Recent developments in biodiesel synthesis from agricultural wastes: A comprehensive review of feedstocks, catalysts, and machine learning approaches

Abstract

The growing demand for sustainable energy and increasing concerns about the environmental effects of fossil fuels have driven interest in biodiesel as a renewable alternative. This review integrates recent advances in biodiesel production, feedstock valorization, catalyst-based approaches, and the applications of artificial intelligence (AI) and machine learning (ML), providing a comprehensive framework that extends beyond prior studies focused on isolated aspects of biodiesel synthesis. Current literature highlights the potential of non-edible oils, agricultural residues, and waste-driven feedstocks, along with emerging microalgae-based systems, as economical and sustainable resources. Improvements in heterogeneous and nanocatalysts have enhanced operational efficiency, ecological metrics, and reusability. Moreover, AI- and ML-based simulations have demonstrated significant predictive capacity as well as optimized approaches achieving biodiesel productivity beyond 95%. Future research should emphasize scaling production of microalgae, improving biocatalyst recovery, and integrating AI/ML-based tools to optimize process pathways and biomass selection, which ultimately facilitates the transition toward eco-friendly and industrially scalable biodiesel production strategies.