Search Results (159)

Biological invasions are major threats to global biodiversity, and mapping their distribution is essential to prioritizing management efforts. The Pinaceae family (hereafter pines) includes invasive trees, particularly in Southern Hemisphere regions where they are non-native. These invasions can increase the severity of fires in wildland–urban interfaces (WUIs). We mapped pine invasion in the Bariloche WUI (≈150,000 ha, northwest Patagonia, Argentina) using supervised land cover classification of Sentinel-2 imagery with a Random Forest algorithm on Google Earth Engine, achieving 90% overall accuracy but underestimating the pine invasion area by about 25%. We then assessed in which main vegetation context pine invasions occurred relying on major vegetation units across the precipitation gradient of our study area. Invasions cover 2% of the study area, mainly in forests (61%), steppes (25.4%), and shrublands (13.4%). Most invaded areas (89.1%) are on private land; nearly 70% are on large properties (>10 ha), where state financial incentives could support removal. Another 13.5% occur on many small properties (<1 ha), where awareness campaigns could enable decentralized, low-effort control. Our land cover map can be developed further to integrate invasion dynamics, inform fire risk and behavior models, optimize management actions, and guide territorial planning. Overall, it provides a valuable tool for targeted, scale-appropriate strategies to mitigate ecological and fire-related impacts of invasive pines. Full article

Wildfires pose significant risks to ecosystems, human lives, and infrastructure, necessitating advanced predictive tools to mitigate their impacts. This study presents a machine learning-based framework for wildfire susceptibility mapping (WSM), designed as a predictive tool for wildfire occurrence. Using geographical information systems (GIS), a comprehensive dataset was developed by combining fourteen critical factors, including climatic, topographic, vegetation, and human activity data, from diverse sources. Four ML methods—Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), and XGBoost—were applied and compared. The results show that the XGBoost model (with an AUC of 0.96) generated the best susceptibility map. Validation using 2024–2025 fire occurrences (MODIS and Protection Civile data) showed that 87.73% of fire events were correctly captured within high and very high susceptibility zones, confirming the robustness of the proposed model. Feature importance analysis revealed that human activities, precipitation, and temperature were the most influential in wildfire prediction. These findings provide valuable insights into wildfire dynamics and contribute to the development of more effective fire prevention and mitigation strategies. Full article

The early detection of smoke signals due to wildfires is vital in containing the extent of loss and reducing response time, particularly in inaccessible or forested areas. For lightweight object detection, this study contrasts the YOLOv9-tiny, YOLOv10-nano, YOLOv11-nano, YOLOv12-nano, and YOLOv13-nano algorithms in determining wildfire smoke at extended ranges. We present a robustness- and generalization-checking five-fold cross-validation. This study is also the first of its kind to train and publicly benchmark YOLOv10-nano up to YOLOv13-nano on the given dataset. We investigate and compare the detection performance against the standard performance metrics of precision, recall, F1-score, and mAP50, as well as the performance metrics regarding computational efficiency, including the training and testing time. Our results offer practical implications regarding the trade-off between pre-processing methods and model architectures for smoke detection when applied in real time on ground-based cameras installed on mountains and other high-risk fire locations. The investigation presented in this work provides a model in which implementations of lightweight deep learning models for wildfire early-warning systems can be achieved. Full article

Forest fires have become increasingly frequent and severe due to climate change and intensified human activities, posing critical challenges to ecological security and emergency management. Despite the availability of abundant environmental, spatial, and operational data, these resources remain fragmented and heterogeneous, limiting the efficiency and accuracy of fire prediction and response. To address this challenge, this study proposes a Semantic Digital Twin-Driven Framework for integrating multi-source data and supporting forest fire prediction and response. The framework constructs a multi-ontology network that combines the Semantic Sensor Network (SSN) and Sensor, Observation, Sample, and Actuator (SOSA) ontologies for sensor and observation data, the GeoSPARQL ontology for geospatial representation, and two domain-specific ontologies for fire prevention and emergency response. Through systematic data mapping, instantiation, and rule-based reasoning, heterogeneous information is transformed into an interconnected knowledge graph. The framework supports both semantic querying (SPARQL) and rule-based reasoning (SWRL) to enable early risk alerts, resource allocation suggestions, and knowledge-based decision support. A case study in Sichuan Province demonstrates the framework’s effectiveness in integrating historical and live data streams, achieving consistent reasoning outcomes aligned with expert assessments, and improving decision timeliness by enhancing data interoperability and inference efficiency. This research contributes a foundational step toward building intelligent, interoperable, and reasoning-enabled digital forest systems for sustainable fire management and ecological resilience. Full article

