Comparison of the Machine Learning Methods to Predict Wildfire Areas

Abstract

In the last decades, global warming has changed the temperature. It caused an increasing the wildfire in everywhere. Wildfires affect people's social lives, animal lives, and countries' economies. Therefore new prevention and control mechanisms are required for forest fires. Artificial intelligence and neural networks have been benefited from in the management of forest fires since the 1990s. Since that time, machine learning (ML) methods have been used in environmental science in various subjects. This study aims to present a performance comparison of ML algorithms applied in fire management. In this paper, different ML models were used to forecast fire size based on various characteristics such as temperature, wind, humidity and precipitation, using records of 512 wildfires that took place in a national park in Northern Portugal.

A Brief Review of Machine Learning Algorithms in Forest Fires Science

“…There are several studies in the literature discussing the use of machine learning in forest fire science [31][32][33]. Here, we review publications relevant to forest fires that investigate and employ machine learning approaches in multiple domains of application.…”

An overview of machine learning (ML) techniques applied to forest fire studies

“… Simulation and Modeling: Deep Learning, especially techniques like GANs, can simulate forest fire spread patterns based on various parameters. These simulations can aid firefighters and forest managers in understanding the potential spread direction of the fire and the factors influencing it (Bayat & Yıldız, 2022).  Risk Assessment: By assessing vast amounts of data from different regions, ML algorithms can classify areas based on their fire risk.…”