Machine learning method of metal organic framework based on 2-CEES

The invention discloses a 2-CEES-based metal organic framework machine learning method, which comprises the following steps: S1, obtaining metal organic framework structure parameters through giant regular Monte Carlo simulation, obtaining adsorption separation performance parameters of the metal organic framework to a mustard gas simulation agent 2-CEES, and sorting the obtained data to obtain a data set; s2, dividing the obtained data set into a test set and a prediction set, adopting five-fold cross validation, and using a machine learning model to predict the data set; s3, hyper-parameters of the machine learning model are adjusted until the evaluation result of the machine learning model meets the expected requirement; and S4, screening the MOFs according to an evaluation result. According to the method, the MOF is used as a 2-CEES adsorbent, machine learning is used for prediction, the high-performance MOF can be screened out, the development speed of the MOF is increased, and a new method is provided f