Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height

Shaddy, Bryan; Binder, Brianna; Dasgupta, Agnimitra; Qin, Haitong; Haley, James; Farguell, Angel; Hilburn, Kyle; Mallia, Derek V.; Kochanski, Adam; Mandel, Jan; Oberai, Assad A.

doi:10.3390/rs18020227

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height

by

Bryan Shaddy

^1,*

,

Brianna Binder

¹,

Agnimitra Dasgupta

¹

,

Haitong Qin

²,

James Haley

³

,

Angel Farguell

⁴

,

Kyle Hilburn

³

,

Derek V. Mallia

⁵,

Adam Kochanski

⁴

,

Jan Mandel

⁶

and

Assad A. Oberai

¹

Department of Aerospace and Mechanical Engineering, University of Southern California, Los Angeles, CA 90089, USA

²

Department of Mathematics, University of Southern California, Los Angeles, CA 90089, USA

³

Cooperative Institute for Research in the Atmosphere, Colorado State University, Fort Collins, CO 80521, USA

⁴

Wildfire Interdisciplinary Research Center, San Jose State University, San Jose, CA 95192, USA

⁵

Department of Atmospheric Sciences, University of Utah, Salt Lake City, UT 84112, USA

⁶

Department of Mathematical and Statistical Sciences, University of Colorado Denver, Denver, CO 80204, USA

^*

Author to whom correspondence should be addressed.

Remote Sens. 2026, 18(2), 227; https://doi.org/10.3390/rs18020227

Submission received: 23 October 2025 / Revised: 24 December 2025 / Accepted: 8 January 2026 / Published: 10 January 2026

(This article belongs to the Special Issue Integrating Artificial Intelligence and Remote Sensing for Wildfire Detection, Monitoring and Management)

Download Review Reports Versions Notes

Abstract

Wildfire spread prediction models, including even the most sophisticated coupled atmosphere–wildfire models, diverge from observed wildfire progression during multi-day simulations, motivating the need for measurement-based assessments of wildfire state and improved data assimilation techniques. Data assimilation in the context of coupled atmosphere–wildfire models entails estimating wildfire progression history from observations and using this to obtain initial conditions for subsequent simulations through a spin-up process. In this study, an approach is developed for estimating fire progression history from VIIRS active fire measurements, GOES-derived ignition times, and terrain height data. The approach utilizes a conditional Wasserstein Generative Adversarial Network trained on simulations of historic wildfires from the coupled atmosphere–wildfire model WRF-SFIRE, with corresponding measurements for training obtained through the application of an approximate observation operator. Once trained, the cWGAN leverages measurements of real fires and corresponding terrain data to probabilistically generate fire progression estimates that are consistent with the WRF-SFIRE solutions used for training. The approach is validated on five Pacific US wildfires, and results are compared against high-resolution perimeters measured via aircraft, finding an average Sørensen–Dice coefficient of 0.81. The influence of terrain data on fire progression estimates is also assessed, finding an increased contribution when measurements are uninformative.

Keywords: conditional generative models; deep learning; fire monitoring; active fires satellite data; data assimilation; model initialization; Bayesian methods

Share and Cite

MDPI and ACS Style

Shaddy, B.; Binder, B.; Dasgupta, A.; Qin, H.; Haley, J.; Farguell, A.; Hilburn, K.; Mallia, D.V.; Kochanski, A.; Mandel, J.; et al. Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height. Remote Sens. 2026, 18, 227. https://doi.org/10.3390/rs18020227

AMA Style

Shaddy B, Binder B, Dasgupta A, Qin H, Haley J, Farguell A, Hilburn K, Mallia DV, Kochanski A, Mandel J, et al. Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height. Remote Sensing. 2026; 18(2):227. https://doi.org/10.3390/rs18020227

Chicago/Turabian Style

Shaddy, Bryan, Brianna Binder, Agnimitra Dasgupta, Haitong Qin, James Haley, Angel Farguell, Kyle Hilburn, Derek V. Mallia, Adam Kochanski, Jan Mandel, and et al. 2026. "Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height" Remote Sensing 18, no. 2: 227. https://doi.org/10.3390/rs18020227

APA Style

Shaddy, B., Binder, B., Dasgupta, A., Qin, H., Haley, J., Farguell, A., Hilburn, K., Mallia, D. V., Kochanski, A., Mandel, J., & Oberai, A. A. (2026). Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height. Remote Sensing, 18(2), 227. https://doi.org/10.3390/rs18020227

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI