{"title":"Concluding remarks: <i>Faraday Discussion</i> on data-driven discovery in the chemical sciences.","authors":"Andrew I Cooper","doi":"10.1039/d4fd00174e","DOIUrl":null,"url":null,"abstract":"<p><p>This <i>Faraday Discussion</i> was the first to focus on the increasingly central role of big data, machine learning, and artificial intelligence in the chemical sciences. The aim was to critically discuss these topics, and to explore the question of how data can enable new discoveries in chemistry, both now and in the future. The programme spanned computational and experimental work, and encompassed emerging topics such as natural language processing, machine-learned potentials, optimization strategies, and robotics and self-driving laboratories. Here I provide some brief introductory comments on the history of this field, along with some personal views on the discussion topics covered, concluding with three future challenges for this area.</p>","PeriodicalId":76,"journal":{"name":"Faraday Discussions","volume":" ","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Faraday Discussions","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1039/d4fd00174e","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0
Abstract
This Faraday Discussion was the first to focus on the increasingly central role of big data, machine learning, and artificial intelligence in the chemical sciences. The aim was to critically discuss these topics, and to explore the question of how data can enable new discoveries in chemistry, both now and in the future. The programme spanned computational and experimental work, and encompassed emerging topics such as natural language processing, machine-learned potentials, optimization strategies, and robotics and self-driving laboratories. Here I provide some brief introductory comments on the history of this field, along with some personal views on the discussion topics covered, concluding with three future challenges for this area.