Data-Driven Optimization of Biodiesel Synthesis from Waste Cooking Oil over Sargassum sp.-Based Catalyst Using ANN and RSM

Abstract

The increasing depletion of fossil fuels and associated environmental concerns have intensified the need for sustainable alternative energy sources. Biodiesel derived from waste cooking oil (WCO) offers a promising solution; however, conventional homogeneous catalysts remain limited due to their sensitivity to water content and free fatty acids (FFA), leading to soap formation and complicated separation processes. To address these challenges, this study explores the use of a heterogeneous catalyst derived from Sargassum sp. macroalgae as an eco-friendly and cost-effective alternative. The novelty of this work lies in integrating marine biomass-derived catalysts with data-driven optimization techniques to enhance biodiesel production efficiency. This study aims to predict and optimize biodiesel synthesis from WCO using artificial neural network (ANN) and response surface methodology (RSM). Transesterification reactions were conducted at temperatures of 50–70 °C, reaction times of 60–180 min, oil-to-methanol molar ratios of 1:3 to 1:12, and a fixed catalyst loading of 2 wt%. A Box–Behnken design (BBD) was employed for RSM modeling, while ANN was trained using the Levenberg–Marquardt algorithm in MATLAB R2022a. The results indicate that the maximum experimental biodiesel yield reached 95.8 wt% under optimal conditions of 60 °C, a molar ratio of 1:9, and a reaction time of 90 min. Comparative analysis shows that ANN provides lower prediction errors than RSM, demonstrating superior accuracy in modeling biodiesel production under varying reaction conditions. The findings highlight the effectiveness of combining marine biomass-derived catalysts with advanced predictive modeling tools to improve process efficiency.