Enhancing wildfire spread modelling by building a gridded fuel moisture content product with machine learning

Abstract

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, dead FMC measurements are provided by a relatively sparse network of remote automatic weather stations (RAWS), while live FMC is relatively infrequently measured manually. We developed a high resolution, gridded, real-time FMC data sets that did not previously exist for assimilation into operational wildland fire prediction systems based on ML. 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 Terra and Aqua reflectances are used to predict the live and dead FMC measured by the Wildland Fire Assessment System and RAWS). We evaluate multiple machine learning methods including multiple linear regression, random forests (RFs), gradient boosted regression and artificial neural networks. The models are trained to learn the relationships between the satellite reflectances, surface weather and soil moisture observations and FMC. After training on data corresponding to the temporally and spatially nearest grid points to the irregularly spaced surface FMC observations, the machine learning models could be applied to all grid cells for a gridded product over the Conterminous United States (CONUS). The results show generally that the rule-based approaches have the lowest errors likely due to the sharp decision boundaries among the predictors, and the RF approach that utilizes bagging to avoid over-fitting has the lowest error on the test dataset. The errors are typically between 25%−33% the typical variability of the FMC data, which indicate the skill of the RF in estimating the FMC based on satellite data and surface characteristics. The FMC gridded product based on the RF runs operationally daily over CONUS and can be assimilated into WRF-Fire for more accurate wildland fire spread predictions.

Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal Data

“…Combinations of SI have been successfully employed to estimate LFMC [6,15,21,26]. In addition, some authors found stronger predictive power by including land surface temperature (LST) along with optical data to the empirical relationships [22,[27][28][29]. The connection between LFMC and LST lies on the interaction between the plant energy balance mechanisms and its response to water stress [24].…”

Modelling chamise fuel moisture content across California: a machine learning approach

“…Many efforts to model LFMC have been made in recent years, most of which include the use of remote sensing technologies to measure leaf water content (Chuvieco 2003;Danson and Bowyer 2004;Peterson et al 2008;Qi et al 2012;Yebra et al 2013;Garcı ´a et al 2020;McCandless et al 2020;Rao et al 2020;Michael et al 2021). Specifically, the use of Moderate Resolution Imaging Spectroradiometer (MODIS) and Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) has been reported by Serrano et al (2000), Yebra et al (2008) and Myoung et al (2018).…”

“…To model daily LFMC as a function of weather predictors, we adopted a random forest (RF) regression method. RF was found to minimise the LFMC error compared with several other machine learning methods, according to a recent study by McCandless et al (2020). Separate chamise new-and oldgrowth RF models were trained using predictors from the gridded high-resolution weather data.…”

“…Ruffault et al (2018) model has an R 2 and RMSE of 0.3 and 20%; and theMcCandless et al (2020) model has an overall RMSE of ,22% (all figures respective). The R 2 in various LFMC models proposed inViegas et al (2001) range from 0.12 to 0.79.…”

Three Lines of Defense for Wildfire Risk Management in Electric Power Grids: A Review

“…Rather than anchor into historical fire regimes, many operational models focus on existing conditions, recent fire history, and environmental factors to calibrate predictions [36]. Relevant environmental factors that can be considered in wildfire risk modeling can include the relative dryness of fuels-which varies throughout the season as well as from season to season [37]. In addition, as the ambient temperature varies by seasonal changes, the convective and radiative heat loss rates, which help to cool down the components, reduce significantly.…”