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
Wildland Fire Detection and Monitoring Using a Drone-Collected RGB/IR Image Dataset
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
- Award ID(s):
- 2120485
- NSF-PAR ID:
- 10467303
- Publisher / Repository:
- IEEE Access
- Date Published:
- Volume:
- 10
- Page Range / eLocation ID:
- 121301-121317
- Subject(s) / Keyword(s):
- ["autonomous aerial vehicles","deep learning (artificial intelligence)","forestry","geophysical image processing","image colour analysis","image fusion","infrared imaging","object detection","remote sensing","robot vision","video signal processing","wildfires"]
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Wildfires are one of the deadliest and dangerous natural disasters in the world. Wildfires burn millions of forests and they put many lives of humans and animals in danger. Predicting fire behavior can help firefighters to have better fire management and scheduling for future incidents and also it reduces the life risks for the firefighters. Recent advance in aerial images shows that they can be beneficial in wildfire studies. Among different methods and technologies for aerial images, Unmanned Aerial Vehicles (UAVs) and drones are beneficial to collect information regarding the fire. This study provides an aerial imagery dataset using drones during a prescribed pile fire in Northern Arizona, USA. This dataset consists of different repositories including raw aerial videos recorded by drones' cameras and also raw heatmap footage recorded by an infrared thermal camera. To help researchers, two well-known studies; fire classification and fire segmentation are defined based on the dataset. For approaches such as Neural Networks (NNs) and fire classification, 39,375 frames are labeled ("Fire" vs "Non-Fire") for the training phase. Also, another 8,617 frames are labeled for the test data. 2,003 frames are considered for the fire segmentation and regarding that, 2,003 masks are generated for the purpose of Ground Truth data with pixel-wise annotation.more » « less
-
Disturbance events can happen at a temporal scale much faster than wildland fire fuel data updates. When used as input for wildland fire behavior models, outdated fuel datasets can contribute to misleading forecasts, which have implications for operational firefighting, mitigation, and wildland fire research. Remote sensing and machine learning methods can provide a solution for on-demand fuel estimation. Here, we show a proof of concept using C-band synthetic aperture radar and multispectral imagery, land cover classes, and tree mortality surveys to train a random forest classifier to estimate wildland fire fuel data in the East Troublesome Fire (Colorado) domain. The algorithm classified over 80% of the test dataset correctly, and the resulting wildland fire fuel data was used to simulate the East Troublesome Fire using the coupled atmosphere—wildland fire behavior model, WRF-Fire. The simulation using the modified fuel inputs, where 43% of original fuels are replaced with fuels representing dead trees, improved the burn area forecast by 38%. This study demonstrates the need for up-to-date fuel maps available in real time to provide accurate prediction of wildland fire spread, and outlines the methodology based on high-resolution satellite observations and machine learning that can accomplish this task.more » « less
-
more » « less
Despite recent advances in both coupled fire modeling and measurement techniques to sample the fire environment, the fire–atmosphere coupling mechanisms that lead to fast propagating wildfires remain poorly understood. This knowledge gap adversely affects fire management when wildland fires propagate unexpectedly rapidly and shift direction due to the fire impacts on local wind conditions. In this work, we utilized observational data from the FireFlux2 prescribed burn and numerical simulations performed with a coupled fire–atmosphere model WRF-SFIRE to assess the small-scale impacts of fire on local micrometeorology under moderate wind conditions (10–12 m/s). The FireFlux2 prescribed burn provided a comprehensive observational dataset with in situ meteorological observations as well as IR measurements of fire progression. To directly quantify the effects of fire–atmosphere interactions, two WRF-SFIRE simulations were executed. One simulation was run in a two-way coupled mode in which the heat and moisture fluxes emitted from the fire were injected into the atmosphere, and the other simulation was performed in a one-way coupled mode for which the atmosphere was not affected by the fire. The difference between these two simulations was used to analyze and quantify the fire impacts on the atmospheric circulation at different sections of the fire front. The fire-released heat fluxes resulted in vertical velocities as high as 10.8 m/s at the highest measurement level (20 m above ground level) gradually diminishing with height and dropping to 7.9 m/s at 5.77 m. The fire-induced horizontal winds indicated the strongest fire-induced flow at the lowest measurement levels (as high as 3.3 m/s) gradually decreasing to less than 1 m/s at 20 m above ground level. The analysis of the simulated flow indicates significant differences between the fire-induced circulation at the fire head and on the flanks. The fire-induced circulation was much stronger near the fire head than at the flanks, where the fire did not produce particularly strong cross-fire flow and did not significantly change the lateral fire progression. However, at the head of the fire the fire-induced winds blowing across the front were the strongest and significantly accelerated fire progression. The two-way coupled simulation including the fire-induced winds produced 36.2% faster fire propagation than the one-way coupled run, and more realistically represented the fire progression.
-
This data set contains the raw files from flight RU_ALN_TR1_FL007R. The remote sensing imagery is collected using uncrewed aerial vehicles at a series of fire perimeters in larch forests located in northeastern Siberia in 2018 and 2019. Images were collected using visible sensors (blue, green, and red wavelengths) and multispectral sensors (green, red, red-edge, and near-infrared wavelengths). The data were collected perpendicular to fire perimeter boundaries in order to characterize variation vegetation composition and structure between burned and burned forests, and as a function of distance from the unburned forest edge. The resulting images are co-located with field observations of ecosystem properties collected as part of this project that are posted in a related data set (Alexander et al, 2018). Heather Alexander, Jennie DeMarco, Rebecca Hewitt, Jeremy Lichstein, Michael Loranty, et al. 2018. Fire influences on forest recovery and associated climate feedbacks in Siberian Larch Forests, Russia, June-July 2018. Arctic Data Center. urn:uuid:a5de1514-78d3-449f-aad1-2ff8f8d0fb27.more » « less
