Search Results (86)

Wildfires increasingly threaten human life, ecosystems, and infrastructure, with events like the 2025 Palisades and Eaton fires in Los Angeles County underscoring the urgent need for more advanced prediction frameworks. Existing physics-based and deep-learning models struggle to capture dynamic wildfire spread across both 2D and 3D domains, especially when incorporating real-time, multimodal geospatial data. This paper explores how generative artificial intelligence (AI) models—such as GANs, VAEs, and transformers—can serve as transformative tools for wildfire prediction and simulation. These models offer superior capabilities in managing uncertainty, integrating multimodal inputs, and generating realistic, scalable wildfire scenarios. We adopt a new paradigm that leverages large language models (LLMs) for literature synthesis, classification, and knowledge extraction, conducting a systematic review of recent studies applying generative AI to fire prediction and monitoring. We highlight how generative approaches uniquely address challenges faced by traditional simulation and deep-learning methods. Finally, we outline five key future directions for generative AI in wildfire management, including unified multimodal modeling of 2D and 3D dynamics, agentic AI systems and chatbots for decision intelligence, and real-time scenario generation on mobile devices, along with a discussion of critical challenges. Our findings advocate for a paradigm shift toward multimodal generative frameworks to support proactive, data-informed wildfire response. Full article

Accurate real-time tracking of forest fires using UAV platforms is crucial for timely early warning, reliable spread prediction, and effective autonomous suppression. Existing detection-based multi-object tracking methods face challenges in accurately associating targets and maintaining smooth tracking trajectories in complex forest environments. These difficulties stem from the highly nonlinear movement of flames relative to the observing UAV and the lack of robust fire-specific feature modeling. To address these challenges, we introduce AO-OCSORT, an association-optimized observation-centric tracking framework designed to enhance robustness in dynamic fire scenarios. AO-OCSORT builds on the YOLOX detector. To associate detection results across frames and form smooth trajectories, we propose a temporal–physical similarity metric that utilizes temporal information from the short-term motion of targets and incorporates physical flame characteristics derived from optical flow and contours. Subsequently, scene classification and low-score filtering are employed to develop a hierarchical association strategy, reducing the impact of false detections and interfering objects. Additionally, a virtual trajectory generation module is proposed, employing a kinematic model to maintain trajectory continuity during flame occlusion. Locally evaluated on the 1080P-resolution FireMOT UAV wildfire dataset, AO-OCSORT achieves a 5.4% improvement in MOTA over advanced baselines at 28.1 FPS, meeting real-time requirements. This improvement enhances the reliability of fire front localization, which is crucial for forest fire management. Furthermore, AO-OCSORT demonstrates strong generalization, achieving 41.4% MOTA on VisDrone, 80.9% on MOT17, and 92.2% MOTA on DanceTrack. Full article

This study assesses future wildfire risk in Greece using the Fire Weather Index (FWI), based on data from the Copernicus Climate Change Service. Historical conditions (1971–2000) and future projections (2069–2098) under RCP4.5 and RCP8.5 scenarios were analyzed, with a primary focus on the core fire season (May–October) and consideration of April and November to evaluate potential seasonal extension. The results show a significant shift toward higher fire risk classes, with the “very high” category increasing from 24% historically to 31% under RCP4.5 and 37% under RCP8.5, and the “extreme” class rising from 4% to 11% and 16%, respectively. Southern Greece, especially Crete, and the Dodecanese, is projected to experience the most severe increases. These changes, driven by rising temperatures and intensified drought conditions, indicate an increased likelihood of extreme fire events, posing increased risks to ecosystems, infrastructure, and regional economies. The findings highlight the need for targeted adaptation and fire management strategies. Full article

