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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Becerra, Lucas, Denham, Monica Malen, Kolton, Alejandro B., Laneri, Karina
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915971697999872
author Becerra, Lucas
Denham, Monica Malen
Kolton, Alejandro B.
Laneri, Karina
author_facet Becerra, Lucas
Denham, Monica Malen
Kolton, Alejandro B.
Laneri, Karina
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00167
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Data-Driven Modelling to predict forest fire spread in the Patagonian region in Argentina
Becerra, Lucas
Denham, Monica Malen
Kolton, Alejandro B.
Laneri, Karina
Disordered Systems and Neural Networks
Atmospheric and Oceanic Physics
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.
title Data-Driven Modelling to predict forest fire spread in the Patagonian region in Argentina
topic Disordered Systems and Neural Networks
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2605.00167