Search Results (30)

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

To address the recent increase in wildfire severity and incidence, as well as the subsequent financial and physical costs, forest managers and wildland firefighting agencies rely on remotely sensed products for better decision-making and mitigation efforts. To address the remote sensing needs of these agencies, which include high spatial resolution, immunity to atmospheric and solar illumination effects, and day/night capabilities, the use of synthetic aperture radar (SAR) is under investigation for application in current and upcoming systems for all phases of a wildfire. Focusing on the active phase, a method for monitoring wildfire activity is presented based on changes in the radar vegetation index (RVI). L-band backscatter measurements from NASA/JPL’s UAVSAR instrument are used to obtain RVI images on multiple dates during the 2020 Bobcat (located in Southern CA, USA) and Hennessey (located in Northern CA, USA) fires and the 2021 Caldor (located in the Sierra Nevada region of CA, USA) fire. Changes in the RVI between measurement dates of a single fire are then compared to indicators of fire activity such as ancillary GIS-based burn extent perimeters and the Landsat 8-based difference normalized burn ratio (dNBR). An RVI-based wildfire “burn” detector/index is then developed by thresholding the RVI change. A combination of the receiver operating characteristic (ROC) curves and F1 scores for this detector are used to derive change detection thresholds at varying spatial resolutions. Six repeat-track UAVSAR lines over the 2020 fires are used to determine appropriate threshold values, and the performance is subsequently investigated for the 2021 Caldor fire. The results show good performance for the Bobcat and Hennessey fires at 100 m resolution, with optimum probability of detections of 67.89% and 71.98%, F1 scores of 0.6865 and 0.7309, and Matthews correlation coefficients of 0.5863 and 0.6207, respectively, with an overall increase in performance for all metrics as spatial resolution becomes coarser. The results for pixels identified as “burned” compare well with other fire indicators such as soil burn severity, known progression maps, and post-fire agency publications. Good performance is also observed for the Caldor fire where the percentage of pixels identified as burned within the known fire perimeters ranges from 37.87% at ~5 m resolution to 88.02% at 500 m resolution, with a general increase in performance as spatial resolution increases. All detections for Caldor show dense collections of burned pixels within the known perimeters, while pixels identified as burned that lie outside of the know perimeters have a sparse spatial distribution similar to noise that decreases as spatial resolution is degraded. The Caldor results also align well with other fire indicators such as soil burn severity and vegetation disturbance. Full article

In 2020, wildfires scarred over 4,000,000 hectares in the western United States, devastating urban populations and ecosystems alike. The significant impact that wildfires have on plants, animals, and human environments makes wildfire adaptation, management, and mitigation strategies a critical task. This study uses satellite imagery from Landsat to calculate burn severity and map the fire progression for the Dolan Fire of central Coastal California which occurred in August 2020. Several environmental factors, such as temperature, humidity, fuel type, topography, surface conditions, and wind velocity, are known to affect wildfire spread and burn severity. The aim of this study is the investigation of the relationship between these environmental factors, estimates of burn severity, and fire spread patterns. Burn severity is calculated and classified using the Difference in Normalized Burn Ratio (dNBR) before being displayed as a time series of maps. The Dolan Fire had a moderate severity burn with an average dNBR of 0.292. The ignition site location, when paired with the patterns of fire spread, is consistent with wind speed and direction data, suggesting fire movement to the southeast of the fire ignition site. Patterns of increased burn severity are compared with both topography (slope and aspect) and fuel type. Locations that were found to be more susceptible to high burn severity featured Long Needle Timber Litter and Mature Timber fuels, intermediate slope angles between 15 and 35°, and north- and east-facing slopes. This study has implications for the future predictive modeling of wildfires that may serve to develop wildfire mitigation strategies, manage climate change impacts, and protect human lives. Full article

