Data-Driven Modelling to predict forest fire spread in the Patagonian region in Argentina

TL;DR

This paper presents a hybrid computational framework combining genetic algorithms and machine learning to accurately model and predict wildfire spread in Patagonia, Argentina, using high-resolution landscape data.

Contribution

It introduces an integrated approach that combines Reaction-Diffusion-Convection modeling with GA and XGBoost for improved wildfire simulation accuracy.

Findings

GA accurately recovers model parameters across scenarios.

XGBoost refinement significantly improves prediction accuracy.

The framework effectively estimates difficult-to-measure wildfire parameters.

Abstract

Wildfires are among the most severe disturbances affecting forest ecosystems, with over 50,000 hectares burned in Patagonia, Argentina, during 2025 alone. This study implements a Reaction-Diffusion-Convection (RDC) model to simulate wildfire spread in the Steffen and Martin Lakes area, a region severely impacted by fires. By integrating high-resolution maps of slope, wind velocity, and vegetation, we conducted three computational experiments of increasing complexity to simulate fire propagation across heterogeneous landscapes. We employed a Genetic Algorithm (GA) to recover reference model parameters by maximizing the spatial overlap between simulated and reference burned areas. Subsequently, parameter estimates were refined using XGBoost to improve accuracy. Results demonstrate that the GA accurately recovers reference parameters across all scenarios, while the XGBoost fine-tuning significantly enhances accuracy in simpler cases. This integrated framework offers a systematic approach for estimating difficult-to-measure wildfire parameters, demonstrating the potential of hybrid computational methods for wildfire modeling and forest management.