Wildfires in central-south Chile, consistent with trends observed in other Mediterranean regions, are expected to become more frequent and severe, threatening ecosystems and impacting millions of people. This study aims to enhance wildfire resilience in the central-south regions of Chile through the provision of robust information on current wildfire management practices and comparison with successful alternatives implemented in other fire-prone Mediterranean regions. With this aim, we consulted 55 local stakeholders involved in wildfire management, and alongside a comparative analysis of wildfire statistics and resource allocation in selected Mediterranean regions, we critically assessed different strategies to improve wildfire prevention and management in central-south Chile. The comparative analysis indicated notable economic under-investment for wildfire prevention in Chile. Compared to other Mediterranean countries, Chile is clearly below in terms of investment in forest fire prevention, both in global (public investment) and specific terms ($ ha⁻¹, GDP per capita). The experts consulted included fuel management, governance and community participation, territorial management, landscape planning, socioeconomic evaluation, and education and awareness as key aspects for wildfire prevention. The results of the questionnaire indicated that there was a broad consensus regarding the importance of managing biomass to reduce fuel loads and vegetation continuity, thereby enhancing landscape resilience. Landscape planning and territorial management were also emphasized as critical tools to balance ecological needs with those of local communities, mitigating wildfire risks. Fire-Smart management emerged as a nature-based solution and a promising integrated approach, combining fuel treatments with modeling, simulation, and scenario evaluation based on local and regional environmental data. Additionally, educational and social engagement tools were considered vital for addressing misconceptions and fostering community support. Besides a better integration of rural planning with social demands, this study underscores the urgent need to substantially increase the investment and significance of wildfire prevention measures in central-south Chile, which are key to improving its wildfire resilience. Our work contextualizes the reality of wildfires in central-south Chile and directly contributes to mitigating this growing concern by critically examining successful wildfire resilience strategies from comparable fire-prone regions, complementing ongoing local efforts and offering a practical guide for stakeholders in wildfire management and prevention, with particular relevance to central-south Chile and other regions with similar characteristics. Full article

The incorporation of climate refugia concepts in large-scale protection efforts (e.g., 30% protected by 2030, 50% by 2050) is needed to forestall the global extinction crisis. The 8.19 M ha Northern Rockies Ecoregion (NRE) of western Montana, northeastern Washington, and northern Idaho, USA, includes the 159,822 Yaak River Watershed (YRW) in northwest Montana, a proposed climate refugium that may buffer extreme climate change effects. Climate projections show temperature increases along with reduced summer precipitation, lowered spring snowpack, and increased wildfire susceptibility across the NRE but to a lesser extent in the YRE under an intermediate emissions scenario. Overall protection levels were quite low in the NRE (2.2% in GAP 1 or 2) and even lower in the YRW (1% of national forests; the USDA Forest Service manages most of the area). Approximately 32% of forests are mature but only 2.4% and 0.25% are protected (GAP 1 or 2) within the NRE and YRW, respectively. Habitat protection levels for eight focal forest species selected to reflect conservation priorities were generally low, with only wolverine (Gulo gulo) meeting conservation targets if roadless areas were better protected. Most (~75%) Forest Service fuel reduction treatments were >1 km from structures despite congressional funds aimed at the wildland–urban interface/intermix. Increased roadless area protections would close the lower bound (30%) target for most ecosystem types and focal species but still fall short of upper targets. We recommend coupling conservation targets with strategic investments in fuel reductions aimed at the innermost buffer around structures, while reducing logging and roadbuilding in priority areas and refugia. Full article

In response to the escalating complexity and frequency of wildland fires, this study investigates the feasibility of using wearable devices for real-time monitoring of cardiac, respiratory, physical, and environmental parameters during live wildfire suppression tasks. Data were collected from twelve male firefighters (FFs) from the Italian National Fire Corp during a simulated protocol, including rest, running, and active fire suppression phases. Physiological and physical metrics such as heart rate (HR), heart rate variability (HRV), respiratory frequency (f_R) and physical activity levels were extracted using chest straps. The protocol designed to mimic real-world firefighting scenarios revealed significant cardiovascular and respiratory strain, with HR often exceeding 85% of age-predicted maxima and sustained elevations in high-stress roles. Recovery phases highlighted variability in physiological responses, with reduced HRV indicating heightened autonomic stress. Additionally, physical activity analysis showed task-dependent intensity variations, with debris management roles exhibiting consistently high exertion levels. These findings demonstrate the relevance of wearable technology for real-time monitoring, providing an accurate analysis of key metrics to offer a comprehensive overview of work-rest cycles, informing role-specific training and operational strategies. Full article