The rising severity and frequency of wildfires in recent years in the United States have raised numerous concerns regarding the improvement in wildfire emergency response management and decision-making systems, which require operational high temporal and spatial resolution monitoring capabilities. Satellites are one of the tools that can be used for wildfire monitoring. However, none of the currently available satellite systems provide both high temporal and spatial resolution. For example, GOES-17 geostationary satellite fire products have high temporal (1–5 min) but low spatial resolution (≥2 km), and VIIRS polar orbiter satellite fire products have low temporal (~12 h) but high spatial resolution (375 m). This work aims to leverage currently available satellite data sources, such as GOES and VIIRS, along with deep learning (DL) advances to achieve an operational high-resolution, both spatially and temporarily, wildfire monitoring tool. Specifically, this study considers the problem of increasing the spatial resolution of high temporal but low spatial resolution GOES-17 data products using low temporal but high spatial resolution VIIRS data products. The main idea is using an Autoencoder DL model to learn how to map GOES-17 geostationary low spatial resolution satellite images to VIIRS polar orbiter high spatial resolution satellite images. In this context, several loss functions and DL architectures are implemented and tested to predict both the fire area and the corresponding brightness temperature. These models are trained and tested on wildfire sites from 2019 to 2021 in the western U.S. The results indicate that DL models can improve the spatial resolution of GOES-17 images, leading to images that mimic the spatial resolution of VIIRS images. Combined with GOES-17 higher temporal resolution, the DL model can provide high-resolution near-real-time wildfire monitoring capability as well as semi-continuous wildfire progression maps. Full article

Wildfires play a crucial role in the transformation of forest ecosystems and exert a significant influence on the global climate over geological timescales. Recent shifts in climate patterns and intensified human–forest interactions have led to an increase in the incidence of wildfires. These fires are characterized by their extensive coverage, higher frequency, and prolonged duration, rendering them increasingly destructive. To mitigate the impact of wildfires on climate change, ecosystems, and biodiversity, it is imperative to conduct systematic monitoring of wildfire progression and evaluate their environmental repercussions on a global scale. Satellite remote sensing is a powerful tool, offering precise and timely data on terrestrial changes, and has been extensively utilized for wildfire identification, tracking, and impact assessment at both local and regional levels. The Canada Centre for Mapping and Earth Observation, in collaboration with the Canadian Forest Service, has developed a comprehensive National Burned Area Composite (NBAC). This composite serves as a benchmark for curating a bi-temporal multi-source satellite image dataset for change detection, compiled from the archives of Sentinel-2, Sentinel-1, and ALOS-2 PALSAR-2. To our knowledge, this dataset is the inaugural large-scale, multi-source, and multi-frequency satellite image dataset with 20 m spatial resolution for wildfire mapping, monitoring, and evaluation. It harbors significant potential for enhancing wildfire management strategies, building upon the profound advancements in deep learning that have contributed to the field of remote sensing. Based on our curated dataset, which encompasses major wildfire events in Canada, we conducted a systematic evaluation of the capability of multi-source satellite earth observation data in identifying wildfire-burned areas using statistical analysis and deep learning. Our analysis compares the difference between burned and unburned areas using post-event observation solely or bi-temporal (pre- and post-event) observations across diverse land cover types. We demonstrate that optical satellite data yield higher separability than C-Band and L-Band Synthetic Aperture Radar (SAR), which exhibit considerable overlap in burned and unburned sample distribution, as evidenced by SAR-based boxplots. With U-Net, we further explore how different input channels influence the detection accuracy. Our findings reveal that deep neural networks enhance SAR’s performance in mapping burned areas. Notably, C-Band SAR shows a higher dependency on pre-event data than L-Band SAR for effective detection. A comparative analysis of U-Net and its variants indicates that U-Net works best with single-sensor data, while the late fusion architecture marginally surpasses others in the fusion of optical and SAR data. Accuracy across sensors is highest in closed forests, with sequentially lower performance in open forests, shrubs, and grasslands. Future work will extend the data from both spatial and temporal dimensions to encompass varied vegetation types and climate zones, furthering our understanding of multi-source and multi-frequency satellite remote sensing capabilities in wildfire detection and monitoring. Full article

