activities related to extinguishing and transport of extinguishing agent to the fire site. With the increasing incidence of forest fires, there are also serious implications for the environment, ecosystems and communities. The relevance of this topic is indisputable, as forest fires are becoming more frequent and intense, with a consequent need for systematic analysis. In this paper, critical sites are identified and assessed, and a description of the equipment used to extinguish a particular fire is provided, with a description of the firefighting strategy in a difficult-to-access site in forest firefighting. This paper shows the effective solution in extinguishing forest fires and then in the design of measures to minimize this risk. We have also assessed the risk activities in this paper. The intent of this article is to show how to effectively extinguish a forest fire. The knowledge gained and recommendations made are aimed at improving firefighter preparedness, techniques and tactics to extinguish forest fires.

The assessment of fire effects in Aleppo pine forests is crucial for guiding the recovery of burnt areas. This study presents a methodology using UAV-LiDAR data to quantify malleability and elasticity in four burnt areas (1970, 1995, 2008 and 2015) through the statistical analysis of different metrics related to height structure and diversity (Height mean, 99th percentile and Coefficient of Variation), coverage, relative shape and distribution strata (Canopy Cover, Canopy Relief Ratio and Strata Percent Coverage), and canopy complexity (Profile Area and Profile Area Change). In general terms, malleability decreases over time in forest ecosystems that have been affected by wildfires, whereas elasticity is higher than what has been determined in previous studies. However, a particular specificity has been detected from the 1995 fire, so we can assume that there are other situational factors that may be affecting ecosystem resilience. LiDAR metrics and uni-temporal sampling between burnt sectors and control aids are used to understand community resilience and to identify the different recovery stages in P. halepensis forests.

Forest fires diminish forests’ ecological services, including carbon sequestration, water retention, air cooling, and recreation, while polluting the environment and endangering habitats. Despite considerable economic advancements, firefighting strategies remain less than optimal. This paper introduces the Bi-layer Predictive Ensemble (BIPE), an innovative machine learning model designed to enhance the accuracy and generalization of forest fire susceptibility mapping. BIPE integrates model-centric and data-driven strategies, employing automated methods such as 10-fold cross-validation and meta-learning to improve stability and generalization. During its 10-fold cross-validation, BIPE demonstrated excellent performance, with the Area Under the Curve (AUC) values ranging from 0.990 to 0.996 and accuracy levels consistently high, around 97%, underscoring its robust class separation ability and strong generalization across different datasets. Our results confirm that BIPE outperforms traditional high-performance models like Support Vector Machine (SVM), Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), Deep Neural Network (DNN), and Convolutional Neural Network (CNN), showcasing its practical effectiveness and reliability on the data of nonlinear, high-dimensional, and complex interactions. Additionally, our forest fire susceptibility maps offer valuable complementary information for German forest fire management authorities, enhancing their ability to assess and manage fire risks more effectively.

Forests are vital for life on Earth but are threatened by forest fires, which have significant impacts on climate change both locally and globally. This study examines a forest fire that lasted from 15 to 26 February 2019 in Karnataka, India, using the Weather Research and Forecasting model with Chemistry (WRF-Chem) model to analyze the effects and atmospheric spread of fire-emitted aerosols. Model simulations are analyzed to understand the horizontal and vertical transport and radiative effects of the fire. The results show high aerosol levels and smoke particles reaching up to 3.5 km altitude and above. The fire raised near-surface air temperatures by ~1–1.5 °C. The net atmospheric forcing due to the fire over the affected area ranged from approximately 10 to 14 W/m2, resulting in heating rates between about 0.002 and 0.005 K/day in the impacted region.

Forest fires pose a great threat to the global ecological environment as well as human life and the safety of property. Formulating effective policies for preventing forest fires is not only a scientific concern but also an urgent need for government management. Canada and China both have extensive forest areas but have different fire management strategies. Canada primarily focuses on fire suppression while China pays more attention on fire prevention. This difference led to significant discrepancies in the forest fire regimes between the two countries, providing an opportunity to explore the impact of fire management policies on forest fire. By analyzing the fire occurrences in Canada and China since 1990, combining the fire prevention funds and fire management strategies, this paper discussed the influence of different policies on fire occurrence. Previously, Canada’s forest suppression strategy has been widely recognized internationally, but recent widespread fires indicate that its fire management policy may still require further improvement to cope with future global warming. Although China’s fire prevention strategy can effectively control current forest fires, the lack of fundamental theories on forest fires and the backwardness of fire prevention technology and equipment may increase the likelihood of major forest fires in the future. As global warming continues to intensify in the future, the length of the forest fire season and the intensity of fires will increase, making it urgent to develop more effective forest fire prevention and suppression policies to achieve sustainable development.

The semi-arid Caatinga biome is particularly susceptible to fire dynamics. Periodic droughts amplify fire risks, while anthropogenic activities such as agriculture, pasture expansion, and land-clearing significantly contribute to the prevalence of fires. This research aims to evaluate the effectiveness of a fire detection model and analyze the spatial and temporal patterns of burned areas, providing essential insights for fire management and prevention strategies. Utilizing deep neural network (DNN) models, we mapped burned areas across the Caatinga biome from 1985 to 2023, based on Landsat-derived annual quality mosaics and minimum NBR values. Over the 38-year period, the model classified 10.9 Mha (12.7% of the Caatinga) as burned, with an average annual burned area of approximately 0.5 Mha (0.56%). The peak burned area reached 0.89 Mha in 2021. Fire scars varied significantly, ranging from 0.18 Mha in 1985 to substantial fluctuations in subsequent years. The most affected vegetation type was savanna, with 9.8 Mha burned, while forests experienced only 0.28 Mha of burning. October emerged as the month with the highest fire activity, accounting for 7266 hectares. These findings underscore the complex interplay of climatic and anthropogenic factors, highlighting the urgent need for effective fire management strategies.

Previous evaluation models for cultural relic buildings in relation to fire risk fail to consider the necessity for effective firefighting and rescue capabilities in complex forest environments. This paper incorporates variables, including those pertaining to forest fires and climatic conditions, into the assessment index system. The hierarchical analysis method and the local punishment-incentive variable weighting method are employed to introduce a compensation coefficient score. A model for the evaluation of firefighting and rescue capability in a continuous area of cultural relic buildings in conjunction with the surrounding forest environment has been developed. The firefighting and rescue capability of the Yuelu Mountain scenic spot was evaluated at 73.91 (level III) using the fixed weight method and 69.52 (level IV) using the variable weight method. The variable weight method proved to be a more accurate approach for evaluating the status and importance of dynamic targets, thus enabling a more precise evaluation of the comprehensive evaluation area. The evaluation results inform the formulation of targeted improvement measures for enhancing the firefighting and rescue capabilities of cultural relic buildings.

