High-Resolution LFMC Maps for Wildfire Risk From Multimodal Earth Observation Data

Patrick Alan Johnson, Gabriel Tseng, Yawen Zhang, Heather Heward, Virginia Sjahli, Favyen Bastani, Joseph Redmon, Patrick Beukema
Proceedings of The TerraBytes {ICML} Workshop: Towards global datasets and models for Earth Observation, PMLR 292:111-123, 2025.

Abstract

Wildfires are increasing in intensity and severity at an alarming rate. Recent advances in AI and publicly available satellite data enable monitoring critical wildfire risk factors globally, at high resolution and low latency. Live Fuel Moisture Content (LFMC) is a critical wildfire risk factor and is valuable for both wildfire research and operational response. However, ground-based LFMC samples are both labor intensive and costly to acquire resulting in sparse and infrequent updates. In this work, we explore the use of a pretrained, highly-multimodal earth-observation model for generating large-scale spatially complete (wall-to-wall) LFMC maps. Our approach achieves significant improvements over previous methods using randomly initialized models ($>20%$ reduction in RMSE). We provide an automated pipeline that enables rapid generation of these LFMC maps across the United States, and demonstrate its effectiveness in two regions recently impacted by wildfire (Eaton and Palisades).

Cite this Paper

BibTeX
@InProceedings{pmlr-v292-johnson25a, title = {High-Resolution {LFMC} Maps for Wildfire Risk From Multimodal Earth Observation Data}, author = {Johnson, Patrick Alan and Tseng, Gabriel and Zhang, Yawen and Heward, Heather and Sjahli, Virginia and Bastani, Favyen and Redmon, Joseph and Beukema, Patrick}, booktitle = {Proceedings of The TerraBytes {ICML} Workshop: Towards global datasets and models for Earth Observation}, pages = {111--123}, year = {2025}, editor = {Audebert, Nicolas and Azizpour, Hossein and Barrière, Valentin and Castillo Navarro, Javiera and Czerkawski, Mikolaj and Fang, Heng and Francis, Alistair and Marsocci, Valerio and Nascetti, Andrea and Yadav, Ritu}, volume = {292}, series = {Proceedings of Machine Learning Research}, month = {19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v292/main/assets/johnson25a/johnson25a.pdf}, url = {https://proceedings.mlr.press/v292/johnson25a.html}, abstract = {Wildfires are increasing in intensity and severity at an alarming rate. Recent advances in AI and publicly available satellite data enable monitoring critical wildfire risk factors globally, at high resolution and low latency. Live Fuel Moisture Content (LFMC) is a critical wildfire risk factor and is valuable for both wildfire research and operational response. However, ground-based LFMC samples are both labor intensive and costly to acquire resulting in sparse and infrequent updates. In this work, we explore the use of a pretrained, highly-multimodal earth-observation model for generating large-scale spatially complete (wall-to-wall) LFMC maps. Our approach achieves significant improvements over previous methods using randomly initialized models ($>20%$ reduction in RMSE). We provide an automated pipeline that enables rapid generation of these LFMC maps across the United States, and demonstrate its effectiveness in two regions recently impacted by wildfire (Eaton and Palisades).} }
Endnote
%0 Conference Paper %T High-Resolution LFMC Maps for Wildfire Risk From Multimodal Earth Observation Data %A Patrick Alan Johnson %A Gabriel Tseng %A Yawen Zhang %A Heather Heward %A Virginia Sjahli %A Favyen Bastani %A Joseph Redmon %A Patrick Beukema %B Proceedings of The TerraBytes {ICML} Workshop: Towards global datasets and models for Earth Observation %C Proceedings of Machine Learning Research %D 2025 %E Nicolas Audebert %E Hossein Azizpour %E Valentin Barrière %E Javiera Castillo Navarro %E Mikolaj Czerkawski %E Heng Fang %E Alistair Francis %E Valerio Marsocci %E Andrea Nascetti %E Ritu Yadav %F pmlr-v292-johnson25a %I PMLR %P 111--123 %U https://proceedings.mlr.press/v292/johnson25a.html %V 292 %X Wildfires are increasing in intensity and severity at an alarming rate. Recent advances in AI and publicly available satellite data enable monitoring critical wildfire risk factors globally, at high resolution and low latency. Live Fuel Moisture Content (LFMC) is a critical wildfire risk factor and is valuable for both wildfire research and operational response. However, ground-based LFMC samples are both labor intensive and costly to acquire resulting in sparse and infrequent updates. In this work, we explore the use of a pretrained, highly-multimodal earth-observation model for generating large-scale spatially complete (wall-to-wall) LFMC maps. Our approach achieves significant improvements over previous methods using randomly initialized models ($>20%$ reduction in RMSE). We provide an automated pipeline that enables rapid generation of these LFMC maps across the United States, and demonstrate its effectiveness in two regions recently impacted by wildfire (Eaton and Palisades).
APA
Johnson, P.A., Tseng, G., Zhang, Y., Heward, H., Sjahli, V., Bastani, F., Redmon, J. & Beukema, P.. (2025). High-Resolution LFMC Maps for Wildfire Risk From Multimodal Earth Observation Data. Proceedings of The TerraBytes {ICML} Workshop: Towards global datasets and models for Earth Observation, in Proceedings of Machine Learning Research 292:111-123 Available from https://proceedings.mlr.press/v292/johnson25a.html.

Related Material