Search Results (2,929)

The wildfires in the vicinity of the power transmission corridors are famous for their sudden occurrence, rapid growth, and susceptibility to interference from fire-like interferences at night, which can easily lead to line discharge and trip accidents, thus affecting the safe operation of the power system. In order to address the issue of the high false alarm rate and poor generalization performance of wildfire image recognition in complex power transmission corridor environments, a wildfire image recognition method based on an improved AlexNet is proposed in this paper. The proposed method improves the description of flame and smoke properties at different scales by designing a reparameterized multi-scale feature extraction structure, and effectively alleviates the influence of strong light reflection and fire-like interference at night by using lightweight multi-scale attention and hybrid pooling attention mechanisms. A wildfire image dataset is constructed based on 1246 on-site images of the power transmission corridor captured by a visual monitoring device and 600 wildfire images downloaded from the internet, and tested in real-world imbalanced distribution scenarios. The experimental results show that the proposed method can recognize wildfire images with an accuracy of 96.9% and an F1 value of 94.9% on the test dataset, which is much higher than that of the original AlexNet, and has a strong ability to adapt to cross-dataset tests. The research work can provide technical support for online monitoring and operation and maintenance of wildfires in power transmission corridors. Full article

A substantial proportion of wildfires in Mediterranean regions continue to be recorded without information about the cause or source of ignition, limiting our ability to understand ignition drivers and design effective prevention strategies. In this study, we develop a spatially harmonised wildfire database for mainland Spain by integrating ignition records from the Spanish General Fire Statistics (EGIF) with fire perimeters generated from satellite images. We then apply a Random Forest classifier to infer ignition causes for events lacking cause attribution. To interpret model behaviour, we use Shapley Additive Explanation (SHAP) values at both global and local scales. Results indicate that human-caused ignitions are dominant, with intentional and negligence-related fires accounting for 52.13% of all known events, although they are associated with contrasting climatic and land-use settings. Negligence-related fires tend to occur under hot, dry and windy conditions, often in agricultural interfaces, whereas intentional fires are more frequent under cooler and wetter conditions and in areas with higher population density and land-use change. Lightning-caused fires represent a small fraction of total ignitions (3%) but exhibit a distinct climatic signature, occurring primarily in sparsely populated areas, under intermediate moisture conditions, and often leading to larger burned areas. Despite strong overall model performance (F1-score = 0.82), minority classes (e.g., lightning and fire rekindling, 0.17%) remain challenging to classify, reflecting both data imbalance and uncertainty in causal attribution. Overall, the combined use of machine learning and explainable AI provides a coherent spatial characterisation of wildfire ignition drivers across mainland Spain, highlights systematic differences among ignition causes, and identifies key limitations in existing fire cause records. This framework represents a practical step towards improving fire cause information by integrating remote sensing products with field-based fire reports, thereby supporting more targeted and evidence-based fire risk management. Full article

Community land management plays an important role in wildfire-prone landscapes in Mediterranean Europe. However, in Portugal, information on the spatial extent and boundaries of community land remains fragmented across multiple institutions. This study addresses a critical but often overlooked issue in wildfire management: the fragmentation of institutional data on community land boundaries in mainland Portugal and its direct implications for forest fire risk management, planning, and accountability. We harmonized georeferenced datasets from various government and public institutions, applying multi-institutional spatial integration supported by legal land use criteria using the Land Use Land Cover map 2018 (LULC2018). The resulting national map represents the first fully harmonized spatial assessment of community land (baldios) in mainland Portugal. Our results show that baldios currently occupy approximately 595 thousand hectares, significantly exceeding official estimates. Of this total, around 74% are under partial forest regime law, and approximately 76% are classified as having a high or very high wildfire hazard. This means that three out of every four hectares of baldios in mainland Portugal are structurally susceptible to extreme wildfire conditions. Beyond improving cartographic data, the study’s findings demonstrate how the lack of land registry weakens the institutional foundations for community-based wildfire management. Without a functional, legally validated national map of community land boundaries, responsibilities, co-management mechanisms, and prevention measures remain spatially inconsistent. Full article

