An efficient catalyst screening strategy combining machine learning and causal inference.

Journal: Journal of environmental management
PMID:

Abstract

Due to the diversity of catalyst synthesis methods, the optimization of catalysts by traditional experimental methods have brought greater challenges. This study presents a new strategy for determining catalyst performance by substituting causal inference results as prior knowledge into machine learning models, which was used to explore the correlation between the ratio of nitrogen functional groups in catalysts and degradation performance, so as to solve the problem of low efficiency in catalyst screening. A dataset comprising 14 critical parameters, including the physicochemical properties of catalysts and reaction conditions, was established through the analysis of 182 experimental results. The analysis results based on real data show that CatBoost model performs best (R = 0.953, MAE = 3.277, RMSE = 5.615). SHAP analysis showed that pyridinic N was a key N-functional group that affects the degradation performance of BPA. DoWhy causal inference further verified the positive effect of pyridinic N, with causal effect estimate of 0.4388. This strategy reduces the selection range of the best catalyst through causal inference pre-screening, and used CatBoost model to accurately evaluate the performance of its catalyst, which can reduce the catalyst screening process from multiple processes to a single process, and significantly improve the catalyst selection efficiency.

Authors

  • Chenyu Song
    Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China.
  • Yintao Shi
    Engineering Research Center Clean Production of Textile Dyeing and Printing, Ministry of Education, Wuhan, 430073, PR China; School of Environmental Engineering, Wuhan Textile University, Wuhan, 430073, PR China.
  • Meng Li
    Co-Innovation Center for the Sustainable Forestry in Southern China; Cerasus Research Center; College of Biology and the Environment, Nanjing Forestry University, Nanjing, China.
  • Lin Wu
    Key Laboratory of Grain and Oil Processing and Food Safety of Sichuan Province, College of Food and Bioengineering, Xihua University Chengdu 610039 China xingyage1@163.com.
  • Xiaorong Xiong
    School of Computing, Huanggang Normal University, Huanggang, 438000, PR China.
  • Jianyun Liu
    Textile Pollution Controlling Engineering Centre of Ministry of Ecology and Environment, College of Environmental Science and Engineering, Donghua University, Shanghai, 201620, PR China.
  • Dongsheng Xia
    Engineering Research Center Clean Production of Textile Dyeing and Printing, Ministry of Education, Wuhan, 430073, PR China. Electronic address: dongsheng_xia@wtu.edu.cn.