Comparative Analysis of Machine Learning Models for Predicting and Optimizing Biodiesel Production Yield: A Study of Neural Networks, Random Forest, and Decision Tree Algorithms

Document Type : Original Article

Author

Department of Chemical and Petroleum Engineering, Fouman Faculty of Engineering, College of Engineering, University of Tehran , Tehran, Iran

10.22091/jdaid.2026.14976.1031

Abstract

This study compares three machine learning algorithms (Multilayer Perceptron Neural Network (MLP), Random Forest (RF), and Decision Tree (DT)) for modeling biodiesel production. For this purpose the synthesis methods (UIMS, MS, FPUI, PUI), the methanol to oil ratio (3:1 to 15:1) and reaction times (5–50 minutes), were considered as input parameters and the percentage of biodiesel production was considered as the output of the model. According to the results, the MLP model demonstrated superior predictive performance, with an R² score of 0.9800, RMSE of 3.28, and MAE of 2.35, significantly outperforming RF (R² = 0.8892) and DT (R² = 0.8500). Also, the neural network model represents that all parameters (reaction time, methanol to oil ratio, and synthesis method) hold nearly equal importance. Based on the neural network model, the optimal synthesis conditions are: the UIMS method, a reaction time of 47 minutes, and a methanol-to-oil ratio of 5.8:1, yielding a predicted conversion of 98%.

Keywords

Main Subjects

Journal of Data Analytics and Intelligent Decision-making
Volume 1, Issue 4
January 2026
Pages 116-126

Files

Share

How to cite

Statistics