WildFireGS: Physics-Based Wildfire Simulation in Large-Scale Semantics-Enriched Gaussian Splatting Forest Scenes

2026-08-11

AI Summary

This work addresses the limitations of existing physics-based wildfire simulation methods, which rely on idealized environments and struggle to generalize to real forest scenes. The authors propose a novel approach that natively integrates semantically enhanced 3D Gaussian splatting reconstruction with a particle-level physical combustion model, enabling direct simulation of flame propagation, heat transfer, and rain-induced cooling on the Gaussian representation—without requiring mesh or voxel conversion. Semantic-aware fuel properties are incorporated to support fireline suppression and biomass loss estimation. Experiments demonstrate that the method accurately reproduces wildfire dynamics in both real and synthetic aerial forest scenes, capturing the influence of vegetation density, wind speed, and terrain. The framework also successfully validates firebreak efficacy and enables ecological impact assessment.

Abstract

Climate-driven environmental change is driving an increase in both the frequency and severity of wildfire events, making accurate simulation and prediction critical for effective risk mitigation and landscape management. While recent physics-based wildfire models achieve high realism by explicitly simulating combustion, heat transfer, and fuel dynamics, they remain largely restricted to synthetic environments with complete and idealized knowledge of forest structure, limiting their applicability to real-world environments captured via aerial imagery. To provide a pathway toward real-world wildfire digital twins derived directly from observational data, we present WildFireGS, a physics-based wildfire simulation framework operating directly on large-scale, semantics-enriched 3D Gaussian Splatting forest reconstructions. Our approach bridges learning-based scene reconstruction and environmental simulation by augmenting Gaussian primitives with semantics and material properties that encode vegetation type and fuel characteristics. We introduce a particle-based combustion model that operates natively on Gaussian representations, simulating ignition, heat transfer, combustion, and flame propagation across complex forest structures. This enables direct physics-based simulation of fire behavior on reconstructed real-world environments, without requiring conversion to explicit meshes or volumetric grids. We demonstrate the modularity of WildFireGS through a rain-driven cooling mechanism in terms of an energy-sink process to realistically model fire containment. Evaluations on synthetic scenes and real aerial forest captures show physically consistent wildfire behavior, reproducing characteristic dynamics including propagation scaling with vegetation density, wind velocity, and terrain slope. In addition, we validate our model through novel firebreak experiments and biomass loss estimation.

Problem

• wildfire simulation
• real-world environments
• forest scene reconstruction
• physics-based modeling
• aerial imagery

Innovation

• Gaussian Splatting
• physics-based wildfire simulation
• semantic-enriched reconstruction
• particle-based combustion model
• wildfire digital twin