Machine Learning Approaches to Equilibrium Burnup Analysis for Molten Salt Reactor

•A filtering model and a prediction model for equilibrium state of Molten Salt Reactors are developed.•The LightGBM model is the most favorable for filtering the burnup state and predicting the neutronic parameters.•The LightGBM model obtains the accuracy of 0.98 for classification and the relative error of 1.10% for regression.