Search Results (212)

Forest fire detection is an essential application in environmental surveillance since wildfires cause devastating damage to ecosystems, human life, and property every year. The effective and accurate detection of fire is necessary to allow for timely response and efficient management of disasters. Traditional techniques for fire detection often experience false alarms and delayed responses in various environmental situations. Therefore, developing robust, intelligent, and real-time detection systems has emerged as a central challenge in remote sensing and computer vision research communities. Despite recent achievements in deep learning, current forest fire detection models still face issues with generalizability, lightweight deployment, and accuracy trade-offs. In order to overcome these limitations, we introduce a novel technique (FireNet-KD) that makes use of knowledge distillation, a method that maps the learning of hard models (teachers) to a light and efficient model (student). We specifically utilize two opposing teacher networks: a Vision Transformer (ViT), which is popular for its global attention and contextual learning ability, and a Convolutional Neural Network (CNN), which is esteemed for its spatial locality and inductive biases. These teacher models instruct the learning of a Swin Transformer-based student model that provides hierarchical feature extraction and computational efficiency through shifted window self-attention, and is thus particularly well suited for scalable forest fire detection. By combining the strengths of ViT and CNN with distillation into the Swin Transformer, the FireNet-KD model outperforms state-of-the-art methods with significant improvements. Experimental results show that the FireNet-KD model obtains a precision of 95.16%, recall of 99.61%, F1-score of 97.34%, and mAP@50 of 97.31%, outperforming the existing models. These results prove the effectiveness of FireNet-KD in improving both detection accuracy and model efficiency for forest fire detection. Full article

Arundo donax L. has been introduced in markets worldwide due to its economic value. However, it is listed in the world’s 100 worst alien invasive species because it easily escapes from cultivation, and forms dense monospecific stands in riparian areas, agricultural areas, and grassland areas along roadsides, including in protected areas. This species grows rapidly and produces large amounts of biomass due to its high photosynthetic ability. It spreads asexually through ramets, in addition to stem and rhizome fragments. Wildfires, flooding, and human activity promote its distribution and domination. It can adapt to various habitats and tolerate various adverse environmental conditions, such as cold temperatures, drought, flooding, and high salinity. A. donax exhibits defense mechanisms against biotic stressors, including herbivores and pathogens. It produces indole alkaloids, such as bufotenidine and gramine, as well as other alkaloids that are toxic to herbivorous mammals, insects, parasitic nematodes, and pathogenic fungi and oomycetes. A. donax accumulates high concentrations of phytoliths, which also protect against pathogen infection and herbivory. Only a few herbivores and pathogens have been reported to significantly damage A. donax growth and populations. Additionally, A. donax exhibits allelopathic activity against competing plant species, though the allelochemicals involved have yet to be identified. These characteristics may contribute to its infestation, survival, and population expansion in new habitats as an invasive plant species. Dense monospecific stands of A. donax alter ecosystem structures and functions. These stands impact abiotic processes in ecosystems by reducing water availability, and increasing the risk of erosion, flooding, and intense fires. The stands also negatively affect biotic processes by reducing plant diversity and richness, as well as the fitness of habitats for invertebrates and vertebrates. Eradicating A. donax from a habitat requires an ongoing, long-term integrated management approach based on an understanding of its invasive mechanisms. Human activity has also contributed to the spread of A. donax populations. There is an urgent need to address its invasive traits. This is the first review focusing on the invasive mechanisms of this plant in terms of adaptation to abiotic and biotic stressors, particularly physiological adaptation. Full article