Accurate wildfire prediction and identification of key environmental drivers are critical for effective wildfire management. We propose a spatiotemporally adaptive framework integrating ST-DBSCAN clustering with GTWR-RFR. In this hybrid model, Random Forest captures local nonlinear relationships, while GTWR assigns adaptive spatiotemporal weights to refine predictions. Using historical wildfire records from Hunan Province, China, we first derived wildfire occurrence probabilities via ST-DBSCAN, avoiding the need for artificial non-fire samples. We then benchmarked GTWR-RFR against seven models, finding that our approach achieved the highest accuracy (R² = 0.969; RMSE = 0.1743). The framework effectively captures spatiotemporal heterogeneity and quantifies dynamic impacts of environmental drivers. Key contributing drivers include DEM, GDP, population density, and distance to roads and water bodies. Risk maps reveal that central and southern Hunan are at high risk during winter and early spring. Our approach enhances both predictive performance and interpretability, offering a replicable methodology for data-driven wildfire risk assessment. Full article

In recent years, ecosystems in Saudi Arabia have experienced severe degradation due to factors such as hyperaridity, overgrazing, climate change, urban expansion, and an increase in uncontrolled wildfires. Among these, wildfires have emerged as the second most significant threat to forests after urban expansion. This study aims to map wildfire susceptibility in southwestern Saudi Arabia by identifying key driving factors and evaluating the performance of several machine learning models under conditions of limited and imbalanced data. The models tested include Maxent, logistic regression, random forest, XGBoost, and support vector machine. In addition, an NDVI-based phenological approach was applied to assess seasonal vegetation dynamics and to compare its effectiveness with conventional machine learning-based susceptibility mapping. All methods generated effective wildfire risk maps, with Maxent achieving the highest predictive accuracy (AUC = 0.974). The results indicate that human activities and dense vegetation cover are the primary contributors to wildfire occurrence. This research provides valuable insights for wildfire risk assessment in data-scarce regions and supports proactive fire management strategies in non-traditional fire-prone environments. Full article

Mountainous urban areas like Guiyang face unique fire safety challenges due to rugged terrain and complex road networks, which hinder fire station accessibility. This study proposes a GIS-based framework that integrates nighttime light (NPP/VIIRS) and point of interest (POI) data to assess fire risk and accessibility. Kernel density estimation quantified POI distributions across four risk categories, and the Spatial Appraisal and Valuation of Environment and Ecosystems (SAVEE) model combined these with NPP/VIIRS data to generate a composite fire risk map. Accessibility was evaluated using the enhanced two-step floating catchment area (E2SFCA) method with road network travel times; 80.13% of demand units were covered within the five-minute threshold, while 53.25% of all units exhibited low accessibility. Spatial autocorrelation analysis (Moran’s I) revealed clustered high risk in central basins and service gaps on surrounding hills, reflecting the dominant influence of terrain alongside protected forests and farmlands. The results indicate that targeted road upgrades and station relocations can improve fire service coverage. The approach is scalable and supports more equitable emergency response in mountainous settings. Full article

Seasonal fires in northern Thailand are a persistent environmental and public health concern, yet existing fire probability mapping approaches in Thailand rely heavily on subjective multi-criteria analysis (MCA) methods and temporally static data aggregation methods. To address these limitations, we present a flexible, replicable, and operationally viable seasonal fire probability mapping methodology using a Random Forest (RF) machine learning model in the Google Earth Engine (GEE) platform. We trained the model on historical fire occurrence and fire predictor layers from 2016–2023 and applied it to 2024 conditions to generate a probabilistic fire prediction. Our novel approach improves upon existing operational methods and scientific literature in several ways. It uses a more representative sample design which is agnostic to the burn history of fire presences and absences, pairs fire and fire predictor data from each year to account for interannual variation in conditions, empirically refines the most influential fire predictors from a comprehensive set of predictors, and provides a reproducible and accessible framework using GEE. Predictor variables include both socioeconomic and environmental drivers of fire, such as topography, fuels, potential fire behavior, forest type, vegetation characteristics, climate, water availability, crop type, recent burn history, and human influence and accessibility. The model achieves an Area Under the Curve (AUC) of 0.841 when applied to 2016–2023 data and 0.848 when applied to 2024 data, indicating strong discriminatory power despite the additional spatial and temporal variability introduced by our sample design. The highest fire probabilities emerge in forested and agricultural areas at mid elevations and near human settlements and roads, which aligns well with the known anthropogenic drivers of fire in Thailand. Distinct areas of model uncertainty are also apparent in cropland and forests which are only burned intermittently, highlighting the importance of accounting for localized burning cycles. Variable importance analysis using the Gini Impurity Index identifies both natural and anthropogenic predictors as key and nearly equally important predictors of fire, including certain forest and crop types, vegetation characteristics, topography, climate, human influence and accessibility, water availability, and recent burn history. Our findings demonstrate the heavy influence of data preprocessing and model design choices on model results. The model outputs are provided as interpretable probability maps and the methods can be adapted to future years or augmented with local datasets. Our methodology presents a scalable advancement in wildfire probability mapping with machine learning and open-source tools, particularly for data-constrained landscapes. It will support Thailand’s fire managers in proactive fire response and planning and also inform broader regional fire risk assessment efforts. Full article