Wildfires represent a significant global environmental challenge, necessitating advanced monitoring and assessment techniques. This study explores the integration of Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical data within a Google Earth Engine (GEE) framework to enhance wildfire detection, burned area estimation, and severity assessment. By leveraging SAR’s capability to penetrate atmospheric obstructions and optical data’s spectral sensitivity to vegetation changes, the proposed methodology addresses limitations of single-sensor approaches. The results demonstrate strong correlations between SAR-based indices, such as the Radar Vegetation Index (RVI) and Dual-Polarized SAR Vegetation Index (DPSVI), and traditional optical indices, including the Normalized Burn Ratio (NBR) and differenced NBR (ΔNBR). Despite challenges related to terrain influence, sensor resolution differences, and computational demands, the integration of multi-sensor data in a cloud-based environment offers a scalable and efficient solution for wildfire monitoring. During the peak of the fire events, significant atmospheric obstruction was technically verified using Sentinel-2 metadata and the QA60 cloud mask band, which confirmed persistent cloud cover and thick smoke plumes over the study areas. This interference limited the reliability of purely optical monitoring, further justifying the integration of SAR data. Future research should focus on refining data fusion techniques, incorporating additional datasets such as thermal infrared imagery and meteorological variables, and enhancing automation through artificial intelligence (AI). This study underscores the potential of remote sensing advancements in improving fire management strategies and global wildfire mitigation efforts. Full article

This study presents a comprehensive wildfire risk assessment framework for Rhodes Island, Greece, aimed at quantifying the impacts of climate change on hazard levels and vulnerability in a typical Mediterranean environment. The approach integrates Fire Weather Index (FWI) data, detailed fuel-type mapping, and multiple vulnerability indicators covering ecological, socioeconomic, and population factors, enabling spatially explicit estimates of current and future wildfire risk. Historically, Rhodes mostly faces moderate wildfire risk, mainly in central and northeastern regions, with localised areas of higher risk near settlements and key economic sites. Climate forecasts for 2025–2049 predict a notable increase in hazard, with areas experiencing extreme fire weather (FWI > 50) increasing from 15.19% to 66–72%, across all emission scenarios. Ecological vulnerability is particularly alarming, as 93% of the island is already highly susceptible; fire-prone forest and agricultural zones are expected to move into the highest ecological risk categories, especially in the central mountain areas. The devastating 2023 wildfire, which burned over 17,600 hectares, caused more than €5.8 million in direct damages and led to the largest evacuation in the island’s history, closely aligning with high-risk zones modelled in the framework. An important insight is the limited spatial variation in near-future risk between RCP 4.5 and RCP 8.5, indicating that significant wildfire intensification is largely unavoidable by mid-century, emphasising the urgent need for quick adaptation and risk mitigation efforts for Mediterranean critical infrastructure and communities. Full article

Cross-sectional surveys of psychological distress using the Kessler-6 tool (K6+) were conducted among training cohorts per year of New Jersey (NJ) secondary school teachers between January 2022 and December 2024. Data downloaded for 12–18 annual virtual synchronous live session training date ranges related to specified teacher cohorts, consisting of 30 calendar days prior to its date to relate to K6+ questions (575 unique participants across 42 total live sessions). Utilizing data from federal/state air quality monitoring stations (AQMS), we constructed a database of estimated exposures to ambient/outdoor air quality. Cohorts were broken down by school district (SD) and paired with AQMS based on approximate geographic proximity for each SD’s school’s physical address utilizing NJ-GeoWeb. Once addresses were reported and associated with two AQMS, associated reviewed daily criteria pollutant data (2021–2024) were retrieved for particulate matter (PM, PM₁₀ and PM_2.5) and ozone. Data were averaged for relevant stations. Analyses suggested prior 30-day PM_2.5 showed a significant negative correlation with K6+ scores, −0.32 with PM_2.5 concentration (p = 0.04) and −0.48 with PM_2.5 AQI (p = 0.002); however, wind speed had a positive association, 0.33, with K6+ scores (p = 0.03). These results suggested how specific events and meteorological conditions affected ambient air quality for only some of the prior 30 days yet still potentially influenced K6+ scores for some cohorts, e.g., large wildfires then prevailing winds. More research with improved exposure assessment is warranted. This initial environmental epidemiology study with ecological design can inform future collaborative research and practice work on mental health and the effects of environmental factors. Full article

