About
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.
The interactive map below is a tool designed to help you explore, select, and download tiled datasets organized by the ARD (Analysis-Ready Data) tiling scheme. These tiles serve as reference grids, making it easier to locate the datasets you need for your area of interest.
Here's how to get started:
1. Explore the Map: Start by zooming in and panning around the map to find the area you’re interested in. The ARD tile grid will act as a guide, outlining the spatial boundaries of the available datasets.
2. Select Your Tiles: Click on one or more tiles to highlight them. Each tile you highlight represents the specific geographic area of the data you’ll download.
3. Review and Adjust Your Selection: Use the checkboxes in the selection list to confirm your choices. If you’ve changed your mind, simply uncheck any tile to remove it from your selection.
4. Download Your Data: Once your selection is finalized, click the ‘Download Data’ button. The datasets associated with your selected tiles will be zipped into a single file for you to download.
A Few Things to Keep in Mind
Tile Limitations: For smooth performance, we recommend selecting no more than 50 tiles at a time (approximately 1 GB of data). Larger selections may exceed your browser’s memory capacity and cause issues. If you need more tiles, divide your selection into smaller batches and download them separately.
Dataset Organization: The ARD tiling scheme organizes the datasets, making them easy to integrate into your GIS projects. Depending on the extent you need to analyze, larger datasets can be merged in your GIS software for broader regional analysis.
Ready to Dive In?
Choose your tiles and hit ‘Download Data’ to get started with your dataset download.
Selected Data Tiles:
Download
Wildfire Ignition Probability
Combined probability of wildfire ignitions from both human and natural (lightning) causes across western landscapes.
Direct Download (Full File) - HTTPS Link
Use this link to download the entire file directly to your local storage through the browser. This method is ideal for quick and easy access but requires sufficient local storage and bandwidth for the full download.
Direct Access
Get hands-on access to this dataset using interactive notebooks. Choose between the Google Colab notebook for quick exploration in your browser or access the hosted Jupyter Notebooks via Binder or GitHub for more advanced workflows.
Direct access to the Google Collab notebook
Open and explore instantly
Click the button to the left to launch an interactive notebook directly in your browser. This pre-configured Colab notebook provides a quick and easy way to explore, visualize, and analyze the data—no setup required.
GitHub hosted Jupyter Notebooks
Flexible access for advanced workflows
Access the full collection of Jupyter Notebooks hosted on GitHub. These notebooks can be used on your local machine or via cloud platforms like Binder or Google Colaboratory, providing flexibility for more advanced customizations.