The present study aims to develop a random forest algorithm-based classifier to predict the occurrence of fire events using observed meteorological parameters a day in advance. We considered the skin temperature, the air temperature close to the surface, the humidity close to the surface level, and soil moisture as important meteorological factors influencing forest fire occurrence. Twenty additional parameters were derived based on these four parameters that account for the energy exchanged in sensible and latent forms and the change in parameters in recent trends. We used the mutual information approach to identify critical meteorological parameters that carry significant information about fire occurrence the next day. The top nine parameters were then fed as input to the random forest algorithm to predict fire/no fire the next day. The weighted data sampling and SMOTE techniques were employed to address the class imbalance in the fire data class. Both techniques correctly classified fire incidents well, given the meteorological input from the previous days. This study also showed that as the class imbalance increases to 1:9, the performance based on the precision, recall, F1 score, and accuracy are maximum, showing the model’s ability to perform with class imbalance. Both techniques helped the random forest algorithm forecast fire instances as the data sample size increased.

The number and area of forest fires in northern Europe have been dramatically reduced during the past century, and several fire-favoured species are now threatened. To promote the recovery of these species, prescribed burning is often used as a conservation measure, and to optimise the use of these conservation burns, knowledge is needed on suitable fire frequency, size and placement in the landscape. The aim of this study was to analyse the effect of recent fire history (12 yrs) on beetles sampled using smoke attraction traps at 21 forest sites in a 10,000 km2 region. We analysed the odds of finding a fire-favoured beetle species or individual among the beetles in each trap using a new spatiotemporal connectivity measure and compared the results to non-fire-favoured and saproxylic species. For fire-favoured beetles, both the number of species and individuals significantly increased with connectivity to previous fires, while the other two groups did not. The spatiotemporal connectivity that best explained the patterns suggests that fire-favoured beetles mainly respond to fires within a 2 km range up to 2–3 years after the fire. Hence, to preserve fire-favoured insects, prescribed fires must be close in space and time to other fires—whether prescribed or natural.

Wildfires are a critical driver of landscape transformation on Earth, representing a dynamic and ephemeral process that poses challenges for accurate early detection. To address this challenge, researchers have increasingly turned to deep learning techniques, which have demonstrated remarkable potential in enhancing the performance of wildfire detection systems. This paper provides a comprehensive review of fire detection using deep learning, spanning from 1990 to 2023. This study employed a comprehensive approach, combining bibliometric analysis, qualitative and quantitative methods, and systematic review techniques to examine the advancements in fire detection using deep learning in remote sensing. It unveils key trends in publication patterns, author collaborations, and thematic focuses, emphasizing the remarkable growth in fire detection using deep learning in remote sensing (FDDL) research, especially from the 2010s onward, fueled by advancements in computational power and remote sensing technologies. The review identifies “Remote Sensing” as the primary platform for FDDL research dissemination and highlights the field’s collaborative nature, with an average of 5.02 authors per paper. The co-occurrence network analysis reveals diverse research themes, spanning technical approaches and practical applications, with significant contributions from China, the United States, South Korea, Brazil, and Australia. Highly cited papers are explored, revealing their substantial influence on the field’s research focus. The analysis underscores the practical implications of integrating high-quality input data and advanced deep-learning techniques with remote sensing for effective fire detection. It provides actionable recommendations for future research, emphasizing interdisciplinary and international collaboration to propel FDDL technologies and applications. The study’s conclusions highlight the growing significance of FDDL technologies and the necessity for ongoing advancements in computational and remote sensing methodologies. The practical takeaway is clear: future research should prioritize enhancing the synergy between deep learning techniques and remote sensing technologies to develop more efficient and accurate fire detection systems, ultimately fostering groundbreaking innovations.

(1) Background: In recent years, forest fires have become increasingly frequent both domestically and internationally. The pollutants emitted from the burning of fuel have exerted considerable environmental stress. To investigate the influence of forest fires on the atmospheric environment, it is crucial to analyze the variations in PM2.5 emissions from various forest fuels under differing fire conditions. This assessment is essential for evaluating the effects on both the atmospheric environment and human health. (2) Methods: Indoor simulated combustion experiments were conducted on the branches, leaves, and bark of typical tree species in the Liangshui National Natural Reserve, including Pinus koraiensis (PK), Larix gmelinii (LG), Picea koraiensis (PAK), Betula platyphylla (BP), Fraxinus mandshurica (FM), and Populus davidiana (PD). The PM2.5 concentrations emitted by six tree species under various combustion states were measured and analyzed, reflecting the impact of moisture content on the emission of pollutants from fuel combustion, as indicated by the emission factors for pollutants. (3) Results: Under different fuel loading and moisture content conditions, the mass concentration values of PM2.5 emitted from the combustion of different organs of various tree species exhibit variability. (4) Conclusions: Among the various tree species, broad-leaved varieties release a greater quantity of PM2.5 compared to coniferous ones. A positive correlation exists between the moisture content of the fuel and the concentration of PM2.5; changes in moisture content notably influence PM2.5 levels. The emission of PM2.5 from fuel with varying loads increases exponentially. Utilizing the Response Surface Methodology (RSM) model for simulation, it was determined that both moisture content and fuel load exert a significant combined effect on the release of PM2.5 during combustion.

Fire detection and extinguishing systems are critical for safeguarding lives and minimizing property damage. These systems are especially vital in combating forest fires. In recent years, several forest fires have set records for their size, duration, and level of destruction. Traditional fire detection methods, such as smoke and heat sensors, have limitations, prompting the development of innovative approaches using advanced technologies. Utilizing image processing, computer vision, and deep learning algorithms, we can now detect fires with exceptional accuracy and respond promptly to mitigate their impact. In this article, we conduct a comprehensive review of articles from 2013 to 2023, exploring how these technologies are applied in fire detection and extinguishing. We delve into modern techniques enabling real-time analysis of the visual data captured by cameras or satellites, facilitating the detection of smoke, flames, and other fire-related cues. Furthermore, we explore the utilization of deep learning and machine learning in training intelligent algorithms to recognize fire patterns and features. Through a comprehensive examination of current research and development, this review aims to provide insights into the potential and future directions of fire detection and extinguishing using image processing, computer vision, and deep learning.

Forest fire is one of the dominant disturbances in the forests of Heilongjiang Province, China, and is one of the most rapid response predictors that indicate the impact of climate change on forests. This study calculated the Canadian FWI (Fire Weather Index) and its components from meteorological record over past years, and a linear model was built from the monthly mean FWI and monthly fire numbers. The significance test showed that fire numbers and FWI had a very pronounced correlation, and monthly mean FWI was suitable for predicting the monthly fire numbers in this region. Then FWI and its components were calculated from the SRES (IPCC Special Report on Emission Scenarios) A2 and B2 climatic scenarios, and the linear model was rebuilt to be suitable for the climatic scenarios. The results indicated that fire numbers would increase by 2.98–129.97% and −2.86–103.30% in the A2 and B2 climatic scenarios during 2020–2090, respectively. The monthly variation tendency of the FWI components is similar in the A2 and B2 climatic scenarios. The increasing fire risk is uneven across months in these two climatic scenarios. The monthly analysis showed that the FFMC (Fine Fuel Moisture Code) would increase dramatically in summer, and the decreasing precipitation in summer would contribute greatly to this tendency. The FWI would increase rapidly from the spring fire season to the autumn fire season, and the FWI would have the most rapid increase in speed in the spring fire season. DMC (Duff Moisture Code) and DC (Drought Code) have relatively balanced rates of increasing from spring to autumn. The change in the FWI in this region is uneven in space as well. In early 21st century, the FWI of the north of Heilongjiang Province would increase more rapidly than the south, whereas the FWI of the middle and south of Heilongjiang Province would gradually catch up with the increasing speed of the north from the middle of 21st century. The changes in the FWI across seasons and space would influence the fire management policy in this region, and the increasing fire numbers and variations in the FWI scross season and space suggest that suitable development of the management of fire sources and forest fuel should be conducted.