Spatial and temporal estimates of burned areas are often used to model greenhouse gas and air pollutant emissions from fire events that occur in a region of interest and over specified time frames. However, fire behaviour, fuel consumption, fire severity, and ecological effects vary over both time and space when a fire grows across varying fuels and topography under different environmental conditions. We developed a method for estimating the progression of individual wildfires (i.e., day-of-burn) employing ordinary kriging of a combination of different satellite-based active fire detection data sources. We compared kriging results obtained using active fire detection products from the Moderate Resolution Imaging Spectroradiometer (MODIS), the Visible Infrared Imaging Radiometer Suite (VIIRS), and combined MODIS and VIIRS data to study how inferences about a wildfire’s evolution vary among data sources. A quasi-validation procedure using combined MODIS and VIIRS active fire detection products that we applied to an independent data set of 37 wildfires that occurred in the boreal forest region of the province of Ontario, Canada, resulted in nearly half of each fire’s burned area being accurately estimated to within one day of when it actually burned. Our results demonstrate the strengths and limitations of this geospatial interpolation approach to mapping the progression of individual wildfires in the boreal forest region of Canada. Our study findings highlight the need for future validations to account for the presence of spatial autocorrelation, a pervasive issue in ecology that is often neglected in day-of-burn analyses. Full article

Fire risk assessment is a crucial step in effective fire control, playing an important role in reducing fire losses. It has remained a significant topic in the field of fire safety. To explore the research hotspots and frontier trends in fire risk assessment and to understand its macroscopic development trajectory, a sample of 1596 papers from 1976 to 2023, extracted from the Web of Science (WoS) database, was utilized to create a knowledge map. The study employed bibliometric methods, visual analysis, and content analysis to uncover the research pulse and hotspots in the field, offering insights into its future development. The findings indicate that research in fire risk assessment has demonstrated continuous growth over the past 50 years. China and the United States are the dominant research forces in the field, while India and Australia show potential as new drivers for development. Expert groups have formed in this field, with intra-institutional cooperation being the primary focus, while inter-institutional collaboration remains limited. The research outcomes exhibit multidisciplinary crossovers, exerting a significant impact on various disciplinary domains. The research hotspots primarily revolve around investigating fire and explosion accidents, assessing the vulnerability of fire subjects, and identifying potential fire hazards. The application of artificial intelligence technology is identified as a pivotal tool for future development. However, to achieve substantial progress, it is important to enhance the importance accorded to fire risk assessment, foster multinational and cross-institutional cooperation, and prioritize research innovation. Full article

One of the primary tools used for determining the origin of a wildfire is analyzing burn patterns formed during the fire progression. These patterns, called fire pattern indicators, are interpreted and used to document the direction of fire movement at specific points, creating a directional map back to the specific area of origin. This concept was first set forth in 1978 by a U.S. governmental organization, the National Wildfire Coordinating Group (NWCG). Their recommendations are currently (2016) in the third edition, and in our study, we examine these indicators. Specifically, the objective was to perform a validation exercise where controlled burns were conducted of natural vegetation plots but augmented with 32 identical sets of staged artifacts which would provide additional opportunities for fire movement to create observable directional fire pattern indicators. Three adjacent plots were burned, each using a single point ignition, all located on level, scrubland terrain. The burns were conducted in the fall season, under low to moderate burning conditions. The research was structured as a preliminary study, since only mild terrain and weather conditions were encompassed. The actual fire movements were documented by drone videos, additional ground-based videos, and still photography. Within the three burn plots, a total of 12 data sites out of 32 data sites were selected: each one containing 7 to 12 individual artifacts. Each artifact was photographically documented post-fire, and the actual fire movement direction at that location was established. Assessment entailed the use of four experienced wildland fire investigators, with each one independently assessing the direction and type of fire spread at each artifact using the photographic site evidence. An analysis was then conducted to make a statistical comparison between the actual fire movement direction and the direction estimates provided by the experts analyzing the photographic evidence and the limited information on conditions provided. The results indicate an average error of 103°. These results indicate that additional efforts are needed to study the scientific basis of the indicators and to evolve improvements in both the indicators and in the accompanying guidance to investigators. Full article