With wildfires becoming more frequent and severe in fire-prone regions affected by warmer and drier climate conditions, reducing hazardous fuels is increasingly recognized as a preventative strategy for promoting sustainability and safeguarding valued resources. Prescribed fire is one of the most cost-effective methods for reducing hazardous fuels and hence wildfire severity, yet empirical research on its effectiveness at minimizing damage to highly valued resources and assets (HVRAs) remains limited. The overarching objective of this study was to evaluate wildfire severity under differing weather conditions across various HVRAs characterized by diverse land uses, vegetation types, and treatment histories. The findings from this study reveal that wildfire severity was generally lower in areas treated with prescribed fire, although the significance of this effect varied among HVRAs and diminished as post-treatment duration increased. The wildland–urban interface experienced the greatest initial reduction in wildfire severity following prescribed fire, but burn severity increased more rapidly over time relative to other HVRAs. Elevated drought conditions had a significant effect, increasing wildfire severity across all HVRAs. The implications of this study underscore the role of prescribed fire in promoting sustainable land management by reducing wildfire severity and safeguarding both natural and built environments, particularly in the expanding wildland–urban interface. Full article

Accurate forest fire detection is critical for the timely intervention and mitigation of environmental disasters. It is very important to intervene in forest fires before major damage occurs by using smoke data. This study proposes a novel deep learning-based approach that significantly enhances the accuracy of fire detection by incorporating advanced feature extraction techniques. Through rigorous experiments and comprehensive evaluations, our method outperforms existing approaches, demonstrating its effectiveness in detecting fires at an early stage. The proposed approach leverages convolutional neural networks to automatically identify fire signatures from remote sensing images, offering a reliable and efficient solution for forest fire monitoring. A total of 30 different object detection models, including the proposed model, were run with the extended Wildfire Smoke dataset, and the results were compared. As a result of extensive experiments, it was observed that the proposed model gave the best result among all models, with a test mAP value of 96.9%. Our findings not only contribute to the advancement of fire detection technologies, but also underscore the importance of deep learning in addressing real-world environmental challenges. Full article

Accurate and rapid delineation of wildfire-affected areas is essential in the era of climate-driven increases in fire frequency. This study compares and analyzes four techniques for identifying wildfire-affected areas using Sentinel-2 satellite imagery: (1) calibrated differenced Normalized Burn Ratio (dNBR); (2) differenced NDVI (dNDVI) with empirically defined thresholds (0.04–0.18); (3) supervised SVM classifiers applying linear, polynomial, and RBF kernels; and (4) unsupervised ISODATA clustering. In particular, this study proposes an SVM-based classification method that goes beyond conventional index- and threshold-based approaches by directly using the SWIR, NIR, and RED band values of Sentinel-2 as input variables. It also examines the potential of the ISODATA method, which can rapidly classify affected areas without a training process and further assess burn severity through a two-step clustering procedure. The experimental results showed that SVM was able to effectively identify affected areas using only post-fire imagery, and that ISODATA enabled fast classification and severity analysis without training data. This study performed a wildfire damage analysis through a comparison of various techniques and presents a data-driven framework that can be utilized in future wildfire response and policy-oriented recovery support. Full article

Wildfires represent an increasing global concern, threatening ecosystems, human settlements, and economies. Chile, characterized by diverse climatic zones and extensive forested areas, has been particularly vulnerable to wildfire events over recent decades. In this context, real, long-term data are essential to understand wildfire dynamics and to design effective early warning and prevention systems. This paper introduces a unique dataset containing detailed wildfire occurrence and damage information across Chilean municipalities from 1985 to 2024. Derived from official records by the National Forestry Corporation of Chile CONAF, this dataset encompasses key variables such as the number of fires, total burned area, estimated material damages, and the number of affected individuals. It provides an invaluable resource for researchers and policymakers aiming to improve fire risk assessments, model fire behavior, and develop AI-driven early detection systems. The temporal span of nearly four decades offers opportunities for longitudinal analyses, the study of climate change impacts on fire regimes, and the evaluation of historical prevention strategies. Furthermore, by presenting a complete spatial coverage at the municipal level, it allows fine-grained assessments of regional vulnerabilities and resilience. Full article