With increasing wildfire severity and duration driven by climate change, accurately predicting fire behavior over extended time frames is critical for effective management and mitigation of such wildfires. Fire propagation models play a pivotal role in these efforts, providing simulations that can be used to strategize and respond to active fires. This study examines the fire area simulator (FARSITE) model’s performance in simulating recent wildfire events that persisted over 24 h with limited firefighting intervention in mostly remote access areas across diverse ecosystems. Our findings reveal key insights into a prolonged wildfire scenarios potentially informing improvements in operational fire management and long-term predictive accuracy, as the area comparisons indexes showed reasonable results between the detected fires from the fire information for resource management systems (FIRMSs) in the first 24 h of the fire and the following days. A case study of a recent wildfire in Madeira Island highlights the integration of real-time weather predictions and post-event weather data analysis. This analysis underscores the potential of combining accurate forecasts with retrospective validation to improve predictive capabilities in dynamic fire environments, which guided the development of a software platform designed to analyse ongoing wildfire events in real-time, leveraging image satellite data and weather predictions. Full article

In recent years, the increasingly significant impacts of climate change and human activities on the environment have led to more frequent occurrences of extreme events such as forest fires. The recurrent wildfires pose severe threats to ecological environments and human life safety. Consequently, forest fire prediction has become a current research hotspot, where accurate forecasting technologies are crucial for reducing ecological and economic losses, improving forest fire management efficiency, and ensuring personnel safety and property security. To enhance comprehensive understanding of wildfire prediction research, this paper systematically reviews studies since 2015, focusing on two key aspects: datasets with related tools and prediction algorithms. We categorized the literature into three categories: statistical analysis and physical models, traditional machine learning methods, and deep learning approaches. Additionally, this review summarizes the data types and open-source datasets used in the selected literature. The paper further outlines current challenges and future directions, including exploring wildfire risk data management and multimodal deep learning, investigating self-supervised learning models, improving model interpretability and developing explainable models, integrating physics-informed models with machine learning, and constructing digital twin technology for real-time wildfire simulation and fire scenario analysis. This study aims to provide valuable support for forest natural resource management and enhanced environmental protection through the application of remote sensing technologies and artificial intelligence algorithms. Full article

Climate change exacerbates wildfire risks in regions like the Mediterranean, where rising temperatures and prolonged droughts create ideal fire conditions. Adapting to this scenario requires implementing advanced risk management strategies that leverage cutting-edge technologies. Wildfire early warning systems are crucial tools for detecting fires at an early stage, helping prevent potential future damage. This paper proposes a smart CO₂ sensor network-based early warning system, relying on a platform that enables the connection, management, and processing of data from the devices through the cloud. The wildfire early warning system was tested in a real controlled experiment, in which 44 sensors were deployed in strategically selected locations at varying distances from the fire. To enhance early detection, three Artificial Intelligence (AI) models were developed using AutoEncoders (AEs) and Long-Short-Term Memory (LSTM), and these were compared to a simple threshold-based (NO-AI) model. All AI models, especially the LSTM-based model, were able to extract more valuable information from the CO₂ records, activating up to 56% more sensors than the NO-AI model in less time and tracking potential fire front propagation based on wind patterns. Therefore, the system not only improves early fire detection models but also effectively supports firefighting operations. Full article