With the progress of science and technology, artificial intelligence is widely used in various disciplines and has produced amazing results. The research of the target detection algorithm has significantly improved the performance and role of unmanned aerial vehicles (UAVs), and plays an irreplaceable role in preventing forest fires, evacuating crowded people, surveying and rescuing explorers. At this stage, the target detection algorithm deployed in UAVs has been applied to production and life, but making the detection accuracy higher and better adaptability is still the motivation for researchers to continue to study. In aerial images, due to the high shooting height, small size, low resolution and few features, it is difficult to be detected by conventional target detection algorithms. In this paper, the UN-YOLOv5s algorithm can solve the difficult problem of small target detection excellently. The more accurate small target detection (MASD) mechanism is used to greatly improve the detection accuracy of small and medium targets, The multi-scale feature fusion (MCF) path is combined to fuse the semantic information and location information of the image to improve the expression ability of the novel model. The new convolution SimAM residual (CSR) module is introduced to make the network more stable and focused. On the VisDrone dataset, the mean average precision (mAP) of UAV necessity you only look once v5s(UN-YOLOv5s) is 8.4% higher than that of the original algorithm. Compared with the same version, YOLOv5l, the mAP is increased by 2.2%, and the Giga Floating-point Operations Per Second (GFLOPs) is reduced by 65.3%. Compared with the same series of YOLOv3, the mAP is increased by 1.8%, and GFLOPs is reduced by 75.8%. Compared with the same series of YOLOv8s, the detection accuracy of the mAP is improved by 1.1%. Full article

In Hong Kong, as in many tropical areas, grasslands are maintained by fire on disturbed and abandoned land. However, Hong Kong’s native forests are regenerating in many areas, alongside frequent burning of the hillsides, and are in different stages of structural succession to closed canopy forest patches. Understanding the major determinants of secondary succession is a vital input to forest management policies. Given the importance of forests for biodiversity conservation, watershed protection and carbon cycling. This study examines the relationship between burning regimes and structural forest succession over 42 years from 1973 to 2015, using an archive of satellite images, aerial photographs and field plot data. Overlay of a fire frequency map with maps of forest structural classes at different dates indicates the number of fires undergone by each successional class as well as the time taken to progress from one class to another under different fire regimes. Results indicate that the native sub-tropical evergreen forests, which are naturally fire intolerant, can regenerate alongside moderate burning, and once the shrub stage is reached, succession to closed forest is relatively rapid and can occur within 13 years. More than one burn, however, is more destructive, and twice-burnt areas were seen to have only one-third of the woody biomass of once-burnt plots. The most frequent fires occurred in areas where mono-cultural plantations had been destroyed by disease in the 1960s and were subsequently invaded by grasslands. These former plantation areas remained in early successional stages of grass and open shrubland by 2015. Other plantations from the 1970s and 1980s remain as plantations today and have acted as a barrier to natural forest succession, attesting to the greater effectiveness of fire control over re-afforestation measures. Full article

With the rapid advances in science and technology, ships that do not require any crew on board (i.e., autonomous ships) are being actively researched. Several studies on unmanned ships are in progress, and unmanned engine room studies are also being conducted. These studies mainly focus on engine failure prediction and diagnosis, but have not paid sufficient attention to various abnormal situations. Accordingly, this study focusses on the surveillance of engine rooms and abnormal situations using autonomous mobile robots. The abnormal situation considered in this study was a fire that could be highly dangerous if it occurred in the ship’s engine room. A map of the engine room was created using an autonomous robot, and when a destination was set on the map, a path was found, and the engine room was surveilled by autonomously moving by tracking the path. When a fire is detected during surveillance, the coordinates of the fire are converted so that the autonomous mobile robot can use them and move to a new destination. Experiments were conducted to evaluate the autonomous mobile robot’s movement performance, fire detection performance, and performance in the engine room. In terms of movement performance evaluation, the arrival rate to the destination was 88% on average, and the fire detection performance was a 0.9833 detection rate, 0 false alarm rate, and 0.9916 accuracy. The performance evaluation in the engine room confirmed that the fire was detected while driving, and the destination was changed to a new destination by coordinate conversion and driving was performed autonomously. Through this, it was confirmed that it is possible to surveil the engine room using an autonomous mobile robot, which contributes towards the development of unmanned engine room and ship safety. Full article

Analysis of the progression of forest fires is critical in understanding fire regimes and managing the risk of active fires. Major fire events in Korea mostly occur in the eastern mountainous areas (Gangwon Province), where the wind and moisture conditions are prone to fire in the late winter season. Despite the significance of the fire events in the area both in terms of frequency and severity, their spatial progression characteristics and their dependency on forest types have not been sufficiently analyzed so far, particularly with satellite data. This study first derived the severity map for the Uljin fire which occurred in March 2022, using a series of satellite images acquired over the fire period with very high frequency (every 5 days), and analyzed the characteristics of spatio-temporal progression in terms of forest types. The analysis revealed that the core fire area expanded very rapidly in the first few days, followed by an intensification phase that elevated severity in the active areas with marginal expansion in the peripheral areas. The analysis of the progression showed that the fire did not expand selectively by the forest type, despite the clear difference in their severity levels in the burned areas, where coniferous forest exhibited 3 times higher severity than deciduous forest. Full article