Fire is a distinctive factor in forest ecosystems. While uncontrolled wildfires can cause significant damage, prescribed burning is widely used as a management tool. However, despite the growing threat of forest water stress under climate change, there is a lack of concrete evidence on the impact of fire on water stress in forest ecosystems. This study utilized Landsat time-series remote sensing data combined with the Infrared Canopy Dryness Index (ICDI) to monitor changes in canopy dryness patterns across the eucalyptus-dominated Northern Jarrah Forest of southwestern Australia. The forest was chosen due to its exposure to a changing climate characterized by decreasing rainfall and more frequent droughts, signs of water stress in otherwise drought-resilient trees, and its well-documented fire management history. Analysis of ICDI patterns over the period from 1988 to 2024 revealed a clear overall trend of increasing water stress, coinciding with a small overall decline in annual rainfall in the 10,000 km² study area. Furthermore, by examining five prescribed burns and five wildfires, we found that NDVI-assessed canopy cover recovered rapidly in fire-affected areas, typically within one to three years, depending on fire severity. However, ICDI water stress levels were reduced for approximately 7–8 years following low-severity prescribed burns and more than 20 years after high-severity wildfires. These findings suggest the potential of prescribed burning as a tool to mitigate water stress in vulnerable forest landscapes, particularly in regions prone to drought and climate change. Additionally, the study underscores the effectiveness of the ICDI in monitoring forest water stress and its potential for broader applications in forest management and climate adaptation strategies. Full article

The preservation of historic irrigation infrastructure is vital for sustainable water management, especially in regions grappling with rural depopulation, land degradation, and wildfire risk. This study presents a rehabilitation framework for the Acequia del Diablo (Teruel, Spain), a centuries-old gravity-fed canal that supported 60 hectares of agriculture and contributed to ecological connectivity. Its deterioration—following landslides in 1992 and water source loss in 2020—has led to land abandonment, biodiversity decline, and increased wildfire vulnerability. The proposed solution, centered on restoring the original intake at the Azud de Fonseca and stabilizing damaged sections, reestablishes water autonomy and integrates heritage conservation into water governance. A multi-criteria analysis identified this gravity-based alternative as the most technically, economically, and environmentally viable. Drawing from precedents in the literature, the conservation and rehabilitation of historical irrigation systems play a crucial role in sustainable water management in rural areas; this initiative offers a replicable model for other Mediterranean and semi-arid areas. However, challenges include engineering complexity in unstable terrain, administrative delays, and long-term maintenance. Despite these, this intervention enhances rural resilience, wildfire prevention, and biodiversity, while aligning with circular economy principles and European Green Deal objectives. Full article

Wildfires pose increasing risks to human settlements, particularly in the Wildland–Urban Interface (WUI). This study examines the relationship between land cover (LC) characteristics and housing destruction during the 2023 wildfires in Chile’s Bío-Bío region. Using high-resolution remote sensing data and GIS-based multi-buffer spatial analysis (30 m and 100 m), we assessed LC patterns around affected and unaffected rural houses. Results indicate that the proximity of forest plantations significantly increased housing loss, with a notably higher presence of plantations within 30 m of destroyed houses. In contrast, agricultural and pasture mosaics demonstrated a protective function by reducing fire spread. Shrublands also showed moderate protection, albeit with statistical uncertainty. The findings highlight the critical role of immediate LC in determining wildfire impact, emphasizing the need for integrating LC considerations into wildfire risk management, land-use planning, and policy interventions. Strategies such as creating defensible spaces, enforcing zoning regulations, and promoting fire-resistant landscapes can help mitigate future wildfire damage. This research provides spatially explicit insights that contribute to wildfire risk reduction theory and inform targeted prevention and resilience-building strategies in Chile and other fire-prone regions. Full article

The Internet of Things (IoT) offers transformative capabilities in enhancing public safety, disaster response, and emergency management by leveraging interconnected devices and real-time data. Through the IoT, smart sensors and networks are deployed across cities and environments to monitor critical parameters including air quality, structural integrity, and environmental changes. These systems provide early warnings for natural disasters such as earthquakes, floods, and wildfires, enabling authorities to respond proactively. In emergency management, IoT devices help coordinate resources and improve situational awareness during crises. Real-time data from wearable devices, smart infrastructure, and communication systems allow responders to track people, manage evacuations, and deploy resources more effectively. For example, IoT-enabled drones and autonomous vehicles are used to deliver supplies or assess damage in hazardous areas without risking human lives. IoT technologies improve post-disaster recovery by continuously monitoring areas for safety hazards and supporting infrastructure restoration. Smart traffic management systems assist in controlling traffic flow for emergency vehicles, while IoT-based communication networks ensure connectivity when traditional systems fail. The IoT significantly enhances the speed, accuracy, and effectiveness of disaster response and public safety operations, leading to the better protection of communities and faster recovery from emergencies. Full article

