[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122676-en":3,"doc-seo-122676-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122676,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Machine Learning Descriptors for Data-Driven Catalysis Study - A Review","Traditional trial-and-error experiments and theoretical simulations struggle to optimize catalytic processes and accelerate discovery of better-performing catalysts. This review explains how machine learning can speed catalysis research through learning and prediction, emphasizing that the selection and extraction of catalytic descriptors (input features) critically shape predictive accuracy and reveal drivers of activity and selectivity. The work surveys descriptor tactics, compares effectiveness and limitations, highlights new spectral descriptors, and proposes a computational–experimental paradigm using intermediate descriptors, then outlines challenges and future directions.","UC Irvine  \nUC Irvine Previously Published Works  \nTitle  \nMachine Learning Descriptors for Data‐Driven Catalysis Study  \nPermalink  \n[https://escholarship.org/uc/item/9zc1r279](https://escholarship.org/uc/item/9zc1r279)  \nJournal  \nAdvanced Science, 10(22)  \nISSN  \n2198-3844  \nAuthors  \nMou, Li‐Hui  \nHan, TianTian Smith, Pieter ESet al.  \nPublication Date  \n2023-08-01  \nDOI  \n10.1002/advs.202301020  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nREVIEW  \n[www.advancedscience.com](www.advancedscience.com)  \nMachine Learning Descriptors for Data-Driven Catalysis Study  \nLi-Hui Mou, TianTian Han, Pieter E. S. Smith, Edward Sharman,* and Jun Jiang*  \nTraditional trial-and-error experiments and theoretical simulations have difficulty optimizing catalytic processes and developing new,  \nbetter-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 perspectiveson the application of descriptors and ML techniques to catalysis are also presented.  \n1. Introduction  \nCatalysis plays an important role in modern chemical industry, with its many chemical processes—such as energy conversion and pollutant removal—that need catalysts to greatly reduce input costs and increase product yields.[1] Identifying optimal reaction conditions, designing efficient catalysts, and revealing catalytic mechanisms are important research areas in the field of catalysis. Experimental trial-and-error is the classical research paradigm, in which one variable is usually evaluated at a time, incurring the disadvantages of long timelinesand low efficiency. Moreover, traditional experimental and computational methods rely heavily on prior knowledge and are vulnerable to human cognitive biases. With the development of computational chemistry, theoretical simulations mainly based on density functional theory (DFT) calculations that incorporate simplified model  \nL.-H. Mou, J. Jiang  \nHefei National Research Center for Physical Sciences at the Microscale School of Chemistry and Materials Science  \nUniversity of Science and Technology of China Hefei, Anhui 230026, China  \nE-mail: [jiangj1@ustc.edu.cn](jiangj1@ustc.edu.cn)  \nT. Han  \nHefei JiShu Quantum Technology Co. Ltd.  \nHefei 230026, China  \nP. E. S. Smith YDS Pharmatech ETEC  \n1220 Washington Ave., Albany, NY 12203, USA  \nE. Sharman Department of Neurology University of California Irvine, CA 92697, USA  \nE-mail: [esharman@uci.edu](esharman@uci.edu)  \nThe ORCID identification number(s) for the author(s) of this article can be found under [https://doi.org/10.1002/advs.202301020](https://doi.org/10.1002/advs.202301020)  \n© 2023 The Authors. Advanced Science published by Wiley-VCH GmbH. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \nDOI: 10.1002/advs.202301020  \nsyste","cbCaipkRP2bvebdP","https://ap.wps.com/l/cbCaipkRP2bvebdP","pdf",5696567,1,21,"English","en",105,"# Introduction\n## Catalysis research challenges\n## Role of machine learning in catalysis\n## Importance of catalytic descriptors\n## Review scope and focus","[{\"question\":\"Why do traditional experimental and theoretical approaches have difficulty optimizing catalysis?\",\"answer\":\"They often rely on trial-and-error with slow, low-efficiency workflows and on simulations that become costly as model complexity increases.\"},{\"question\":\"What are catalytic descriptors in machine-learning-assisted catalysis research?\",\"answer\":\"Catalytic descriptors are machine-readable representations extracted from original data that encode reaction conditions, catalysts, and reactants to predict target properties such as yield, selectivity, and adsorption energy.\"},{\"question\":\"What does the review highlight regarding descriptors and future directions?\",\"answer\":\"It discusses tactics for using and extracting descriptors, covers limitations of various descriptor types, emphasizes newly developed spectral descriptors, proposes an intermediate-descriptor paradigm combining computational and experimental ML models, and presents key challenges and future perspectives.\"}]","Machine Learning Descriptors for Data-Driven Catalysis Study - A Review | PDF",1785812124,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-descriptors-for-data-driven-catalysis-study-a-review","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-descriptors-for-data-driven-catalysis-study-a-review/122676/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do traditional experimental and theoretical approaches have difficulty optimizing catalysis?","Question",{"text":75,"@type":76},"They often rely on trial-and-error with slow, low-efficiency workflows and on simulations that become costly as model complexity increases.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are catalytic descriptors in machine-learning-assisted catalysis research?",{"text":80,"@type":76},"Catalytic descriptors are machine-readable representations extracted from original data that encode reaction conditions, catalysts, and reactants to predict target properties such as yield, selectivity, and adsorption energy.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the review highlight regarding descriptors and future directions?",{"text":84,"@type":76},"It discusses tactics for using and extracting descriptors, covers limitations of various descriptor types, emphasizes newly developed spectral descriptors, proposes an intermediate-descriptor paradigm combining computational and experimental ML models, and presents key challenges and future perspectives.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]