文献类型：期刊文献

英文题名：Thermodynamics-Guided Machine Learning Framework with a Multiobjective Optimizer for Catalyst Discovery

作者：Tan, Zhenfeng[1];Zhu, Yuanming[2];Shao, Bin[1];Qian, Feng[2];Hu, Jun[1]

机构：[1]East China Univ Sci & Technol, Sch Chem & Mol Engn, State Key Lab Green Chem Engn & Ind Catalysis, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Sch Informat Sci & Engn, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2026

卷号：16

期号：2

起止页码：1312

外文期刊名：ACS CATALYSIS

收录：;EI(收录号：20260319934063);WOS:【SCI-EXPANDED(收录号:WOS:001653531400001)】；

基金：This research was supported by the National Natural Science Foundation of China (22250005, 22408095), National Key R&D Program of China (2024YFA1509801), the Science and Technology Commission of Shanghai Municipality (25DZ3000804), China National Postdoctoral Program for Innovative Talents (BX20240116), China Postdoctoral Science Foundation (2023M741170), and Fundamental Research Funds for the Central Universities.

语种：英文

外文关键词：machine learning; reverse water-gas shift; thermodynamics-guided; multiobjective optimizer; normalization approach

摘要：Machine learning (ML) holds great promise for discovering catalysts; however, simultaneously possessing high interpretability, prediction accuracy, and catalyst discovery efficiency remains a substantial challenge. Here, an ML framework with thermodynamic guidelines from scratch is constructed to explore superior multimetallic catalysts for the representative reverse water-gas shift (RWGS) reaction. A normalization approach is employed to redefine the elemental physicochemical properties, leveraging the advantages of the elemental and property features of active metals. This not only enables accurate predictions but also derives the value range of each feature through deep insights into the catalytic mechanisms. More importantly, a genetic algorithm (GA)-based multiobjective optimizer is developed for reverse engineering the compositions of multimetallic catalysts. Specifically, by enforcing explicit thermodynamic constraints and self-correcting by experimentally validated results into the ML models, both rigorous discovery of catalysts within the training data set and extrapolation are successfully achieved. After two rounds of self-corrections, optimal ternary-metallic catalysts are experimentally validated with a superior CO yield close to the equilibrium limitation. Therefore, this ML framework is a promising paradigm for catalyst research, as highlighted by intrinsic theoretical guidance and experimental validation.