Portugal’s increasing wildfire frequency has led to home destruction, large areas burned, ecological damage, and economic loss, emphasizing the need for effective fire exposure assessments. This study builds on a Canadian approach to wildfire exposure and evaluates wildfire exposure in the Portuguese municipality of Mafra, using artificial territories (AT) as a proxy for the wildland–urban interface (WUI) and integrates land use land cover (LULC) data with a neighborhood analysis to map exposure at the municipal scale. Fire exposure was assessed for three fire transmission distances: radiant heat (RH, <30 m), short-range spotting (SRS, <100 m), and longer-range spotting (LRS, 100–500 m) using fine resolution (5 m) LULC data. Results revealed that while AT generally exhibited lower exposure (<16% “very high” exposure), adjacent hazardous LULC subtypes significantly increase wildfire hazard, with up to 51% of LULC subtypes classified as “very high exposure”. Field validation confirmed the accuracy of exposure maps, supporting their use in wildfire risk reduction strategies. This cost-effective, scalable approach offers actionable insights for forest and land managers, civil protection agencies, and policymakers, aiding in fuel management prioritization, community preparedness, and the design of evacuation planning. The methodology is adaptable to other fire-prone regions, particularly mediterranean landscapes. Full article

Climate change has emerged as a significant driver of the increasing frequency and severity of power outages. Rising global temperatures place additional stress on electrical grids that must meet substantial electricity demands, while extreme weather events such as hurricanes, floods, heatwaves, and wildfires frequently damage vulnerable electrical infrastructure. Ensuring the resilient operation of distribution systems under these conditions poses a major challenge. This paper presents a comprehensive two-stage techno-economic strategy to enhance the resilience of modern distribution systems. The approach optimizes the scheduling of distributed energy resources—including distributed generation (DG), wind turbines (WTs), battery energy storage systems (BESSs), and electric vehicle (EV) charging stations—along with the strategic placement of remotely controlled switches. Key objectives include preventing damage propagation through the isolation of affected areas, maintaining power supply via islanding, and implementing prioritized load shedding during emergencies. Since improving resilience incurs additional costs, it is essential to strike a balance between resilience and economic factors. The performance of our two-stage multi-objective mixed-integer linear programming approach, which accounts for uncertainties in vulnerability modeling based on thresholds for line damage, market prices, and renewable energy sources, was evaluated using the IEEE 33-bus test system. The results demonstrated the effectiveness of the proposed methodology, highlighting its ability to improve resilience by enhancing system robustness, enabling faster recovery, and optimizing operational costs in response to high-impact low-probability (HILP) natural events. Full article

