Machine Learning Descriptors for Data‐Driven Catalysis Study

Abstract Traditional trial‐and‐error experiments and theoretical simulations have difficulty optimizing catalytic processes and developing new, better‐performing catalysts. Machine learning (ML) provides a promising approach for accelerating catalysis research due to its powerful learning and predic...

Full description

Bibliographic Details
Main Authors: Li‐Hui Mou, TianTian Han, Pieter E. S. Smith, Edward Sharman, Jun Jiang
Format: Article
Language:English
Published: Wiley 2023-08-01
Series:Advanced Science
Subjects:
Online Access:https://doi.org/10.1002/advs.202301020
_version_ 1827877452548931584
author Li‐Hui Mou
TianTian Han
Pieter E. S. Smith
Edward Sharman
Jun Jiang
author_facet Li‐Hui Mou
TianTian Han
Pieter E. S. Smith
Edward Sharman
Jun Jiang
author_sort Li‐Hui Mou
collection DOAJ
description Abstract Traditional trial‐and‐error experiments and theoretical simulations have difficulty optimizing catalytic processes and developing new, better‐performing catalysts. Machine learning (ML) provides a promising approach for accelerating catalysis research due to its powerful learning and predictive abilities. The selection of appropriate input features (descriptors) plays a decisive role in improving the predictive accuracy of ML models and uncovering the key factors that influence catalytic activity and selectivity. This review introduces tactics for the utilization and extraction of catalytic descriptors in ML‐assisted experimental and theoretical research. In addition to the effectiveness and advantages of various descriptors, their limitations are also discussed. Highlighted are both 1) newly developed spectral descriptors for catalytic performance prediction and 2) a novel research paradigm combining computational and experimental ML models through suitable intermediate descriptors. Current challenges and future perspectives on the application of descriptors and ML techniques to catalysis are also presented.
first_indexed 2024-03-12T17:37:38Z
format Article
id doaj.art-62c534a4c17f4e43aa3cc4a0018e6820
institution Directory Open Access Journal
issn 2198-3844
language English
last_indexed 2024-03-12T17:37:38Z
publishDate 2023-08-01
publisher Wiley
record_format Article
series Advanced Science
spelling doaj.art-62c534a4c17f4e43aa3cc4a0018e68202023-08-04T07:49:49ZengWileyAdvanced Science2198-38442023-08-011022n/an/a10.1002/advs.202301020Machine Learning Descriptors for Data‐Driven Catalysis StudyLi‐Hui Mou0TianTian Han1Pieter E. S. Smith2Edward Sharman3Jun Jiang4Hefei National Research Center for Physical Sciences at the Microscale School of Chemistry and Materials Science University of Science and Technology of China Hefei Anhui 230026 ChinaHefei JiShu Quantum Technology Co. Ltd. Hefei 230026 ChinaYDS Pharmatech ETEC 1220 Washington Ave. Albany NY 12203 USADepartment of Neurology University of California Irvine CA 92697 USAHefei National Research Center for Physical Sciences at the Microscale School of Chemistry and Materials Science University of Science and Technology of China Hefei Anhui 230026 ChinaAbstract Traditional trial‐and‐error experiments and theoretical simulations have difficulty optimizing catalytic processes and developing new, better‐performing catalysts. Machine learning (ML) provides a promising approach for accelerating catalysis research due to its powerful learning and predictive abilities. The selection of appropriate input features (descriptors) plays a decisive role in improving the predictive accuracy of ML models and uncovering the key factors that influence catalytic activity and selectivity. This review introduces tactics for the utilization and extraction of catalytic descriptors in ML‐assisted experimental and theoretical research. In addition to the effectiveness and advantages of various descriptors, their limitations are also discussed. Highlighted are both 1) newly developed spectral descriptors for catalytic performance prediction and 2) a novel research paradigm combining computational and experimental ML models through suitable intermediate descriptors. Current challenges and future perspectives on the application of descriptors and ML techniques to catalysis are also presented.https://doi.org/10.1002/advs.202301020catalytic descriptorsheterogeneous catalysishigh‐throughput experimentsmachine learningtheoretical simulations
spellingShingle Li‐Hui Mou
TianTian Han
Pieter E. S. Smith
Edward Sharman
Jun Jiang
Machine Learning Descriptors for Data‐Driven Catalysis Study
Advanced Science
catalytic descriptors
heterogeneous catalysis
high‐throughput experiments
machine learning
theoretical simulations
title Machine Learning Descriptors for Data‐Driven Catalysis Study
title_full Machine Learning Descriptors for Data‐Driven Catalysis Study
title_fullStr Machine Learning Descriptors for Data‐Driven Catalysis Study
title_full_unstemmed Machine Learning Descriptors for Data‐Driven Catalysis Study
title_short Machine Learning Descriptors for Data‐Driven Catalysis Study
title_sort machine learning descriptors for data driven catalysis study
topic catalytic descriptors
heterogeneous catalysis
high‐throughput experiments
machine learning
theoretical simulations
url https://doi.org/10.1002/advs.202301020
work_keys_str_mv AT lihuimou machinelearningdescriptorsfordatadrivencatalysisstudy
AT tiantianhan machinelearningdescriptorsfordatadrivencatalysisstudy
AT pieteressmith machinelearningdescriptorsfordatadrivencatalysisstudy
AT edwardsharman machinelearningdescriptorsfordatadrivencatalysisstudy
AT junjiang machinelearningdescriptorsfordatadrivencatalysisstudy