期刊
NATURE CATALYSIS
卷 5, 期 3, 页码 175-184出版社
NATURE PORTFOLIO
DOI: 10.1038/s41929-022-00744-z
关键词
-
资金
- US DOE Office of Basic Energy Sciences, Division of Chemical Sciences [DE-SC0021008]
- CBET-National Science Foundation under DMREF [2116646]
- Michigan Institute for Data Science (MIDAS) PODS Grant
- University of Michigan J. Robert Beyster Computational Innovation Graduate Fellows Program
- U.S. Department of Energy (DOE) [DE-SC0021008] Funding Source: U.S. Department of Energy (DOE)
- Directorate For Engineering
- Div Of Chem, Bioeng, Env, & Transp Sys [2116646] Funding Source: National Science Foundation
Most applications of machine learning in heterogeneous catalysis use black-box models, which are not easily interpretable. Interpretable machine learning methods offer an alternative by merging the predictive capacity of black-box models with the interpretability of physics-based models. This Perspective discusses the potential, challenges, and opportunities of interpretable machine learning in catalysis research.
Most applications of machine learning in heterogeneous catalysis thus far have used black-box models to predict computable physical properties (descriptors), such as adsorption or formation energies, that can be related to catalytic performance (that is, activity or stability). Extracting meaningful physical insights from these black-box models has proved challenging, as the internal logic of these black-box models is not readily interpretable due to their high degree of complexity. Interpretable machine learning methods that merge the predictive capacity of black-box models with the physical interpretability of physics-based models offer an alternative to black-box models. In this Perspective, we discuss the various interpretable machine learning methods available to catalysis researchers, highlight the potential of interpretable machine learning to accelerate hypothesis formation and knowledge generation, and outline critical challenges and opportunities for interpretable machine learning in heterogeneous catalysis.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据