The Cerrado is Brazil’s second largest biome, covering continuous areas in several states. Covering approximately 23% of Brazil’s territory, the Cerrado biome connects with all the main biomes in South America, thus forming a major biological corridor. This biome is one of those that has suffered the most from the incidence of wildfires, leading to a progressive depletion of the region’s natural resources. The aim of this study was to evaluate the use of an Unmanned Aerial Vehicle (UAV) embedded with an RGB sensor to obtain high-resolution digital products that can be used to identify areas of the Brazilian Cerrado affected by wildfires. The study was carried out in a savannah biome area selecting a vegetation corridor with native vegetation free from anthropogenic influence. The following UAV surveys were carried out before and after a burning event. Once the orthomosaics of the area were available, the GLI, VARI, ExG and NGRDI vegetation indices were used to analyze the vegetation. The data indicate that the B band and the GLI and ExG indices are more suitable for environmental impact analysis in Cerrado areas affected by fires, providing a solid basis for environmental monitoring and management in scenarios of fire disturbance. Full article

Understanding the characteristics of wildfires in North China is critical for advancing regional fire danger prediction and management strategies. This study employed satellite-based burned area products of the Global Fire Emissions Database (GFED) and reanalysis of climate datasets to investigate the spatiotemporal characteristics of wildfires, as well as their relationships with fire danger indices and climatic drivers. The results revealed distinct seasonal variability, with the maximum burned area extent and intensity occurring during the March–April period. Notably, the fine fuel moisture code (FFMC) demonstrated a stronger correlation with burned areas compared to other fire danger or climate indices, both in temporal series and spatial patterns. Further analysis through the self-organizing map (SOM) clustering of FFMC composites then revealed six distinct modes, with the SOM1 mode closely matching the spatial distribution of burned areas in North China. A trend analysis indicated a 7.75% 10a⁻¹ (p < 0.05) increase in SOM1 occurrence frequency, associated with persistent high-pressure systems that suppress convective activity through (1) inhibited meridional water vapor transport and (2) reduced cloud condensation nuclei formation. These synoptic conditions created favorable conditions for the occurrence of wildfires. Finally, we developed a prediction model for burned areas, leveraging the strong correlation between the FFMC and burned areas. Both the SSP245 and SSP585 scenarios suggest an accelerated, increasing trend of burned areas in the future. These findings emphasize the importance of understanding the spatiotemporal characteristics and underlying causes of wildfires, providing critical insights for developing adaptive wildfire management frameworks in North China. Full article

Wildfires pose severe threats to terrestrial ecosystems by causing loss of biodiversity, altering landscapes, compromising ecosystem services, and endangering human lives and infrastructure. Chile, with its diverse geography and climate, faces escalating wildfire frequency and intensity due to climate change. This study employs a spatial machine learning approach using a Random Forest algorithm to predict wildfire risk in Central and Southern Chile under current and future climatic scenarios. The model was trained on a time series dataset incorporating climatic, land use, and physiographic variables, with burned-area scars as the response variable. By applying this model to three projected climate scenarios, this study forecasts the spatial distribution of wildfire probabilities for multiple future periods. The model’s performance was high, achieving an Area Under the Curve (AUC) of 0.91 for testing and 0.87 for validation. The accuracy, True Positive Rate (TPR), and True Negative Rate (TNR) values were 0.80, 0.87, and 0.73, respectively. Currently, the prediction of wildfire risk in Mediterranean-type climate areas and the central Araucanía are most at risk, particularly in agricultural zones and rural–urban interfaces. However, future projections indicate a southward expansion of wildfire risk, with an overall increase in probabilities as climate scenarios become more pessimistic. These findings offer a framework for policymakers, facilitating evidence-based strategies for adaptive land management and effective mitigation of wildfire risk. Full article

