From wildfire severity to snow persistence: a multisource GeoAI study of the 2020 Creek Fire

Wildfire can alter forest-snow interactions, yet accurate prediction of post-fire snow conditions does not by itself identify disturbance-associated change. We developed an explainable geospatial artificial intelligence framework integrating multisource Earth observations, meteorological information, and matched before-after comparisons to examine seasonal snow persistence following the 2020 Creek Fire in California's Sierra Nevada. Harmonized Landsat and Sentinel-2 observations were used to estimate the fraction of clear-sky observations containing snow during October-July for eleven water years, 2016–2026, on a 500 m grid. We matched 3,778 snow-zone cells inside the fire perimeter to comparable unburned controls using terrain and pre-fire snow conditions; all absolute standardized mean differences after matching were no greater than 0.047. Seasonal persistence agreed closely with MODIS, with a mean annual spatial correlation of 0.947. The landscape-average before-after control-impact contrast was +0.0017, with a year-level 95% confidence interval of −0.023 to +0.027. A stronger response emerged in the highest burn-severity class, where observed persistence increased by 0.026 relative to matched controls, equivalent to 2.6 percentage points. Under 5 km spatial cross-validation, XGBoost predicted raw post-fire persistence with an out-of-fold coefficient of determination of 0.811, whereas predictive skill for the fire-adjusted anomaly reached 0.046. Elevation and temperature together accounted for 65.7% of mean absolute model attribution. These findings distinguish a severity-associated optical snow response from terrain-climate relationships that dominate predictive skill and demonstrate a transferable framework for artificial-intelligence-assisted forest disturbance monitoring under global change.