A Geospatial Approach to Wildfire Risk Modeling Using Machine Learning and Remote Sensing Data

Abstract

In recent years, the likelihood of wildfire occurrence has increased in many North American communities as changes in climate have led to longer, more deadly fire seasons. Many Americans, especially those living in Western states, have reported frequent drought and wildfire conditions, leading to an increased need for a modeling program to assess wildfire risk at a low computational cost. The research objective of this article was to develop a machine-learning model capable of producing the accurate wildfire risk assessments using five geospatial datasets: Land fire mean return, annual precipitation, Sentinel-2 imagery, land cover, and moisture deficit and surplus. To create the model, three separate machine-learning architectures were implemented (U-Net, DeepLabV3, and the pyramid scene parsing network) and then applied to the study area of San Bernardino County, CA, for the year of 2020. This study demonstrated a proof of concept for further inquiry into combining artificial intelligence and geospatial datasets to create useful insights.

Keywords

• Deep learning
• geophysical data
• natural disasters and hazard
• optical data