Forest fires pose a catastrophic threat to Earth’s ecology as well as threaten human beings. Timely and accurate monitoring of forest fires can significantly reduce potential casualties and property damage. Thus, to address the aforementioned problems, this paper proposed an unmanned aerial vehicle (UAV) based on a lightweight forest fire recognition model, Fire-Net, which has a multi-stage structure and incorporates cross-channel attention following the fifth stage. This is to enable the model’s ability to perceive features at various scales, particularly small-scale fire sources in wild forest scenes. Through training and testing on a real-world dataset, various lightweight convolutional neural networks were evaluated on embedded devices. The experimental outcomes indicate that Fire-Net attained an accuracy of 98.18%, a precision of 99.14%, and a recall of 98.01%, surpassing the current leading methods. Furthermore, the model showcases an average inference time of 10 milliseconds per image and operates at 86 frames per second (FPS) on embedded devices.

In the present research, the open-source WRF-SFIRE model has been used to carry out surface forest fire spread forecasting in the North Sikkim region of the Indian Himalayas. Global forecast system (GFS)-based hourly forecasted weather model data obtained through the National Centers for Environmental Prediction (NCEP) at 0.25 degree resolution were used to provide the initial conditions for running WRF-SFIRE. A landuse–landcover map at 1:10,000 scale was used to define fuel parameters for different vegetation types. The fuel parameters, i.e., fuel depth and fuel load, were collected from 23 sample plots (0.1 ha each) laid down in the study area. Samples of different categories of forest fuels were measured for their wet and dry weights to obtain the fuel load. The vegetation specific surface area-to-volume ratio was referenced from the literature. The atmospheric data were downscaled using nested domains in the WRF model to capture fire–atmosphere interactions at a finer resolution (40 m). VIIRS satellite sensor-based fire alert (375 m spatial resolution) was used as ignition initiation point for the fire spread forecasting, whereas the forecasted hourly weather data (time synchronized with the fire alert) were used for dynamic forest-fire spread forecasting. The forecasted burnt area (1.72 km2) was validated against the satellite-based burnt area (1.07 km2) obtained through Sentinel 2 satellite data. The shapes of the original and forecasted burnt areas matched well. Based on the various simulation studies conducted, an operational fire spread forecasting system, i.e., Sikkim Wildfire Forecasting and Monitoring System (SWFMS), has been developed to facilitate firefighting agencies to issue early warnings and carry out strategic firefighting.

This study investigates the dynamic deployment of unmanned aerial vehicles (UAVs) using edge computing in a forest fire scenario. We consider the dynamically changing characteristics of forest fires and the corresponding varying resource requirements. Based on this, this paper models a two-timescale UAV dynamic deployment scheme by considering the dynamic changes in the number and position of UAVs. In the slow timescale, we use a gate recurrent unit (GRU) to predict the number of future users and determine the number of UAVs based on the resource requirements. UAVs with low energy are replaced accordingly. In the fast timescale, a deep-reinforcement-learning-based UAV position deployment algorithm is designed to enable the low-latency processing of computational tasks by adjusting the UAV positions in real time to meet the ground devices’ computational demands. The simulation results demonstrate that the proposed scheme achieves better prediction accuracy. The number and position of UAVs can be adapted to resource demand changes and reduce task execution delays.

Forest fire is a significant global natural disaster, and unmanned aerial vehicles (UAVs) have gained attention in wildfire prevention for their efficient and flexible monitoring capabilities. Proper UAV patrol path planning can enhance fire-monitoring accuracy and response speed. This paper proposes a probabilistic path planning (PPP) module that plans UAV patrol paths by combining real-time fire occurrence probabilities at different points. Initially, a forest fire risk logistic regression model is established to compute the fire probabilities at different patrol points. Subsequently, a patrol point filter is applied to remove points with low fire probabilities. Finally, combining fire probabilities with distances between patrol points, a dynamic programming (DP) algorithm is employed to generate an optimal UAV patrol route. Compared with conventional approaches, the experimental results demonstrate that the PPP module effectively improves the timeliness of fire monitoring and containment, and the introduction of DP, considering that the fire probabilities and the patrol point filter both contribute positively to the experimental outcomes. Different combinations of patrol point coordinates and their fire probabilities are further studied to summarize the applicability of this method, contributing to UAV applications in forest fire monitoring and prevention.

This paper presents the results of studying changes in the main parameters and properties of soils in larch and pine forests growing on sandy soils of the Lena-Vilyui interfluve of Central Yakutia, where catastrophic forest fires occurred in 2021. According to the remote monitoring information system of Rosleskhoz, in 2021, almost 8.5 million hectares of forests burned in Yakutia, which is considered as one of the largest forest fires in Russia and in the world in that year. After the fire passes through the forest floor, the content of organic matter decreases as a result of combustion processes. The acidity of the soil changes towards its alkalization due to the entry of combustion products. Changes in soil profiles occur; turbation processes begin more intensively, which in turn change the natural distribution of soil indicator values such as the organic carbon content, the pH, and the number of exchangeable bases. Due to the sharp increase in heat supply after a fire, the depth of seasonal thawing in the soils of burnt larch forests increases by a quarter and by twofold in pine forests. With the beginning of the thawing of the seasonally frozen layer, all the soils experience waterlogging, and ground water occurs above the permafrost.

The timely and precise detection of forest fires is critical for halting the spread of wildfires and minimizing ecological and economic damage. However, the large variation in target size and the complexity of the background in UAV remote sensing images increase the difficulty of real-time forest fire detection. To address this challenge, this study proposes a lightweight YOLO model for UAV remote sensing forest fire detection (LUFFD-YOLO) based on attention mechanism and multi-level feature fusion techniques: (1) GhostNetV2 was employed to enhance the conventional convolution in YOLOv8n for decreasing the number of parameters in the model; (2) a plug-and-play enhanced small-object forest fire detection C2f (ESDC2f) structure was proposed to enhance the detection capability for small forest fires; (3) an innovative hierarchical feature-integrated C2f (HFIC2f) structure was proposed to improve the model’s ability to extract information from complex backgrounds and the capability of feature fusion. The LUFFD-YOLO model surpasses the YOLOv8n, achieving a 5.1% enhancement in mAP and a 13% reduction in parameter count and obtaining desirable generalization on different datasets, indicating a good balance between high accuracy and model efficiency. This work would provide significant technical support for real-time forest fire detection using UAV remote-sensing images.

