An official website of the United States government
Drone based wildfire detection and modeling methods enable high-precision, real-time fire monitoring that is not provided by traditional remote fire monitoring systems, such as satellite imaging. Precise, real-time information enables rapid, effective wildfire intervention and management strategies. Drone systems’ ease of deployment, omnidirectional maneuverability, and robust sensing capabilities make them effective tools for early wildfire detection and evaluation, particularly so in environments that are inconvenient for humans and/or terrestrial vehicles. Development of emerging drone-based fire monitoring systems has been inhibited by a lack of well-annotated, high quality aerial wildfire datasets, largely as a result of UAV flight regulations for prescribed burns and wildfires. The included dataset provides a collection of side-by-side infrared and visible spectrum video pairs taken by drones during an open canopy prescribed fire in Northern Arizona in 2021. The frames have been classified by two independent classifiers with two binary classifications. The Fire label is applied when the classifiers visually observe indications of fire in either RGB or IR frame for each frame pair. The Smoke label is applied when the classifiers visually estimate that at least 50% of the RGB frame is filled with smoke. To provide additional context to the main dataset’s aerial imagery, the provided supplementary dataset includes weather information, the prescribed burn plan, a geo-referenced RGB point cloud of the preburn area, an RGB orthomosaic of the preburn area, and links to further information.
more »
« less
This content will become publicly available on December 1, 2026
Toward AI-driven fire imagery: Attributes, challenges, comparisons, and the promise of VLMs and LLMs
Despite recent advancements in technology-driven fire management systems, environment continues to grapple with the increasing frequency and severity of wildfires, an issue exacerbated by climate change. A recent example is the devastating California wildfire in January 2025, which burned approximately 182,197 acres, destroyed 16,306 structures, and resulted in a total economic loss of over 275 billion dollars. Such events underscore the urgent need for further investment in intelligent, data-driven fire management solutions. One transformative development in this field has been the deployment of Unmanned Aerial Systems (UAS) for wildfire monitoring and control. These systems capture multimodal imagery and sensor data, facilitating the development of advanced Artificial Intelligence (AI) models for fire detection, spread modeling and prediction, effective suppression, and post-incident damage assessment. Unfortunately, most existing wildfire datasets exhibit significant heterogeneity in terms of imaging modalities (e.g., RGB, thermal, IR), annotation quality, target applications, and geospatial attributes. This diversity often complicates the identification of appropriate datasets for new and emerging wildfire scenarios, which remains a core challenge that hampers progress in the field and limits generalizability and reusability. This paper presents a comprehensive review of prominent wildfire datasets, offering a systematic comparison across various dimensions to help researchers, especially newcomers, select the most suitable datasets for their needs. Additionally, it identifies key parameters to consider when designing and collecting new fire imagery datasets to enhance future usability. Another key contribution of this work is its exploration of how emerging Large Language Models/Vision Language Models (LLMs/VLMs) can catalyze the creation, augmentation, and application of wildfire datasets. We discuss the potential of these models to integrate global knowledge for more accurate fire detection, devise evacuation plans, and support data-driven fire control strategies.
more »
« less
- Award ID(s):
- 2120485
- PAR ID:
- 10653696
- Publisher / Repository:
- Machine Learning with Applications
- Date Published:
- Journal Name:
- Machine Learning with Applications
- Volume:
- 22
- Issue:
- C
- ISSN:
- 2666-8270
- Page Range / eLocation ID:
- 100763
- Subject(s) / Keyword(s):
- AI-based environmental management Large Language Models (LLM) Vision Language Models (VLM) Wildland Fire Datasets Image and Video Processing
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The size and frequency of wildland fires in the western United States have dramatically increased in recent years. On high-fire-risk days, a small fire ignition can rapidly grow and become out of control. Early detection of fire ignitions from initial smoke can assist the response to such fires before they become difficult to manage. Past deep learning approaches for wildfire smoke detection have suffered from small or unreliable datasets that make it difficult to extrapolate performance to real-world scenarios. In this work, we present the Fire Ignition Library (FIgLib), a publicly available dataset of nearly 25,000 labeled wildfire smoke images as seen from fixed-view cameras deployed in Southern California. We also introduce SmokeyNet, a novel deep learning architecture using spatiotemporal information from camera imagery for real-time wildfire smoke detection. When trained on the FIgLib dataset, SmokeyNet outperforms comparable baselines and rivals human performance. We hope that the availability of the FIgLib dataset and the SmokeyNet architecture will inspire further research into deep learning methods for wildfire smoke detection, leading to automated notification systems that reduce the time to wildfire response.more » « less
-