Wildfires, a natural part of the wildland life cycle, are experiencing a decades-long trend of increased frequency, duration, and magnitude, resulting in increased risk of fatalities and property damage. Fire suppression methods are adapting accordingly, including the increased use of aerial firefighting. Aerial firefighting, conducted in coordination with ground crews, provides real-time reconnaissance of a wildfire and performs strategic drops of retardant to contain and/or suppress the fire. These flight operations require airport and air traffic control infrastructure. The purpose of this report is to provide statistics on the U.S. aerial firefighting fleet, flight operations, and airport utilization and equipment in 2024. This information, which is not readily available, may be of use to airport planners, air navigation service providers, and policy makers. Thirty-four (34) Very Large/Large Air Tankers (VLAT/LATs) were under contract with the United States Forest Service (USFS) Multiple Award Task Order Contracts (MATOCs) in 2024. The aircraft, ranging in age from 27 to 57 years, performed 11,219 retardant drop and reposition flights. Flights operated on 88% of the days with an average of 35 flights per day and a maximum of 200 flights per day. The number of flights per aircraft across the fleet was not uniform (average 288 flights, max 465 flights). Consistent with firefighting practices, the flights operated under Visual Flight Rules (VFR), mostly in the afternoons, with an average retardant drop flight duration of 34 min. Two hundred and seven (207) airports supported at least one departure, with 14 airports supporting 50% of the departures. Eighty-six (86%) percent of the airports were towered and 84% had precision approach procedures. All but two military airports were public airports that are part of the National Plan for Integrated Airport System (NPIAS) and eligible for Airport Improvement Plan (AIP) funding. Runway length and weight bearing are limitations at several airports. Furthermore, operations are no longer limited to airports west of the Rockies, with increased operations in the mid-west and east coast. 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

Wildfire activity in the western U.S. has highlighted the importance of effective management to address this growing threat. The Lookout Mountain Thinning and Fuels Reduction Study (LMS) is an operational-scale, long-term study of the effects of forest restoration and fuel reduction treatments in ponderosa pine (Pinus ponderosa Dougl. ex Laws.) and mixed-conifer forests in central Oregon, U.S. The broad objectives of the LMS are to examine the effectiveness and longevity of treatments on wildfire risk and to assess the collateral effects. Treatments include four levels of overstory thinning followed by mastication of the understory vegetation and prescribed burning. Stands were thinned to residual densities of 50, 75, or 100% of the upper management zone (UMZ), which accounts for site differences as reflected by stand density relationships for specific plant communities. A fourth treatment combines the 75 UMZ with small gaps (~0.1 ha) to facilitate regeneration (75 UMZ + Gaps). A fifth treatment comprises an untreated control (UC). We examined the causes and levels of tree mortality that occurred 2–9 years after treatments. A total of 391,292 trees was inventoried, of which 2.3% (9084) died. Higher levels of tree mortality (all causes) occurred on the UC (7.1 ± 1.9%, mean ± SEM) than on the 50 UMZ (0.7 ± 0.1%). Mortality was attributed to several bark beetle species (Coleoptera: Curculionidae) (4002 trees), unknown factors (2682 trees), wind (1958 trees), suppression (327 trees), snow breakage (61 trees), prescribed fire (19 trees), western gall rust (15 trees), cankers (8 trees), mechanical damage (5 trees), dwarf mistletoe (4 trees), and woodborers (3 trees). Among bark beetles, tree mortality was attributed to western pine beetle (Dendroctonus brevicomis LeConte) (1631 trees), fir engraver (Scolytus ventralis LeConte) (1580 trees), mountain pine beetle (Dendroctonus ponderosae Hopkins) (526 trees), engraver beetles (Ips spp.) (169 trees), hemlock engraver (Scolytus tsugae (Swaine)) (77 trees), and Pityogenes spp. (19 trees). Higher levels of bark beetle-caused tree mortality occurred on the UC (2.9 ± 0.7%) than on the 50 UMZ (0.3 ± 0.1%) which, in general, was the relationship observed for individual bark beetle species. Higher levels of tree mortality were attributed to wind on the 100 UMZ (1.0 ± 0.2%) and UC (1.2 ± 1.5%) than on the 50 UMZ (0.2 ± 0.02%) and 75 UMZ (0.4 ± 0.1%). Higher levels of tree mortality were attributed to suppression on the UC (0.5 ± 0.3%) than on the 50 UMZ (0.003 ± 0.002%) and 75 UMZ + Gaps (0.0 ± 0.0%). Significant positive correlations were observed between measures of stand density and levels of tree mortality for most causal agents. Tree size (diameter at 1.37 m) frequently had a significant effect on tree mortality, but relationships varied by causal agent. The forest restoration and fuels reduction treatments implemented on the LMS increased resistance to multiple disturbances. The implications of these and other results to the management of fire-adapted forests are discussed. Full article