In satellite imagery, clouds obstruct the ground information, directly impacting various downstream applications. Thus, cloud annotation/cloud detection serves as the initial preprocessing step in remote sensing image analysis. Recently, deep learning methods have significantly improved in the field of cloud detection, but training these methods necessitates abundant annotated data, which requires experts with professional domain knowledge. Moreover, the influx of remote sensing data from new satellites has further led to an increase in the cost of cloud annotation. To address the dependence on labeled datasets and professional domain knowledge, this paper proposes an automatic cloud annotation method for satellite remote sensing images, CloudAUE. Unlike traditional approaches, CloudAUE does not rely on labeled training datasets and can be operated by users without domain expertise. To handle the irregular shapes of clouds, CloudAUE firstly employs a convex hull algorithm for selecting cloud and non-cloud regions by polygons. When selecting convex hulls, the cloud region is first selected, and points at the edges of the cloud region are sequentially selected as polygon vertices to form a polygon that includes the cloud region. Then, the same selection is performed on non-cloud regions. Subsequently, the fast KD-Tree algorithm is used for pixel classification. Finally, an uncertainty method is proposed to evaluate the quality of annotation. When the confidence value of the image exceeds a preset threshold, the annotation process terminates and achieves satisfactory results. When the value falls below the threshold, the image needs to undergo a subsequent round of annotation. Through experiments on two labeled datasets, HRC and Landsat 8, CloudAUE demonstrates comparable or superior accuracy to deep learning algorithms, and requires only one to two annotations to obtain ideal results. An unlabeled self-built Google Earth dataset is utilized to validate the effectiveness and generalizability of CloudAUE. To show the extension capabilities in various fields, CloudAUE also achieves desirable results on a forest fire dataset. Finally, some suggestions are provided to improve annotation performance and reduce the number of annotations.

Given the escalating frequency and severity of global forest fires, it is imperative to develop advanced detection and segmentation technologies to mitigate their impact. To address the challenges of these technologies, the development of deep learning-based forest fire surveillance has significantly accelerated. Nevertheless, the integration of graph convolutional networks (GCNs) in forest fire detection remains relatively underexplored. In this context, we introduce a novel superpixel-based graph convolutional network (SCGCN) for forest fire image segmentation. Our proposed method utilizes superpixels to transform images into a graph structure, thereby reinterpreting the image segmentation challenge as a node classification task. Additionally, we transition the spatial graph convolution operation to a GraphSAGE graph convolution mechanism, mitigating the class imbalance issue and enhancing the network’s versatility. We incorporate an innovative loss function to contend with the inconsistencies in pixel dimensions within superpixel clusters. The efficacy of our technique is validated on two different forest fire datasets, demonstrating superior performance compared to four alternative segmentation methodologies.

With the development of image processing technology and video analysis technology, forest fire monitoring technology based on video recognition is more and more important in the field of forest fire prevention and control. The objects currently applied to forest fire video image monitoring system monitoring are mainly flames and smoke. This paper proposes a forest fire risk monitoring and early warning algorithm, which integrates a deep learning model, infrared monitoring and early warning, and forest fire weather index. The algorithm first obtains the current visible image and infrared image of the same forest area, utilizing a smoke detection model based on deep learning to detect smoke in the visible image, and obtains the confidence level of the occurrence of fire in said visible image. Then, it determines whether the local temperature value of said infrared image exceeds a preset warning value, and obtains a judgment result based on the infrared image. It calculates again a current FWI based on environmental data, and determines a current fire danger level based on the current FWI. Finally, it determines whether or not to carry out a fire warning based on said fire danger level, said confidence level of the occurrence of fire in said visible image, and said judgment result based on the infrared image. The experimental results show that the accuracy of the algorithm in this paper reaches 94.12%, precision is 96.1%, recall is 93.67, and F1-score is 94.87. The algorithm in this paper can improve the accuracy of smoke identification at the early stage of forest fire danger occurrence, especially by excluding the interference caused by clouds, fog, dust, and so on, thus improving the fire danger warning accuracy.

Forest fires can develop rapidly and may cause a wide range of hazards. Therefore, aerial firefighting, which has the ability to respond and reach fire fields quickly, is of great significance to the emergency response to and subsequent extinguishing of forest fires. The burning of forest fires generates a lot of heat and smoke, which changes the air flow environment and vision over the region and brings challenges to aerial firefighting. In the present work, aerial forest firefighting simulation was divided into the forest fire spread model, the air flow model and the aircraft flight dynamic and automatic control model. Each model was constructed based on a physical method. An integrated framework was designed to realize the interaction among fire fields, airfields, and aircraft, and is verified. The proposed framework can be used for the emergency response decision of aerial forest fire fighting and subsequent fire-fighting mission planning.

Since the Palaeozoic era, fire as a potent driver of environmental changes, has dramatically shaped the terrestrial ecosystems. Fire affects soil structure and composition, which in turn affects the floral diversity of an area. This research work aims to examine the impact of fire on vegetation and the physicochemical nature of the soil in fire-affected and fire-free sites across the Mahaban and the surrounding forests, Swabi District, Khyber Pakhtunkhwa, Pakistan. Quadrat quantitative ecological techniques were used for vegetation sampling in fire-free and fire-affected sites. In total, 219 plant species belonging to 173 genera and 70 families were recorded. Among the 219 plant species, 173 species were recorded from fire-free sites and the remaining 122 species were from fire-affected sites. The incidence of fire results in elevated organic matter, nitrogen, phosphorus, and lower calcium carbonate concentrations in the soil. The greatest species richness and evenness were observed across the fire-free sites. Our study concludes that the influence of edaphic and topographic factors on species richness varies between fire-affected and fire-free sites. Fire has significantly altered the nutrient availability in the studied region, and this is confirmed by soil analysis and vegetation research. It is suggested that further research in the field of fire ecology can produce valuable insights.

Forest fires exert detrimental effects on the economic, social, and ecological well-being of both individual nations and expansive geographical regions. These fires lead to the destruction of substantial quantities of valuable timber, the degradation of forest plantations, extensive deforestation, a decline in the protective functions of forests, diminished effectiveness in safeguarding water resources, and heightened soil erosion, particularly in mountainous terrain. Concurrently, agricultural production faces deteriorating conditions, and both wildlife and human populations, along with their production facilities, residences, infrastructure, and other assets, become exposed to significant hazards as a direct or indirect consequence of these raging infernos. The data that are used and analysed are for the period 1980–2018.

