Projecting Large Fires in the Western US With an Interpretable and Accurate Hybrid Machine Learning Method

Journal Article · 19 October 2024 · Earth's Future

DOI: https://doi.org/10.1029/2024ef004588 · OSTI ID:2479509

Li, Fa  ^[1]; Zhu, Qing  ^[2]; Yuan, Kunxiaojia  ^[2]; Ji, Fujiang  ^[1]; Paul, Arindam  ^[3]; Lee, Peng ^[3]; Radeloff, Volker C.  ^[1]; Chen, Min  ^[1]

---

1. Univ. of Wisconsin, Madison, WI (United States)
2. Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
3. American Family Insurance, Madison, WI (United States)

More frequent and widespread large fires are occurring in the western United States (US), yet reliable methods for predicting these fires, particularly with extended lead times and a high spatial resolution, remain challenging. In this study, we proposed an interpretable and accurate hybrid machine learning (ML) model, that explicitly represented the controls of fuel flammability, fuel availability, and human suppression effects on fires. The model demonstrated notable accuracy with a F₁-score of 0.846 ± 0.012, surpassing process-driven fire danger indices and four commonly used ML models by up to 40% and 9%, respectively. More importantly, the ML model showed remarkably higher interpretability relative to other ML models. Specifically, by demystifying the “black box” of each ML model using the explainable AI techniques, we identified substantial structural differences across ML fire models, even among those with similar accuracy. The relationships between fires and their drivers, identified by our model, were aligned closer with established fire physical principles. The ML structural discrepancy led to diverse fire predictions and our model predictions exhibited greater consistency with actual fire occurrence. With the highly interpretable and accurate model, we revealed the strong compound effects from multiple climate variables related to evaporative demand, energy release component, temperature, and wind speed, on the dynamics of large fires and megafires in the western US. Our findings highlight the importance of assessing the structural integrity of models in addition to their accuracy. They also underscore the critical need to address the rise in compound climate extremes linked to large wildfires.

• Research Organization: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF); USDOE Office of Science (SC), Biological and Environmental Research (BER). Earth & Environmental Systems Science (EESS)
• Grant/Contract Number: AC02-05CH11231
• OSTI ID: 2479509
• Journal Information: Earth's Future, Journal Name: Earth's Future Journal Issue: 10 Vol. 12; ISSN 2328-4277
• Publisher: American Geophysical Union (AGU)Copyright Statement
• Country of Publication: United States
• Language: English