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

2025-06-12

AI Summary

This study addresses the challenge of reconstructing wildfire spread dynamics from sparse satellite fire detection observations. We propose a physics-informed deep learning inversion framework centered on time-of-arrival (ToA) of fire front propagation. Specifically, we design a conditional generative adversarial network (cGAN) that integrates the WRF-SFIRE coupled atmosphere-wildfire physical model into the GAN training pipeline for the first time; a differentiable observation operator enables synthetic-data-driven training without ground-truth annotations. Experimental results demonstrate that satellite fire point observations dominate ToA inference, while terrain effects are negligible. Evaluated on five major wildfires in the U.S. West Coast, our method achieves an average Sørensen–Dice coefficient of 0.81 between reconstructed fire perimeters and airborne survey ground truth—significantly outperforming conventional data assimilation approaches.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Increasing wildfire occurrence has spurred growing interest in wildfire spread prediction. However, even the most complex wildfire models diverge from observed progression during multi-day simulations, motivating need for data assimilation. A useful approach to assimilating measurement data into complex coupled atmosphere-wildfire models is to estimate wildfire progression from measurements and use this progression to develop a matching atmospheric state. In this study, an approach is developed for estimating fire progression from VIIRS active fire measurements, GOES-derived ignition times, and terrain height data. A conditional Generative Adversarial Network is trained with simulations of historic wildfires from the atmosphere-wildfire model WRF-SFIRE, thus allowing incorporation of WRF-SFIRE physics into estimates. Fire progression is succinctly represented by fire arrival time, and measurements for training are obtained by applying an approximate observation operator to WRF-SFIRE solutions, eliminating need for satellite data during training. The model is trained on tuples of fire arrival times, measurements, and terrain, and once trained leverages measurements of real fires and corresponding terrain data to generate samples of fire arrival times. The approach is validated on five Pacific US wildfires, with results compared against high-resolution perimeters measured via aircraft, finding an average Sorensen-Dice coefficient of 0.81. The influence of terrain height on the arrival time inference is also evaluated and it is observed that terrain has minimal influence when the inference is conditioned on satellite measurements.

Problem

• Estimating wildfire progression from satellite and terrain data
• Incorporating WRF-SFIRE physics into fire arrival time predictions
• Validating model accuracy against high-resolution fire perimeters

Innovation

• Generative Adversarial Network estimates fire progression
• VIIRS and GOES data integrated with terrain
• WRF-SFIRE physics embedded in training