Due to climate change, the risk of forest fires has increased in Europe, resulting in challenges in the allocation of salvaged wood. We studied the raw material potential for wood products of Norway spruce and Scots pine sawn log trees that remained standing after a large forest fire in Kalajoki, Finland, in July 2021. Eight burned trees, with four reference trees per species, were sampled as standard specimens, and measurements were analyzed with linear mixed models. The effects of fire on the modulus of elasticity and rupture, Brinell hardness, moisture gradient, and color were measured on clear wood specimens of sapwood and heartwood. The wood density, level of fire damage, and height location of a tree were used as additional predictors. The results show some changes in the sapwood material. Spruce wood underwent stronger changes after the fire than pine wood, probably due to spruce wood having a thinner bark and a longer crown. The moisture content decreased in spruce, and the color darkened in both spruce and pine. Changes in the mechanical properties were mostly negligible, but a small increase in the Brinell hardness in spruce and a small decrease in the modulus of rupture in pine were observed. Fresh salvaged wood can be a suitable material for middle-quality and lower-quality wood products. The spread of char and soot into wood and wood processing machinery still limits its usage, especially for spruce.

The assessment of fire effects in Aleppo pine forests is crucial for guiding the recovery of burned areas. This study presents a methodology using UAV-LiDAR data to quantify malleability in three burned areas (1970, 1995, 2008) through the statistical analysis of tree height and Profile Area Change (PAC) metrics. Significant differences in vegetation height (99th percentile) among the three fires, with specific maximum absolute differences (D) depending on the fire year, have been identified. Positive PAC values in 2008 indicate deeper LiDAR penetration, resulting in lower regeneration, while values close to 0 in 1970 suggest more uniform regeneration. The use of LiDAR metrics and uni-temporal sampling between burned sectors and controls aids in understanding community resilience and identifying recovery stages in P. halepensis forests.

Ice–snow freezing may disrupt the growth condition and structure of forest vegetation, increasing combustible loads and thus triggering forest fires. China’s subtropical regions are rich in forest resources, but are often disturbed by ice–snow freezing, especially due to climate change. Clarifying the responsive areas and times of forest fires to ice-snow freezing in this region is of vital importance for local forest fire management. In this study, meteorological data from 2001 to 2019 were used to extract the precipitation and its duration during the freezing period in order to analyze the freezing condition of forest vegetation in subtropical China. To improve the accuracy of identifying forest fires, we extracted forest fire information year-by-year and month-by-month based on the moderate resolution imaging spectroradiometer (MODIS) active fire data (MOD14A2) using the enhanced vegetation index (EVI), and analyzed the forest fire clustering characteristics in the region using the Moran’s Index. Then, correlation analysis between forest fires and freezing precipitation was utilized to explore the responsive areas and periods of forest fires caused by ice–snow freezing. Our analysis shows the following: (1) during the period of 2001–2019, the ice–snow freezing of forest vegetation was more serious in Hunan, Jiangxi, Hubei, and Anhui provinces; (2) forest fires in subtropical China have shown a significant downward trend since 2008 and their degree of clustering has been reduced from 0.44 to 0.29; (3) forest fires in Hunan, Jiangxi, and Fujian provinces are greatly affected by ice–snow freezing, and their correlation coefficients are as high as 0.25, 0.25, and 0.32, respectively; and (4) heavy ice–snow freezing can increase forest combustibles and affect forest fire behavior in February and March. This research is valuable for forest fire management in subtropical China and could also provide a reference for other regions.

Wildfire has extensive and profound impacts on forest structure and function. Therefore, it is important to study the spatial and temporal patterns of forest fire regimes and their drivers in order to better understand the feedbacks between climate change, fire disturbance, and forest ecosystems. Based on the Global Fire Atlas dataset, three forest fire regime components (fire occurrence density, burned rate, and median fire size) were extracted for China from 2003 to 2016. Three statistical models (Boosted Regression Tree, Random Forest, and Support Vector Machine) were used to systematically analyze the relationships between patterns of forest fire disturbance and climate, human activities, vegetation, and topography in China, as well as their spatial heterogeneity in different climatic regions. The results indicate that the spatial distribution of forest fires is heterogeneous, and different forest fire regime components are predicted by different factors. At the national level, the distribution of forest fire regimes mainly corresponds to climatic factors, although the relationship between median fire size and predictors is obscure. At the scale of each ecoregion, the main climate predictors of forest fire occurrence density and burned rate change from temperature in the north to temperature and precipitation in the south. Median fire size varies with elevation and temperature in the south. These results demonstrate that the spatial heterogeneity of predictors and scaling effects must be fully considered in the study of forest fire disturbance.

Forest fires rank among the costliest and deadliest natural disasters globally. Identifying the smoke generated by forest fires is pivotal in facilitating the prompt suppression of developing fires. Nevertheless, succeeding techniques for detecting forest fire smoke encounter persistent issues, including a slow identification rate, suboptimal accuracy in detection, and challenges in distinguishing smoke originating from small sources. This study presents an enhanced YOLOv8 model customized to the context of unmanned aerial vehicle (UAV) images to address the challenges above and attain heightened precision in detection accuracy. Firstly, the research incorporates Wise-IoU (WIoU) v3 as a regression loss for bounding boxes, supplemented by a reasonable gradient allocation strategy that prioritizes samples of common quality. This strategic approach enhances the model’s capacity for precise localization. Secondly, the conventional convolutional process within the intermediate neck layer is substituted with the Ghost Shuffle Convolution mechanism. This strategic substitution reduces model parameters and expedites the convergence rate. Thirdly, recognizing the challenge of inadequately capturing salient features of forest fire smoke within intricate wooded settings, this study introduces the BiFormer attention mechanism. This mechanism strategically directs the model’s attention towards the feature intricacies of forest fire smoke, simultaneously suppressing the influence of irrelevant, non-target background information. The obtained experimental findings highlight the enhanced YOLOv8 model’s effectiveness in smoke detection, proving an average precision (AP) of 79.4%, signifying a notable 3.3% enhancement over the baseline. The model’s performance extends to average precision small (APS) and average precision large (APL), registering robust values of 71.3% and 92.6%, respectively.

The negative impact of climate change is increasingly evident in the severity of forest fires. Fires are becoming more intense and can often only be controlled by aerial means. Aerial firefighting is known as a very effective method—in some cases, it is the only option—of suppressing fire, but it is a very expensive solution. Recently, the effectiveness of this method has received a lot of criticism, with some studies showing a loss of between 60 and 95%, so it is worth approaching this issue in a different way. The aim of this study is to estimate losses using a new method that has not been used before. For this purpose, this study focuses on two components: the requirements of the firebreak and the geometry of the footprint. For the first, the rules of thumb of the practice were applied depending on the fireline intensity. One is the required coverage level of the surface with suppressant, and the other is the required wetted bandwidth, which is the firebreak. In practice, the firebreak should be 2–2.5 times wider than the length of the flame. For the footprint geometry, the author used the results of previous studies dealing with footprint formation. At the end, the design of the required firebreak and the simplified design of the footprint, which is an ellipsoid, were compared to each other. The results show that, in the case of a fireline intensity of 3 MWm−1 and a coverage level of 2.4 kgm−2, the loss is approximately 36.4–44.6% for the ellipsoidal footprint alone and 86–87.8% for the total amount of extinguishing agent. The conclusion is that future work should focus not on a more accurate description and understanding of emissions but on developing a technology that can change the shape of the footprint from an elliptical to a rectangular shape.