With the increasing number of wildfire events, people living close to the wildland–urban interface (WUI) are more likely to be exposed to these events. To mitigate the hazards related to wildfires, it is of great importance to identify areas where human settlements are at a greater risk. Remote sensing-based techniques for mapping and quantifying the inhabitants possibly affected by these events are crucial to reduce the loss of life as well as reduce the negative impact that wildfires pose to the people living in WUIs, the surrounding areas, and the environment. Fine-scale mapping is a suitable auxiliary tool to indicate areas at greater risk. Hence, the dasymetric method was applied to generate a high-resolution map of the study area’s population, using products generated from Sentinel-2 imagery, a census, and Light Detection and Ranging (LiDAR) data. The findings of the proposed methodology show that around 59% of the population in the study area currently lives inside the WUI, while in 2025, most of the people affected by wildfires—77%—lived outside the WUI. This is expected, since wildfires vary in space and time, and they are seen as spatial–temporal processes. In addition, the results demonstrated that women are slightly more exposed to wildfires than other population groups. These results showed that the proposed methodology could not only help identify high-risk areas but also the number of people living in these areas due to the high-resolution dasymetric methodology. The proposed methodology described in this work shows that fine-scale mapping could enrich forest management in order to protect the populations susceptible to the negative impacts of wildfires, consequently protecting the environment. Full article

Climate hazards increasingly disrupt schooling, revealing the limits of preparedness models that treat teachers only as implementers. This study reframes teacher empowerment as a climate-resilience capability and examines how governance arrangements enable (or constrain) hazard-ready education systems. Guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR), searches of Web of Science, Scopus, and Google Scholar (2000–2025) identified 53 eligible studies. Across diverse hazards and settings, the evidence converges on a governance-to-capability pathway: empowerment becomes resilient performance only when the delegated decision space is matched with financed capacity (time, training, contingency resources), timely risk information and functional communication/digital infrastructure, institutionalized cross-sector coordination (education–DRR–health–protection–local government), and learning-oriented accountability (after-action review and adaptive revision rather than punitive compliance). Reported outcomes include higher preparedness quality, earlier protective action, improved learning continuity and safeguarding, and more sustainable teacher well-being/retention. Predictable failure modes include mandate–resource mismatch, accountability overload, unstable centralization–autonomy dynamics, and inequitable empowerment distribution affecting rural schools, women, and contract teachers, and disability inclusion. The evidence gaps remain pronounced for chronic hazards (especially heat and wildfire smoke), high-vulnerability contexts (fragile/conflict settings and informal settlements), and standardized measures of equity, burden distribution, governance performance, and cost-effectiveness. Policies should prioritize integrated governance packages with explicit protection and equity safeguards. Full article

Floodplain disconnection caused by channel incision and/or levee construction has led to widespread loss of riparian habitats and ecosystem functions globally. Restoring full stream–floodplain connectivity is increasingly promoted, yet evidence of ecological outcomes remains limited. This study evaluates the initial performance of two Stage 0 restoration projects on Whychus Creek, Oregon, which reconnected incised channels to their historical floodplains in 2012 and 2016. We combined pre- and post-restoration vegetation surveys along fixed transects with hydrogeomorphic-based riparian and wetland function assessments and applied quantitative analyses, including Kruskal–Wallis tests, Jaccard correlations, Sorensen similarity indices, and factor analysis, to compare changes in plant assemblages and ecosystem functions across restored, transitional, and unrestored reaches. Our research results indicate that two years post-restoration, the active riparian area expanded 2.5-fold, species richness and structural diversity increased significantly, and riparian and wetland functions such as water storage, sediment retention, and habitat support for fish and amphibians improved markedly. Numbers of anadromous salmonids also increased markedly. This is important as salmon recovery is a regional stream restoration goal. Comparisons with a reach restored six years earlier suggest a positive trajectory toward mature, resilient ecosystems. These findings demonstrate that Stage 0 restoration can rapidly reestablish complex habitat mosaics and enhance ecosystem services critical for biodiversity, water quality, and flood resilience. Practically, this evidence supports process-based restoration strategies that prioritize full floodplain reconnection as a cost-effective approach to reversing long-term ecological degradation. Continued monitoring is essential to guide adaptive management and strengthen the evidence base for the wide-scale implementation of valley-floor wide stream restoration. Full article

