Fine-Tuning LightGBM Using an Artificial Ecosystem-Based Optimizer for Forest Fire Analysis

Abstract

Abstract This study’s main objective is to propose a hybrid machine learning model based on a gradient boosting algorithm named LightGBM and an artificial ecosystem-based optimization to improve the accuracy of forest fire susceptibility assessment. Four hundred twenty-six historical forest fires from the NASA portal and thirteen conditional factors including elevation, aspect, slope, curvature, normalized difference vegetation index, normalized difference water index, distance to residence, distance to road, distance to river, temperature, rain, humidity, and wind were used to train the model. The model performance was evaluated and compared with other benchmark models using root mean square error, area under receiver operating characteristics (AUC), and overall accuracy. The results show that the proposed model (AUC = 0.9705) outperforms others, such as Random Forest (AUC = 0.958), AdaBoost (AUC = 0.905), Bagging (AUC = 0.945), and Random Subspace (AUC = 0.938), respectively. The final model was interpreted to better understand the most influential factors of forest fire hazards.