Forest fires from lightnings create a tense situation in various regions of states with forested areas. It is noted that in mountainous areas this is especially important in view of the geophysical processes of lightning activity. The aim of the study is to develop a deterministic-probabilistic approach to predicting forest fire danger due to lightning activity in mountainous regions. To develop a mathematical model, the main provisions of the theory of probability and mathematical statistics, as well as the general theory of heat transfer, were used. The scientific novelty of the research is due to the complex use of probabilistic criteria and deterministic mathematical models of tree ignition by a cloud-to-ground lightning discharge. The paper presents probabilistic criteria for predicting forest fire danger, taking into account the lightning activity, meteorological data, and forest growth conditions, as well as deterministic mathematical models of ignition of deciduous and coniferous trees by electric current of a cloud-to-ground lightning discharge. The work uses synthetic data on the discharge parameters and characteristics of the forest-covered area, which correspond to the forest fire situation in the Republic of Altay and the Republic of Buryatia (Russian Federation). The dependences of the probability for occurrence of forest fires on various parameters have been obtained.

Boreal forest ecosystems are regions vulnerable to climate change. Such areas act as the main atmospheric carbon sinks in the world. Wildfires are among the drivers of ecosystem modification and functioning. Boreal wildfires emit an annual average of about 10% of global fire emissions. Taking into account recent climate warming and increases in the frequency of wildfires, boreal forests might switch their functional role from carbon sink to an additional source of atmospheric carbon. Soil respiration is the second largest component of the global carbon cycle and is highly sensitive to disturbance factors, including wildfires. To study the effect of wildfires on soil CO2 emission rates, the fire chronosequence was investigated. During the first few years following the fire, the soil CO2 emission rates were lower compared with the usual levels. It was found that 23 years after a fire, the site demonstrated transition behavior in soil emission rates between disturbed and completely recovered areas. The emission rates at the earliest successional stages are mainly controlled by soil moisture during the summer period. For the other successional stages, soil temperature had a huge impact on soil emission.

Forest fires are one of the most devastating natural disasters, and technologies based on remote sensing satellite data for fire prevention and control have developed rapidly in recent years. Early forest fire smoke in remote sensing images, on the other hand, is thin and tiny in area, making it difficult to detect. Satellites with high spatial resolution sensors can collect high-resolution photographs of smoke, however the impact of the satellite’s repeat access time to the same area means that forest fire smoke cannot be detected in time. Because of their low spatial resolution, photos taken by satellites with shorter return durations cannot capture small regions of smoke. This paper presents an early smoke detection method for forest fires that combines a super-resolution reconstruction network and a smoke segmentation network to address these issues. First, a high-resolution remote sensing multispectral picture dataset of forest fire smoke was created, which included diverse years, seasons, areas, and land coverings. The rebuilt high-resolution images were then obtained using a super-resolution reconstruction network. To eliminate data redundancy and enhance recognition accuracy, it was determined experimentally that the M11 band (2225–2275 nm) is more sensitive to perform smoke segmentation in VIIRS images. Furthermore, it has been demonstrated experimentally that improving the accuracy of reconstructed images is more effective than improving perceptual quality for smoke recognition. The final results of the super-resolution image segmentation experiment conducted in this paper show that the smoke segmentation results have a similarity coefficient of 0.742 to the segmentation results obtained using high-resolution satellite images, indicating that our method can effectively segment smoke pixels in low-resolution remote sensing images and provide early warning of forest fires.

One of the major responsibilities for forest police is forest fire prevention and forecasting; therefore, accurate and timely fire detection is of great importance and significance. We compared several deep learning networks based on the You Only Look Once (YOLO) framework to detect forest flames with the help of unmanned aerial vehicle (UAV) imagery. We used the open datasets of the Fire Luminosity Airborne-based Machine Learning Evaluation (FLAME) to train the YOLOv5 and its sub-versions, together with YOLOv3 and YOLOv4, under equal conditions. The results show that the YOLOv5n model can achieve a detection speed of 1.4 ms per frame, which is higher than that of all the other models. Furthermore, the algorithm achieves an average accuracy of 91.4%. Although this value is slightly lower than that of YOLOv5s, it achieves a trade-off between high accuracy and real-time. YOLOv5n achieved a good flame detection effect in the different forest scenes we set. It can detect small target flames on the ground, it can detect fires obscured by trees or disturbed by the environment (such as smoke), and it can also accurately distinguish targets that are similar to flames. Our future work will focus on improving the YOLOv5n model so that it can be deployed directly on UAV for truly real-time and high-precision forest flame detection. Our study provides a new solution to the early prevention of forest fires at small scales, helping forest police make timely and correct decisions.

Frequent forest fires are causing severe harm to the natural environment, such as decreasing air quality and threatening different species; therefore, developing accurate prediction models for forest fire danger is vital to mitigate these impacts. This research proposes and evaluates a new modeling approach based on TensorFlow deep neural networks (TFDeepNN) and geographic information systems (GIS) for forest fire danger modeling. Herein, TFDeepNN was used to create a forest fire danger model, whereas the adaptive moment estimation (ADAM) optimization algorithm was used to optimize the model, and GIS with Python programming was used to process, classify, and code the input and output. The modeling focused on the tropical forests of the Phu Yen Province (Vietnam), which incorporates 306 historical forest fire locations from 2019 to 2023 and ten forest-fire-driving factors. Random forests (RF), support vector machines (SVM), and logistic regression (LR) were used as a baseline for the model comparison. Different statistical metrics, such as F-score, accuracy, and area under the ROC curve (AUC), were employed to evaluate the models’ predictive performance. According to the results, the TFDeepNN model (with F-score of 0.806, accuracy of 79.3%, and AUC of 0.873) exhibits high predictive performance and surpasses the performance of the three baseline models: RF, SVM, and LR; therefore, TFDeepNN represents a novel tool for spatially predicting forest fire danger. The forest fire danger map from this study can be helpful for policymakers and authorities in Phu Yen Province, aiding sustainable land-use planning and management.

In recent years, tragedies caused by forest fires have been frequently reported. Forest fires not only result in significant economic losses but also cause environmental damage. The utilization of computer vision techniques and unmanned aerial vehicles (UAVs) for forest fire monitoring has become a primary approach to accurately locate and extinguish fires during their early stages. However, traditional computer-based methods for UAV forest fire image segmentation require a large amount of pixel-level labeled data to train the networks, which can be time-consuming and costly to acquire. To address this challenge, we propose a novel weakly supervised approach for semantic segmentation of fire images in this study. Our method utilizes self-supervised attention foreground-aware pooling (SAP) and context-aware loss (CAL) to generate high-quality pseudo-labels, serving as substitutes for manual annotation. SAP collaborates with bounding box and class activation mapping (CAM) to generate a background attention map, which aids in the generation of accurate pseudo-labels. CAL further improves the quality of the pseudo-labels by incorporating contextual information related to the target objects, effectively reducing environmental noise. We conducted experiments on two publicly available UAV forest fire datasets: the Corsican dataset and the Flame dataset. Our proposed method achieved impressive results, with IoU values of 81.23% and 76.43% for the Corsican dataset and the Flame dataset, respectively. These results significantly outperform the latest weakly supervised semantic segmentation (WSSS) networks on forest fire datasets.

