Machine learning-guided prediction of hydroformylation.

Abstract

A holistic model for predicting yield and linear selectivity for the hydroformylation of 1-octene was developed by machine learning using the experimental data collected from literatures. Physical organic chemistry (POC) parameter-based descriptors were adopted to represent pre-catalyst molecular features. Machine learning models trained respectively by Random Forests (RF) and Extreme Gradient Boost (XGBoost) algorithm showed remarkable performance on predicting linear selectivity. The method can also comprehensively map the correlation between reaction conditions and the results. The accuracy of the prediction results was verified by experimental data.