What question did this study set out to answer?

The aim is to enhance early warning systems for forest fires in Liangshan Prefecture by creating a predictive model.

March 1, 2026Open Access

Forest Fire Forecasting and Early Warning Model Based on Satellite FY-4 and Other Multi-Source Data

Key Points

The aim is to enhance early warning systems for forest fires in Liangshan Prefecture by creating a predictive model.
Constructed a fire risk prediction model using FY-4A satellite data and historical fire records.
Utilized terrain data and conducted principal component analysis for factor selection.
Implemented a logistic regression model to identify key risk drivers.
Achieved an AUC of 0.77 in model validation.
Attained a prediction accuracy of 71.5%.
Identified vegetation moisture content as the most influential risk factor.

Abstract

Forest fires pose a severe threat to ecosystems and human safety in the mountainous Liangshan Prefecture, China. To enhance early warning capabilities, this study constructs a fire risk prediction model by combining FY-4A satellite data, historical fire records, and terrain data. Through principal component analysis and multicollinearity diagnostics, critical factors including topography, vegetation indices (NDVI, NDII7), and a moisture index (TVDI) were selected for a logistic regression model. The model successfully identifies key risk drivers, with vegetation moisture content (NDII7) being the most influential. Validation shows the model achieves an AUC of 0.77 and a prediction accuracy of 71.5%, confirming its effectiveness. This work demonstrates the utility of China’s FY-4 satellite for operational forest fire risk forecasting, providing a methodological basis for improved disaster prevention.

Forest Fire Forecasting and Early Warning Model Based on Satellite FY-4 and Other Multi-Source Data

Key Points

Abstract

Cite This Study