ClassiFiRxe: A data-driven tool to support prescribed fire planning and implementation
| Authors: | Benjamin E. Sweeney, W. Matt Jolly, Patrick Freeborn, Chloe L. Ochocki |
| Year: | 2026 |
| Type: | Scientific Journal |
| Station: | Rocky Mountain Research Station |
| DOI: | https://doi.org/10.1016/j.ecoinf.2026.103970 |
| Source: | Ecological Informatics |
Abstract
Despite a growing need to expand the pace and scale of prescribed burning to address the national fire deficit, there is a lack of data-driven methods to incorporate fire danger information into prescribed fire planning. We assembled nearly two decades of prescribed fire and wildfire records across Montana and Idaho and combined these records with spatially explicit fire danger data. We implement a nonparametric cutpoint analysis to identify objective thresholds from the Energy Release Component (ERC) percentile, treating pile burns, broadcast burns, and wildfires as ordinal classes along an ERC continuum. A novel bootstrapping approach generates distributions of optimal cutpoints, creating overlap zones that quantify uncertainty between fire classes. These thresholds form the basis of a planning guide, ClassiFiRxe, which helps managers determine whether project conditions have historically supported pile burning, broadcast burning, or wildfire and whether a proposed burn falls within a zone of confident support or greater uncertainty. Classification performance varies across regions, performing best in the forested western study area. The West of Divide guide achieves a reasonable cross-validated balanced strict recall of 65% and full recall of 77%. We demonstrate how these zones reveal seasonal patterns in burn conditions, estimate burn windows locally, and map fire danger categories across large landscapes. Such guides can be developed wherever sufficient fire weather and occurrence data exist and ordinality is satisfied, providing a scalable, interpretable, and explainable tool grounded in historical data to support prescribed fire planning and help restore fire to landscapes and reduce the fire deficit.