Machine learning-based prediction and optimization of the cellulose conversion process for levulinic acid production
Levulinic acid (LA) is a promising platform product with wide industrial applications. Efficient conversion of cellulose into LA has become a research hotspot, yet traditional experimental optimization is time-consuming and inefficient. This study integrates multidimensional data—reaction conditions, solvent properties, and physicochemical characteristics of metal salts—to construct a systematic dataset. Six machine learning models (decision tree, gradient boosting regression, K-nearest neighbors, multilayer perceptron, random forest, and support vector machine) were developed to predict LA yield. The gradient boosting regression (GBR) model achieved the best performance, with a test-set determination coefficient (R²) of 0.94 and the lowest root-mean-square error (RMSE). SHapley Additive exPlanations (SHAP) and partial dependence analysis identified water fraction, catalyst dosage, and reaction temperature as the key factors influencing LA formation. By integrating the GBR model with particle swarm optimization (PSO), RuCl₃ was identified as an efficient catalyst under high-temperature and short-reaction-time conditions. This study demonstrates the potential of machine learning in cellulose conversion research, providing a data-driven strategy and theoretical guidance for efficient and green LA production.