Wildfire Ignition Probability - Human - Southeastern Region

Probability of human-caused wildfire ignitions across the southeastern United States.

Data and Resources

Additional Info

Field Value
Last Updated July 14, 2025, 16:11 (UTC)
Created July 14, 2025, 14:17 (UTC)
accessRights To read more about the access rights pertaining to this dataset, (a) click on the download button to the left of "709.3 MB" and (b) fill out a form titled "Please complete the form below to access our dataset"; execute these steps at the following link: https://www.vpdatacommons.org/datasets/human-ignition-probability-southeast
creationMethod Learn more about dataset's creation method at: https://www.vpdatacommons.org/datasets/human-ignition-probability-southeast
creatorEmail chris.moran@vibrantplanet.net
creatorName Chris Moran, PhD
creatorWebsite https://www.vibrantplanet.net/team/dr-chris-moran
dataAuthType public
dataBbox Example bounding box:'geo_bounds = (-124.0, 38.0, -120.0, 42.0)'
dataProvenance [{"date":"2024-01-30","name":"Creation and publication of dataset"},{"date":"2024-05-10","name":"Dataset updated"},{"date":"2024-12-16","name":"Dataset updated"},{"date":"2025-03-06","name":"Dataset updated"}]
dataType GeoTIFF
datasetPageUrl https://www.vpdatacommons.org/datasets/human-ignition-probability-southeast
docsURL https://github.com/Vibrant-Planet-Data-Commons/VPDC_Notebooks
doi https://doi.org/10.17605/OSF.IO/CFGH9
issueDate 2024-01-30
lang en
lastUpdateDate 2025-03-06
pocEmail chris.moran@vibrantplanet.net
pocName Chris Moran, PhD
pocWebsite https://www.vibrantplanet.net/team/dr-chris-moran
publisherEmail contact@pyrologix.com
publisherName Pyrologix
publisherWebsite https://pyrologix.com/
purpose Wildfire ignition probability data provides spatially explicit estimates of the likelihood that a wildfire will start in a given location. The resulting datasets, specific to the Western and Southeastern U.S. regions, offer geospatial estimates of wildfire ignition probabilities, distinguishing between human-caused and natural (lightning) ignitions, as well as providing combined probabilities for both. The authors employ Random Forest machine learning, customized for probabilistic predictions, to model ignition likelihood based on spatial trends in observed fire occurrences, topographic features, climatic factors, vegetation characteristics, and human development patterns. The resulting datasets are scaled to recent observed ignition rates (e.g. 2006-2020 fire occurrence database) and have a spatial resolution of 120 meters. These datasets are a valuable resource for wildfire risk assessments (QWRA), risk mitigation planning, and decision support in land management, policy development, and other fire-related contexts.
spatialProjection EPSG:5070
spatialRes 120 meter
status submitted
theme ["wildfire"]
uploadType dataset