Forest fire risk assessment methodologies vary considerably, presenting challenges for adaptation to specific local contexts. This study provides a systematic analysis of forest fire assessment approaches across the Mediterranean basin, American, African, and Asian regions through a comprehensive review of 112 peer-reviewed studies published from 2015 to 2025. Statistical significance testing (Chi-square tests, p < 0.05) confirmed significant regional variation in methodological preferences and indicator usage patterns. Key findings revealed that Multi-Criteria Decision Analysis dominates the field (44% of studies, n = 49), with Analytical Hierarchical Process being the most utilized method (39 studies). Machine learning approaches represent 25% (n = 28), with Random Forest leading significantly (22 applications). The analysis identified 67 indicators across seven major categories, with topographic factors (slope: 105 studies) and anthropogenic indicators (road networks: 92 studies) showing statistically significantly highest usage rates (p < 0.001), representing a statistically significant critical gap in vulnerability assessment (p < 0.01). Organizational factors remain severely underrepresented (a maximum of 14 studies for any factor), representing a statistically significant critical gap in risk assessments (p < 0.01). Statistical analysis revealed that while Mediterranean approaches excel in integrating historical and cultural factors, American methods emphasize advanced technology integration, while Asian approaches focus on socio-economic dynamics and land-use interactions. This study serves as a foundation for developing tailored assessment frameworks that combine remote sensing analysis, ground-based surveys, and community input while accounting for local constraints in data availability and technical capacity. The study concludes that effective forest fire risk assessment requires a balanced integration of global best practices with local environmental, social, and technical considerations, offering a roadmap for future forest fire risk assessment approaches in different regions worldwide. Full article

The assessment of the economic vulnerability of natural disasters is a necessary step in the evaluation of any risks. This study proposes the approach implemented under the H2020 FirEurisk project to value the economic damage of wildfires on a European scale. Economic damage is assessed as the net value change in natural (agricultural and forestry resources and their ecosystem services) and manufactured assets under simulated fire intensity, taking into consideration the time necessary for natural capital to recover to the pre-damaged conditions. We show minimum, maximum, and average damage for European countries and map the critical areas. Damages to provisioning-ecosystem services are more pronounced in Central Europe because of the lower resilience of ecosystems compared to the Mediterranean, suggesting that mitigation measures (such as managing vegetation to reduce fuel; improving access to fire services; and engaging communities through education, agriculture, and forest management participation) must be enforced. We are confident that the approach proposed may stimulate further research to test the goodness of the estimates proposed and suggest where it is more appropriate to invest in fire prevention. Full article

This study aimed to investigate the physical factors influencing the occurrence of forest fires and to create a fire risk map of Phrae Province. Remote sensing and geographic information system (GIS) technology were applied for the analysis, focusing on seven factors: the digital elevation model (DEM); slope; Normalized Difference Vegetation Index (NDVI); aspect; and distances from people, water, and roads. All of these geographical factors can affect forest fires. This resulted in a MaxEnt (Maximum Entropy) model with an AUC (area under the curve) of 0.849, indicating its great prediction ability. The findings revealed that the variables influencing forest fire incidence were the DEM, NDVI, slope, distance from roads, distance from water, distance from communities, and aspect, in that order. Subsequently, a fire risk map for wildfires was developed by reclassifying the data into five levels—very low risk, low risk, medium risk, high risk, and very high risk—accounting for 341,395.54, 88,132.64, 76,162.41, 81,157.55, and 57,384.10 hectares or 52.99, 13.68, 11.82, 12.60, and 8.91% of the total area, respectively. The areas classified as very high risk, high risk, medium risk, and low risk included the Song, Long, and Rong Kwang Districts. The area with the lowest risk was Nong Muang Khai District. Full article

This study employed Deep Abstract Networks (DANets), independently and in combination with the Whale Optimization Algorithm (WOA), to generate high-resolution susceptibility maps for drought and wildfire hazards in the Oroqen Autonomous Banner in Inner Mongolia. Presence samples included 309 wildfire points from MODIS active fire data and 200 drought points derived from a custom Standardized Drought Condition Index. DANets-WOA models showed clear performance improvements over their solitary counterparts. For drought susceptibility, RMSE was reduced from 0.28 to 0.21, MAE from 0.17 to 0.11, and AUC improved from 85.7% to 88.9%. Wildfire susceptibility mapping also improved, with RMSE decreasing from 0.39 to 0.36, MAE from 0.32 to 0.28, and AUC increasing from 78.9% to 85.1%. Loss function plots indicated improved convergence and reduced overfitting following optimization. A pairwise z-statistic analysis revealed significant differences (p < 0.05) in susceptibility classifications between the two modeling approaches. Notably, the overlap of drought and wildfire susceptibilities within the forest–steppe transitional zone reflects a climatically and ecologically tense corridor, where moisture stress, vegetation gradients, and human land-use converge to amplify multi-hazard risk beyond the sum of individual threats. The integration of DANets with the WOA demonstrates a robust and scalable framework for dual hazard modeling. Full article

