From Wildfire Severity to Snow Persistence: A Multisource GeoAI Study of the 2020 Creek Fire
Abstract
Accurate prediction of post-fire snow conditions does not necessarily establish how wildfire changed those conditions. We developed an explainable geospatial artificial intelligence framework combining 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 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 analysis grid. We matched 3,778 snow-zone cells inside the fire perimeter to comparable unburned controls using terrain and pre-fire snow conditions; absolute standardized mean differences after matching were no greater than 0.047. HLS 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 the terrain-climate relationships that dominate predictive skill. Combining matched comparisons with explainable GeoAI provides a practical framework for forest monitoring that separates accurate environmental mapping from inference about disturbance effects.
Related
- Explainable GeoAI for urban wildfire structure loss: vegetation and built environment in the 2025 Palisades Fire
- Multisource Remote Sensing and Geospatial Analysis of Vineyard Wildfire Impacts and Exposure: The 2019 Kincade Fire
- Hydrogeology and Water Quality of the Unconsolidated Aquifer System in the Lower Fall Creek Valley, Tompkins County, New York
- Geographic and thematic gaps in wildfire resilience research
- Wildfire risk for main vegetation units in a biodiversity hotspot: modelling approach in New-Caledonia, South Pacific.
BibTeX
@misc{farajpoor2026from,
title = {{From Wildfire Severity to Snow Persistence: A Multisource GeoAI Study of the 2020 Creek Fire}},
author = {Parastoo Farajpoor and Mohammadreza Narimani},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36345},
eprint = {2609.36345},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36345},
}
RIS
TY - UNPB
TI - From Wildfire Severity to Snow Persistence: A Multisource GeoAI Study of the 2020 Creek Fire
AU - Parastoo Farajpoor
AU - Mohammadreza Narimani
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.36345
UR - https://arxiv.org/abs/2609.36345
AB - Accurate prediction of post-fire snow conditions does not necessarily establish how wildfire changed those conditions. We developed an explainable geospatial artificial intelligence framework combining 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 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 analysis grid. We matched 3,778 snow-zone cells inside the fire perimeter to comparable unburned controls using terrain and pre-fire snow conditions; absolute standardized mean differences after matching were no greater than 0.047. HLS 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 the terrain-climate relationships that dominate predictive skill. Combining matched comparisons with explainable GeoAI provides a practical framework for forest monitoring that separates accurate environmental mapping from inference about disturbance effects.
ER -