The objectives of this study were to evaluate spatial sampling and statistical aspects of landscape-level wildfire rate of spread (ROS) estimates derived from airborne thermal infrared imagery (ATIR). Wildfire progression maps and ROS estimates were derived from repetitive ATIR image sequences collected during the 2017 Thomas and Detwiler wildfire events in California. Three separate landscape sampling unit (LSU) sizes were used to extract remotely sensed environmental covariates known to influence fire behavior. Statistical relationships between fire spread rates and landscape covariates were analyzed using (1) bivariate regression, (2) multiple stepwise regression, (3) geographically weighted regression (GWR), (4) eigenvector spatial filtering (ESF) regression, (5) regression trees (RT), and (6) and random forest (RF) regression. GWR and ESF regressions reveal that relationships between covariates and ROS estimates are substantially non-stationary and suggest that the global association of fire spread controls are locally differentiated on landscape scales. Directional slope is by far the most strongly associated covariate of ROS for the imaging sequences analyzed and the size of LSUs has little influence on any of the covariate relationships. Full article

Human use and management of fire in landscapes have a long history and vary globally in purpose and impact. Existing local research on how people use and manage fire is fragmented across multiple disciplines and is diverse in methods of data collection and analysis. If progress is to be made on systematic understanding of human fire use and management globally, so that it might be better represented in dynamic global vegetation models, for example, we need improved synthesis of existing local research and literature. The database of anthropogenic fire impacts (DAFI) presented here is a response to this challenge. We use a conceptual framework that accounts for categorical differences in the land system and socio-economic context of human fire to structure a meta-study for developing the database. From the data collated, we find that our defined anthropogenic fire regimes have distinct quantitative signatures and identify seven main modes of fire use that account for 93% of fire instance records. We describe the underlying rationales of these seven modes of fire use, map their spatial distribution and summarise their quantitative characteristics, providing a new understanding that could become the basis of improved representation of anthropogenic fire in global process-based models. Our analysis highlights the generally small size of human fires (60% of DAFI records for mean size of deliberately started fires are <21 ha) and the need for continuing improvements in methods for observing small fires via remote sensing. Future efforts to model anthropogenic fire should avoid assuming that drivers are uniform globally and will be assisted by aligning remotely sensed data with field-based data and process understanding of human fire use and management. Full article

Context and Background. Active fires have the potential to provide early estimates of fire perimeters, but there is a lack of information about the best active fire aggregation distances and how they can vary between fuel types, particularly in large areas of study under diverse climatic conditions. Objectives. The current study aimed at analyzing the effect of aggregation distances for mapping fire perimeters from active fires for contrasting fuel types and regions in Mexico. Materials and Methods. Detections of MODIS and VIIRS active fires from the period 2012–2018 were used to obtain perimeters of aggregated active fires (AGAF) at four aggregation distances (750, 1000, 1125, and 1500 m). AGAF perimeters were compared against MODIS MCD64A1 burned area for a total of 24 fuel types and regions covering all the forest area of Mexico. Results/findings. Optimum aggregation distances varied between fuel types and regions, with the longest aggregation distances observed for the most arid regions and fuel types dominated by shrubs and grasslands. Lowest aggregation distances were obtained in the regions and fuel types with the densest forest canopy and more humid climate. Purpose/Novelty. To our best knowledge, this study is the first to analyze the effect of fuel type on the optimum aggregation distance for mapping fire perimeters directly from aggregated active fires. The methodology presented here can be used operationally in Mexico and elsewhere, by accounting for fuel-specific aggregation distances, for improving rapid estimates of fire perimeters. These early fire perimeters could be potentially available in near-real time (at every satellite pass with a 12 h latency) in operational fire monitoring GIS systems to support rapid assessment of fire progression and fire suppression planning. Full article