The severity of the socio-economic, political, and ecological damage caused by forest fires each year requires action plans for disaster risk reduction (DRR). Despite efforts made to incorporate participatory mechanisms into risk governance, much of the research on disaster risk reduction in academia is conducted under the deficit model. This paper proposes public engagement as a mechanism for incorporating community-based knowledge, experiences, and practices into DRR plans. Based on the case study of forest fires in Galicia (Spain), developed within the MITIGACT project, we explore, through the analysis of in-depth interviews, how forest fires are defined, how disaster management plans are evaluated and what concrete proposals are considered. The results highlight the need to strengthen social governance at the local level and to balance the resources dedicated to the three phases of prevention, extinction, and recovery, moving from a linear to a circular model.

Amazonian biodiversity has been used for generations by human populations, especially by Indigenous peoples and traditional communities in their cultural, social and economic practices. However, forest degradation, driven by forest fires, has threatened the maintenance of these resources. This study examined the effects of recent forest fires on species with timber, non-timber and multiple-use potential in Brazil’s state of Acre. Forest inventories in five forest types were analyzed, identifying species with timber, non-timber and multiple-use potential based on a review of existing scientific articles, books and studies in the technical literature. The indicators of the effect of forest fires on species density were based on the mean and standard deviation of tree density and absolute abundance. We found that 25% of the tree individuals have potential for use by humans, 12.6% for timber, 10.7% non-timber and 1.4% have multiple-use potential. With the negative impact of fire, the reduction in timber, non-timber and multiple-use potential can range from 2 to 100%, depending on the vegetation type and especially on the recurrence of fire. However, even in forests that are degraded by fire, species that are useful to humans can be maintained to a certain degree and contribute to other environmental services, thus they must be preserved.

The forest fire burned area is one of the most basic factors used to describe forest fires and plays a vital role in damage assessment. The development of the NSSI-NDVI vegetation index triangular space method enables simultaneous calculation of the flammable non-photosynthetic vegetation (NPV), combustible photosynthetic vegetation (PV), and incombustible bare soil (BS) fractional cover in forest areas. This can be used to compensate for the calculation method that was based on NDVI vegetation index only by comparing vegetation cover before and after forest fires, with the omission of the NPV burned area. To this end, the NSSI-NDVI triangular space shape consistency before and after forest fires was elucidated through combustion and ash wetting experiments. In addition, the feasibility of the NSSI-NDVI triangular space method for the accurate calculation of the post-fire vegetation damage area was verified. Finally, the applicability and accuracy of this research method were verified based on 10 m spatial resolution satellite hyperspectral images from before and after the forest fire in Lushan, Sichuan Province, China. The NSSI-NDVI triangular space method was used to calculate the PV, NPV, and BS coverage simultaneously, and component transformation was used to calculate the burned area and burned site separately.

Wildfire poses a significant threat and is considered a severe natural disaster, which endangers forest resources, wildlife, and human livelihoods. In recent times, there has been an increase in the number of wildfire incidents, and both human involvement with nature and the impacts of global warming play major roles in this. The rapid identification of fire starting from early smoke can be crucial in combating this issue, as it allows firefighters to respond quickly to the fire and prevent it from spreading. As a result, we proposed a refined version of the YOLOv7 model for detecting smoke from forest fires. To begin, we compiled a collection of 6500 UAV pictures of smoke from forest fires. To further enhance YOLOv7’s feature extraction capabilities, we incorporated the CBAM attention mechanism. Then, we added an SPPF+ layer to the network’s backbone to better concentrate smaller wildfire smoke regions. Finally, decoupled heads were introduced into the YOLOv7 model to extract useful information from an array of data. A BiFPN was used to accelerate multi-scale feature fusion and acquire more specific features. Learning weights were introduced in the BiFPN so that the network can prioritize the most significantly affecting characteristic mapping of the result characteristics. The testing findings on our forest fire smoke dataset revealed that the proposed approach successfully detected forest fire smoke with an AP50 of 86.4%, 3.9% higher than previous single- and multiple-stage object detectors.

Forest disturbances and restoration are key processes in carbon transmission between the terrestrial surface and the atmosphere. In boreal forests, fire is the most common and main disturbance. The reconstruction process for post-disaster vegetation plays an essential role in the restoration of a forest’s structure and function, and it also maintains the ecosystem’s health and stability. Remote sensing monitoring could reflect dynamic post-fire features of vegetation. However, there are still major differences in the remote sensing index in terms of regional feasibility and sensibility. In this study, the largest boreal primary coniferous forest area in China, the Greater Hinggan Mountains forest area, was chosen as the sampling area. Based on time series data from Landsat-5 TM surface reflectance (SR) and data obtained from sample plots, the burned area was extracted using the Normalized Burn Ratio (NBR). We used the pre- and post-fire difference values (dNBR) and compared them with survey data to classify the burn severity level. The Normalized Difference Vegetation Index (NDVI) (based on spectrum combination) and the Disturbance Index (DI) (based on Tasseled-Cap transformation) were chosen to analyze the difference in the degree of burn severity and vegetation restoration observed using various methods according to the sequential variation feature from 1986 to 2011. The results are as follows: (1) The two remote sensing indexes are both sensitive to fire and the burn severity level. When a fire occurred, the NDVI value for that year decreased dramatically while the DI value increased sharply. Alongside these findings, we observed that the rangeability and restoration period of the two indexes is significantly positively correlated with the degree of burn severity. (2) According to these two indexes, natural vegetation restoration was faster than the restoration achieved using artificial methods. However, compared with the NDVI, the DI showed a clearer improvement in restoration, as the restoration period the DI could evaluate was longer in two different ways: the NDVI illustrated great changes in the burn severity in the 5 years post-fire, while the DI was able to show the changes for more than 20 years. Additionally, from the DI, one could identify felling activities carried out when the artificial restoration methods were initially applied. (3) From the sample-plot data, there were few differences in forest canopy density—the average was between 0.55 and 0.6—between the diverse severity levels and restoration methods after 33 years of recovery. The average diameter at breast height (DBH) and height values of trees in naturally restored areas decreased with the increase in burn severity, but the values were obviously higher than those in artificially restored areas. This indicates that both the burn severity level and restoration methods have important effects on forest restoration, but the results may also have been affected by other factors.

