Gridded Fuel Moisture Content Prediction System Utilizing Machine Learning Models Based on MODIS Satellite Observations

Wildland fire decision support systems require accurate predictions of wildland fire spread. Fuel moisture content (FMC) is one of the important parameters controlling the rate of spread of wildland fire. However, FMC is a sparsely and relatively infrequently measured surface variable compared to most atmospheric variables. We developed a high resolution, gridded, real-time FMC data set that did not previously exist for assimilation into operational wildland fire prediction systems. We used surface observations of live and dead FMC to train machine learning models to estimate FMC based on satellite observations. Moderate Resolution Imaging Spectrometer (MODIS) Terra and Aqua reflectances are used to predict the live and dead FMC measured by the Wildland Fire Assessment System (WFAS) and Remote Automated Weather Stations (RAWS). The random forests machine learning method was trained to learn the non-linear relationships between the satellite reflectances, surface weather and soil moisture observations and FMC. This allowed the methods to be trained on MODIS satellite data corresponding to the temporally and spatially nearest grid points to the irregularly spaced surface FMC observations. Machine learning algorithms are applied across the entire spatial grid, populated by MODIS predictors, to achieve a gridded, real-time FMC dataset over CONUS. The results of the test dataset for Colorado show improvements in accuracy for both live and dead FMC estimation compared to persistence and linear regressions. The dead FMC predictions over CONUS were assimilated into WRF-Fire and run for historical case study fires in 2016, and the results of the wildfire spread are presented compared to using a conservative default estimate of 8% FMC.