Effective forest planning in Mediterranean environments requires tools capable of managing ecological complexity, socio-economic pressures, and fragmented governance. This study develops and applies a GIS- and GNSS-based methodological framework for regional forest planning, tested in the “Bosco della Ficuzza, Rocca Busambra, Bosco del Cappelliere, Gorgo del Drago” Regional Nature Reserve (western Sicily, Italy). The main objective is to create a multi-layered Territorial Information System (TIS) that integrates high-resolution cartographic data, a Digital Terrain Model (DTM), and GNSS-based field surveys to support adaptive, participatory, and replicable forest management. The methodology combines the following: (i) DTM generation using Kriging interpolation to model slope and aspect with ±1.2 m accuracy; (ii) road infrastructure mapping and classification, adapted from national and regional forestry survey protocols; (iii) spatial analysis of fire-risk zones and accessibility, based on slope, exposure, and road pavement conditions; (iv) the integration of demographic and land use data to assess human–forest interactions. The resulting TIS enables complex spatial queries, infrastructure prioritization, and dynamic scenario modeling. Results demonstrate that the framework overcomes the limitations of many existing GIS-based systems—fragmentation, static orientation, and limited interoperability—by ensuring continuous data integration and adaptability to evolving ecological and governance conditions. Applied to an 8500 ha Mediterranean biodiversity hotspot, the model enhances road maintenance planning, fire-risk mitigation, and stakeholder engagement, offering a scalable methodology for other protected forest areas. This research contributes an innovative approach to Mediterranean forest governance, bridging ecological monitoring with socio-economic dynamics. The framework aligns with the EU INSPIRE Directive and highlights how low-cost, interoperable geospatial tools can support climate-resilient forest management strategies across fragmented Mediterranean landscapes. Full article

UAVs are essential for forest fire detection due to vast forest areas and inaccessibility of high-risk zones, enabling rapid long-range inspection and detailed close-range surveillance. However, aerial photography faces challenges like multi-scale target recognition and complex scenario adaptation (e.g., deformation, occlusion, lighting variations). RGB-Thermal fusion methods integrate visible-light texture and thermal infrared temperature features effectively, but current approaches are constrained by limited datasets and insufficient exploitation of cross-modal complementary information, ignoring cross-level feature interaction. A time-synchronized multi-scene, multi-angle aerial RGB-Thermal dataset (RGBT-3M) with “Smoke–Fire–Person” annotations and modal alignment via the M-RIFT method was constructed as a way to address the problem of data scarcity in wildfire scenarios. Finally, we propose a CP-YOLOv11-MF fusion detection model based on the advanced YOLOv11 framework, which can learn heterogeneous features complementary to each modality in a progressive manner. Experimental validation proves the superiority of our method, with a precision of 92.5%, a recall of 93.5%, a mAP50 of 96.3%, and a mAP50-95 of 62.9%. The model’s RGB-Thermal fusion capability enhances early fire detection, offering a benchmark dataset and methodological advancement for intelligent forest conservation, with implications for AI-driven ecological protection. Full article

The escalating impacts and occurrence of wildfires threaten the public, economies, and global ecosystems. Physiologically declining or dead trees are a great portion of the fires because these trees are prone to higher ignition and have lower moisture content. To prevent wildfires, hazardous vegetation needs to be removed, and the vegetation should be identified early on. This work proposes a real-time fire risk tree detection framework using UAV images, which is based on lightweight object detection. The model uses the MobileNetV3-Small spine, which is optimized for edge deployment, combined with an SSD head. This configuration results in a highly optimized and fast UAV-based inference pipeline. The dataset used in this study comprises over 3000 annotated RGB UAV images of trees in healthy, partially dead, and fully dead conditions, collected from mixed real-world forest scenes and public drone imagery repositories. Thorough evaluation shows that the proposed model outperforms conventional SSD and recent YOLOs on Precision (94.1%), Recall (93.7%), mAP (90.7%), F1 (91.0%) while being light-weight (8.7 MB) and fast (62.5 FPS on Jetson Xavier NX). These findings strongly support the model’s effectiveness for large-scale continuous forest monitoring to detect health degradations and mitigate wildfire risks proactively. The framework UAV-based environmental monitoring systems differentiates itself by incorporating a balance between detection accuracy, speed, and resource efficiency as fundamental principles. Full article