Wildfires are increasingly complex and geographically dynamic phenomena that require timely and context-sensitive decision support across the management cycle. Artificial intelligence (AI) has been widely applied to wildfire detection, prediction, and remote sensing; however, a systemic understanding of how AI methods are structurally integrated into decision-support architectures remains limited. The present configurational mapping review, reported in alignment with PRISMA-ScR guidance, examines AI applications in rural wildfire management between 2020 and 2024. Using a configurational framework, explicit scope–algorithm–vector relations are mapped, identifying how specific AI paradigms are operationalised through technological infrastructures to support decision-relevant functions. A total of 27 articles were included, from which 168 scope–algorithm–vector triplets were extracted and analysed descriptively. The results reveal a concentration of applications in detection and evolution prediction tasks, predominantly supported by machine learning methods and remote sensing platforms. Explicitly linked configurations to action-oriented or prescriptive decision functions are less frequently documented. The findings contribute to a structured mapping of AI deployment patterns in wildfire management and provide a conceptual basis for future research addressing integrative and action-oriented system design. Full article

Wildfires have become more frequent and intense worldwide due to climate change and anthropogenic activities, which is why accurate and timely burned area mapping is essential for estimating damage and effective post-fire recovery planning. Synthetic Aperture Radar (SAR) data, which operates under all weather conditions and day-night cycles, offers a reliable source for burned area mapping. In this context, several studies have explored the use of dual-polarization SAR imagery and machine learning, yet the influence of multi-date, dual-orbit pass data and texture features remained unexplored. Therefore, this study aims to assess the Sentinel-1 acquisition configurations, varying in temporal depth and orbital direction, for wildfire burned area mapping, considering the recent Palisades wildfire event as a study area. A comparative study was conducted across different scenarios to evaluate the effectiveness of using single-date versus multi-date SAR imagery, the integration of ascending and descending orbit passes, and the contribution of Grey-Level Co-occurrence Matrix texture features. The performance of Random Forest (RF) and Extreme Gradient Boosting classifiers was analyzed through the scenarios mentioned above. The single-date configuration using RF achieved an accuracy of 82.34%, F1-score of 81.43%, precision of 83.07%, recall of 80.84%, and ROC-AUC of 90.88%, whereas the multi-date approach reached 85.78%, 85.15%, 86.45%, 84.56%, and 93.28%, respectively. Our study highlights the importance of acquisition configuration and texture information for reliable SAR-based wildfire burned area assessment. Full article

The background modification of ecosystems affected by fire can cause black or dark colours in animals to become adaptive, providing better protection against visually oriented predators. We surveyed fire-prone Mediterranean woodlands to describe the behaviour, position and background characteristics of the black cicada Tibicina quadrisignata Hagen, 1855 found in recently burnt and unburnt trees. A human detectability test, using cicada pictures in natural backgrounds taken during the fieldwork, was used to assess detection risk. Most cicadas found were solitary males uttering courtship song. Many cicadas flew when approached, with 82% of flight initiation distances being less than 3 m and half of the flights being less than 30 m. Cicadas favoured sunny locations in early morning, and shady sites as the temperature increased. Fire altered fine-scale microhabitat use by cicadas, since cicadas were found in 71% thicker stems and at 14% lower height on the tree, in burnt trees, in relation to unburnt trees. Generalised Linear Mixed Models (GLMMs) revealed a negative fire effect on cicada detection by human test participants. The probability of detection fell from 0.62 in unburnt backgrounds to 0.48 in burnt backgrounds, while the time needed for detection did not change between burnt and unburnt sites. Overall, these results show that T. quadrisignata cicadas adjust their substrate use after fire and are less detectable on burnt backgrounds. Real predation risk, however, also depends on thermoregulation-associated exposure, courtship song activity and predator densities. Full article