Soil organic carbon (SOC) is essential for maintaining ecosystem health, and its depletion is widely recognized as a key indicator of soil degradation. Activities such as mining and wildfire disturbances significantly intensify soil degradation, leading to quantitative and qualitative declines in SOC. Accurate SOC monitoring is critical, yet traditional methods are often costly and time-intensive. Advances in technologies like Unmanned Aerial Vehicles (UAVs) and satellite remote sensing (SRS) now offer efficient and scalable alternatives. Combining UAV and satellite data through machine learning (ML) techniques can improve the accuracy and spatial resolution of SOC monitoring, facilitating better soil management strategies. In this context, this study proposes a methodology that integrates geochemical data (SOC) with UAV-derived information, upscaling the UAV data to satellite platforms (GEOSAT-2 and SENTINEL-2) using ML techniques, specifically random forest (RF) algorithms. The research was conducted in two distinct environments: a reclaimed open-pit coal mine, representing a severely degraded ecosystem, and a high-altitude region prone to recurrent wildfires, both characterized by extreme environmental conditions and diverse soil properties. These scenarios provide valuable opportunities to evaluate the effects of soil degradation on SOC quality and to assess the effectiveness of advanced monitoring approaches. The RF algorithm, optimized with cross-validation (CV) techniques, consistently outperformed other models. The highest performance was achieved during the UAV-to-SENTINEL-2 upscaling, with an R² of 0.761 and an rRMSE of 8.6%. Cross-validation mitigated overfitting and enhanced the robustness and generalizability of the models. UAV data offered high-resolution insights for localized SOC assessments, while SENTINEL-2 imagery enabled broader-scale evaluations, albeit with a smoothing effect. These findings underscore the potential of integrating UAV and satellite data with ML approaches, providing a cost-effective and scalable framework for SOC monitoring, soil management, and climate change mitigation efforts. Full article

Seasonally dry mature and old-growth (MOG) forests in the western USA face increasing threats from catastrophic wildfire and drought due to historical fire exclusion and climate change. The Emerald Point forest at Lake Tahoe in the Sierra Nevada of California, one of the last remaining old-growth stands at lake level, is at high risk due to elevated fuels and tree densities. The stand supports huge trees and the highest tree diversity in the Lake Tahoe Basin and protects important raptor habitat. In this study, we simulate forest response to vegetation management and wildfire to assess the impacts of four fuel-reduction scenarios on fire behavior and stand resilience at Emerald Point. Results: Our results demonstrate that restorative forest management can greatly improve an MOG forest’s resistance to catastrophic fire. Thinning to the natural range of variation for density, basal area, and fuel loads, followed by a prescribed burn, was most effective at reducing large-tree mortality, maintaining basal area, and retaining live tree carbon post-wildfire, while reducing secondary impacts. Conclusions: Our findings highlight the value of proactive management in protecting old-growth forests in seasonally dry regions from severe fire events, while also enhancing their ecological integrity and biodiversity. Full article

Wildfires significantly impact water quality in the Western United States, posing challenges for water resource management. However, limited research quantifies post-wildfire stream temperature and turbidity changes across diverse climatic zones. This study addresses this gap by using Random Forest (RF) and Support Vector Regression (SVR) models to predict post-wildfire stream temperature and turbidity based on climate, streamflow, and fire data from the Clackamas and Russian River Watersheds. We selected Random Forest (RF) and Support Vector Regression (SVR) because they handle non-linear, high-dimensional data, balance accuracy with efficiency, and capture complex post-wildfire stream temperature and turbidity dynamics with minimal assumptions. The primary objectives were to evaluate model performance, conduct sensitivity analyses, and project mid-21st century water quality changes under Representative Concentration Pathway (RCP) 4.5 and 8.5 scenarios. Sensitivity analyses indicated that 7-day maximum air temperature and discharge were the most influential predictors. Results show that RF outperformed SVR, achieving an R² of 0.98 and root mean square error of 0.88 °C for stream temperature predictions. Post-wildfire turbidity increased up to 70 NTU during storm events in highly burned subwatersheds. Under RCP 8.5, stream temperatures are projected to rise by 2.2 °C by 2050. RF’s ensemble approach captured non-linear relationships effectively, while SVR excelled in high-dimensional datasets but struggled with temporal variability. These findings underscore the importance of using machine learning for understanding complex post-fire hydrology. We recommend adaptive reservoir operations and targeted riparian restoration to mitigate warming trends. This research highlights machine learning’s utility for predicting post-wildfire impacts and informing climate-resilient water management strategies. Full article