FLAME 3 is the third dataset in the FLAME series of aerial UAV-collected side-by-side multi-spectral wildlands fire imagery (see FLAME 1 and FLAME 2). This set contains a single-burn subset of the larger FLAME 3 dataset focusing specifically on Computer Vision tasks such as fire detection and segmentation. Included are 622 image quartets labeled Fire and 116 image quartets labeled No Fire. The No Fire images are of the surrounding forestry of the prescribed burn plot. Each image quartet is composed of four images - a raw RGB image, a raw thermal image, a corrected FOV RGB image, and a thermal TIFF. Each of the four data types are detailed in the below Table 1. More information on data collection methods, data processing procedures, and data labeling can be found in https://arxiv.org/abs/2412.02831. This dataset also contains a NADIR Thermal Fire set, providing georeferenced overhead thermal imagery, captured by UAV every 3-5 seconds, focusing on monitoring fire progression and burn behaviors over time. This data, when processed, enables centimeter-grade measurements of fire spread and energy release over time. Pre, post, and during burn imagery are included, along with ground control point (GCP) data. This dataset is based on the research conducted in the paper: FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management. It provides detailed insights and analysis related to forest fire monitoring and modeling.If you use this dataset in your research or projects, please cite the original paper as follows: APA: Hopkins, B., ONeill, L., Marinaccio, M., Rowell, E., Parsons, R., Flanary, S., Nazim I, Seielstad C, Afghah, F. (2024). FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management. arXiv preprint arXiv:2412.02831.BibTeX: @misc{hopkins2024flame3datasetunleashing, title={FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management}, author={Bryce Hopkins and Leo ONeill and Michael Marinaccio and Eric Rowell and Russell Parsons and Sarah Flanary and Irtija Nazim and Carl Seielstad and Fatemeh Afghah}, year={2024}, eprint={2412.02831}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2412.02831}, }more » « less
-
Purpose of Review I aim to contextualize wildfire-disease interactions with the goal of building a better understanding of where these may be of ecological importance and problems for sustainable forest management. Recent Findings While wildfire-disease interactions have been documented, they are not well represented in the ecological literature, probably because they require considerable effort or serendipity to rigorously quantify. Examples of disease-fire interactions are relatively limited and tend to be clearer in systems where fire and disease are management problems. The most resolved systems include Phytophthora pathogens although wildfire-disease interactions are not limited to these pathogens. Documented interactions encompass a range of effects which include the magnification of problems associated with each disturbance. Wildfire-disease interactions are also likely to shape basic ecological function in systems where both wildfire and disease are common but not necessarily critical management problems. Climate change has altered the fundamental controls on both fire and disease suggesting it will also alter the magnitude and likelihood (occurrence or detection) of disease-fire interactions. Summary I present a framework for linking wildfire-disease interactions and highlight the importance of host community/fuels structure on linking and mediating these interactions. I provide a series of examples where understanding interactive effects, interfacing with climate change, and the magnitude of changes to wildfire and disease intensification are of practical value and/or advance basic ecological knowledge. While much remains to be understood about these interactions, I make the argument that, in some cases, management can address both problems simultaneously.more » « less
-
Current forest monitoring technologies including satellite remote sensing, manned/piloted aircraft, and observation towers leave uncertainties about a wildfire’s extent, behavior, and conditions in the fire’s near environment, particularly during its early growth. Rapid mapping and real-time fire monitoring can inform in-time intervention or management solutions to maximize beneficial fire outcomes. Drone systems’ unique features of 3D mobility, low flight altitude, and fast and easy deployment make them a valuable tool for early detection and assessment of wildland fires, especially in remote forests that are not easily accessible by ground vehicles. In addition, the lack of abundant, well-annotated aerial datasets – in part due to unmanned aerial vehicles’ (UAVs’) flight restrictions during prescribed burns and wildfires – has limited research advances in reliable data-driven fire detection and modeling techniques. While existing wildland fire datasets often include either color or thermal fire images, here we present (1) a multi-modal UAV-collected dataset of dual-feed side-by-side videos including both RGB and thermal images of a prescribed fire in an open canopy pine forest in Northern Arizona and (2) a deep learning-based methodology for detecting fire and smoke pixels at accuracy much higher than the usual single-channel video feeds. The collected images are labeled to “fire” or “no-fire” frames by two human experts using side-by-side RGB and thermal images to determine the label. To provide context to the main dataset’s aerial imagery, the included supplementary dataset provides a georeferenced pre-burn point cloud, an RGB orthomosaic, weather information, a burn plan, and other burn information. By using and expanding on this guide dataset, research can develop new data-driven fire detection, fire segmentation, and fire modeling techniques.more » « less
