Bayesian Hyperparameter Optimization of Machine Learning Models for Predicting Biomass Gasification Gases
Pınar Cihan
Abstract
Predicting biomass gasification gases is crucial for energy production and environmental monitoring but poses challenges due to complex relationships and variability. Machine learning has emerged as a powerful tool for optimizing and managing these processes. This study uses Bayesian optimization to tune parameters for various machine learning methods, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient-Boosting Machine (LightGBM), Elastic Net, Adaptive Boosting (AdaBoost), Gradient-Boosting Regressor (GBR), K-nearest Neighbors (KNN), and Decision Tree (DT), aiming to identify the best model for predicting the compositions of CO, CO2, H2, and CH4 under different conditions. Performance was evaluated using the correlation coefficient (R), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), Relative Absolute Error (RAE), and execution time, with comparisons visualized using a Taylor diagram. Hyperparameter optimization’s significance was assessed via t-test effect size and Cohen’s d. XGBoost outperformed other models, achieving high R values under optimal conditions (0.951 for CO, 0.954 for CO2, 0.981 for H2, and 0.933 for CH4) and maintaining robust performance under suboptimal conditions (0.889 for CO, 0.858 for CO2, 0.941 for H2, and 0.856 for CH4). In contrast, K-nearest Neighbors (KNN) and Elastic Net showed the poorest performance and stability. This study underscores the importance of hyperparameter optimization in enhancing model performance and demonstrates XGBoost’s superior accuracy and robustness, providing a valuable framework for applying machine learning to energy management and environmental monitoring.