Prescribed fire is a vital tool for ecosystem management and wildfire risk reduction but its escalation is constrained by overly conservative burn windows because of uncertainties, for instance, in wind forecasts. This review describes the state of the art in weather product use by fire/smoke models and identifies three priority research gaps that artificial intelligence/machine learning (AI/ML) is well positioned to address: (1) spatial and temporal downscaling to meter-scale, sub-hourly wind fields; (2) bias correction for systematic model errors in complex terrain; and (3) robust uncertainty quantification to inform ensemble-based simulations. Emerging AI/ML techniques offer promising frameworks to address all three challenges. By providing high-resolution, bias-corrected, and probabilistic wind fields, AI/ML-enhanced forecasts will allow for expanded burn windows, improved ignition strategy design and a reduced reliance on expert intuition, especially when a prescribed fire is introduced into new areas. Full article

Following bushfires (also known as wildfires), impacted free-living wildlife with welfare or conservation concerns are captured and presented for veterinary assessment where possible. This study represents an in-depth retrospective analysis of the veterinary records of 259 animals in Victoria, Australia, impacted by bushfire in 2019–2020. In total, 35 different species were assessed, including 196 koalas. Multivariable analyses of 126 koalas with complete medical records identified several clinical prognostic factors affecting 6-month survival outcomes. Increased odds of negative outcomes (death or euthanasia) were associated with increasing age (tooth wear class; odds ratio 2.70 for one unit increase), lower body condition score (one-unit decrease OR 7.27), and the earlier animals were presented after the fire event (OR 0.94 for each passing day). In 83 koalas with burn injuries, negative outcomes were also associated with burns more severe than minor (85% survival for minor burns only, compared to 31% survival with moderate or severe burns), and burns to more than 10 digits (12% survival). In burnt koalas, the combination of burn severity and digital involvement appear to be important prognostic factors for long-term outcomes. These findings can support veterinarians to more accurately evaluate prognosis for bushfire-affected koalas during initial assessment and will facilitate the strategic allocation of limited treatment and rehabilitation resources to the animals most likely to recover. The scope of this study was limited to the consideration of health outcomes, with the recognition of health as just one of many factors that must inform decisions about rehabilitating injured wildlife. Full article

Efficient and accurate active fire detection is crucial for timely firefighting and mitigating hazards. Geostationary satellites deliver high-frequency observations that offer valuable data for near-real-time fire monitoring. However, current operational fire detection algorithms often underutilize temporal information, failing to decouple fire-induced anomalies from inherent surface thermal heterogeneity, which results in frequent false alarms. To address this limitation, we constructed a ten-day historical background brightness temperature (BT) reference database from multi-year Himawari-8/9 data, serving as a stable, fire-undisturbed baseline. Based on this, an active fire detection algorithm was developed that integrates instantaneous spatial–contextual differences with historical deviations of these differences from the reference database. Evaluated against a robust dataset of over 55,000 fire pixels (cross-verified using 10 m Sentinel-2 burn-scar data), the proposed algorithm significantly outperforms the Himawari-8/9 Wildfire (WLF) product, achieving a commission error (CE) of 2.9%, an omission error (OE) of 37.5%, and an F1-score of 0.76. The framework demonstrated superior detection accuracy in challenging scenarios such as low-temperature, smoke-obscured, and early-stage fires, while maintained robust performance across diverse fire types. The approach enables rapid full-disk fire detection in less than one minute and can be adapted to other geostationary satellites, providing a technical foundation for building a globally coordinated fire monitoring system. Full article