Forest fires are one of the most severe natural disasters facing global ecosystems, as they have a significant impact on ecological security and social development. As remote sensing technology has developed, burned areas can now be quickly extracted to support fire monitoring and post-disaster recovery. This study focused on monitoring forest fires that occurred in Chongqing, China, in August 2022. The burned area was identified using various satellite images, including Sentinel-2, Landsat8, Environmental Mitigation II A (HJ2A), and Gaofen-6 (GF-6). The burned area was extracted using visual interpretation, differenced Normalized Difference Vegetation Index (dNDVI), and differenced Normalized Burnup Ratio (dNBR). The results showed that: (1) The results of the three monitoring methods were very consistent, with a coefficient of determination R2 > 0.96. (2) A threshold method based on the dNBR-extracted burned area was used to analyze fire severity, with moderate-severity fires making up the majority (58.05%) of the fires. (3) Different topographic factors had some influence on the severity of the forest fires. High elevation, steep slopes and the northwestern aspect had the largest percentage of burned area.

Climate change-induced heat waves increase the global risk of forest fires, intensifying biomass burning and accelerating climate change in a vicious cycle. This presents a challenge to the response system in heavily forested South Korea, increasing the risk of more frequent and large-scale fire outbreaks. This study aims to optimize IIASA’s wildFire cLimate impacts and Adaptation Model (FLAM)—a processed-based model integrating biophysical and human impacts—to South Korea for projecting the pattern and scale of future forest fires. The developments performed in this study include: (1) the optimization of probability algorithms in FLAM based on the national GIS data downscaled to 1 km2 with additional factors introduced for national specific modeling; (2) the improvement of soil moisture computation by adjusting the Fine Fuel Moisture Code (FFMC) to represent vegetation feedbacks by fitting soil moisture to daily remote sensing data; and (3) projection of future forest fire frequency and burned area. Our results show that optimization has considerably improved the modeling of seasonal patterns of forest fire frequency. Pearson’s correlation coefficient between monthly predictions and observations from national statistics over 2016–2022 was improved from 0.171 in the non-optimized to 0.893 in the optimized FLAM. These findings imply that FLAM’s main algorithms for interpreting biophysical and human impacts on forest fire at a global scale are only applicable to South Korea after the optimization of all modules, and climate change is the main driver of the recent increases in forest fires. Projections for forest fire were produced for four periods until 2100 based on the forest management plan, which included three management scenarios (current, ideal, and overprotection). Ideal management led to a reduction of 60–70% of both fire frequency and burned area compared to the overprotection scenario. This study should be followed by research for developing adaptation strategies corresponding to the projected risks of future forest fires.

Volatile oils in forest fuel can significantly affect forest fire behavior, especially extreme fire behavior, e.g., deflagration, fire storms, blowups, eruptive fires and crown fires. However, how these oils influence fire behavior remains unclear, as few qualitative studies have been performed globally. In the present study, we compared the volatile oil contents and components in live branches and surface dead fuel of Pinus yunnanensis Franch, which is widely distributed in Southwest China, to explore their potential effects on extreme fire behavior. Fifteen samples of live branches and fifteen samples of surface dead fuel were collected. Volatile oils were extracted from the samples using steam distillation, and their components were identified and analyzed using gas chromatography–mass spectrometry (GC-MS). The results show that the volatile oil content in live branches was as high as 8.28 mL·kg−1 (dry weight) and was significantly higher than that in surface dead fuel (3.55 mL·kg−1). The volatile oil content in the P. yunnanensis forest was 126.12 kg per hectare. The main volatile oil components were terpenoids, of which monoterpenes accounted for the highest proportion based on their content (62.63%), followed by sesquiterpenes (22.44%). The terpenoid compounds in live branches were more abundant than those in surface dead fuel. Monoterpenes and sesquiterpenes in volatile oils in forest fuel have low boiling points, high calorific values and a lower explosion limit (LEL; 38.4 g·m−3), which are important characteristics in the manifestation of extreme fire behavior such as deflagration. The analysis results indicate that when heated, the oily gases from P. yunnanensis forest could fill 3284.26 m3 per hectare, with a gas concentration reaching the LEL. We conclude that volatile oil in P. yunnanensis has an important influence on the manifestation of extreme fire behavior, and live branches have a greater effect than surface dead fuel.

The world has seen an increase in the number of wildland fires in recent years due to various factors. Experts warn that the number of wildland fires will continue to increase in the coming years, mainly because of climate change. Numerous safety mechanisms such as remote fire detection systems based on deep learning models and vision transformers have been developed recently, showing promising solutions for these tasks. To the best of our knowledge, there are a limited number of published studies in the literature, which address the implementation of deep learning models for wildland fire classification, detection, and segmentation tasks. As such, in this paper, we present an up-to-date and comprehensive review and analysis of these vision methods and their performances. First, previous works related to wildland fire classification, detection, and segmentation based on deep learning including vision transformers are reviewed. Then, the most popular and public datasets used for these tasks are presented. Finally, this review discusses the challenges present in existing works. Our analysis shows how deep learning approaches outperform traditional machine learning methods and can significantly improve the performance in detecting, segmenting, and classifying wildfires. In addition, we present the main research gaps and future directions for researchers to develop more accurate models in these fields.

Wildfires are worsening in Canada and globally, partly due to climate change. The government of Canada is designing and building WildFireSat, the world’s first purpose-built operational satellite system for wildfire monitoring. It will provide new fire intelligence to support decision-making. It takes time for fire management agencies to use new information: to understand it and its implications, change processes, develop training, and modify computer systems. Preparing for the system’s prelaunch will allow agencies to benefit more rapidly from the new information. We present (1) an assessment of the readiness of 12 Canadian fire management agencies to integrate WildFireSat information and (2) guidance for reducing readiness gaps. We used survey and other data to score readiness indicators for three readiness components: understanding, organization, and information technology. We weighted the influence of each indicator score on each component. We modelled scoring and weighting uncertainties and used Monte Carlo simulation to generate distributions of aggregated agency readiness. The results indicated that most agencies have a moderate level of readiness while others have a higher level of readiness. Cluster analysis was used to group agencies by similarity in multiple dimensions. Strategies for increasing readiness are highlighted. This identifies opportunities for agencies and the WildFireSat team to collaborate on enhancing readiness for the forthcoming WildFireSat data products.

Predicting the behaviour of wildfires can help save lives and reduce health, socioeconomic, and environmental impacts. Because wildfire behaviour is highly dependent on fuel type and distribution, their accurate estimation is paramount for accurate prediction of the fire propagation dynamics. This paper studies the effect of combining automated hyperparameter tuning with Bayesian optimisation and recursive feature elimination on the accuracy of three boosting (AdaB, XGB, CatB), two bagging (Random Forest, Extremely Randomised Trees), and three stacking ensemble models with respect to their ability to estimate the vegetation cover type from cartographic data. The models are trained on the University of California Irvine (UCI) cover type dataset using five-fold cross-validation. Feature importance scores are calculated and used in recursive feature elimination analysis to study the sensitivity of model accuracy to the different feature combinations. Our results indicate that the implemented fine-tuning procedure significantly affects the accuracy of all models investigated, with XGB achieving an overall accuracy of 97.1% slightly outperforming the others.