Machine Learning for Computational Heterogeneous Catalysis. Issue 16 (18th June 2019)

• Record Type: Journal Article
• Authors: Schlexer Lamoureux, Philomena; Winther, Kirsten T.; Garrido Torres, Jose Antonio; Streibel, Verena; Zhao, Meng; Bajdich, Michal; Abild‐Pedersen, Frank; Bligaard, Thomas
• Is Part Of: ChemCatChem. Volume 11:Issue 16(2019)
• Page Start: 3581
• Page End: 3601
• Publication Date: 2019-06-18
• Subjects: Computational chemistry -- density functional theory -- heterogeneous catalysis -- machine learning -- materials science; Catalysis -- Periodicals; 541.39505
• DOI: 10.1002/cctc.201900595
• Languages: English
• ISSNs: 1867-3880

Abstract

Abstract: Big data and artificial intelligence has revolutionized science in almost every field – from economics to physics. In the area of materials science and computational heterogeneous catalysis, this revolution has led to the development of scientific data repositories, as well as data mining and machine learning tools to investigate the vast materials space. The goal of using these tools is to establish a deeper understanding of the relations between materials properties and activity, selectivity and stability – the important figures of merit in catalysis. Based on these insights, catalyst design principles can be established, which hopefully lead us to discover highly efficient catalysts to solve pressing issues for a sustainable future and the synthesis of highly functional materials, chemicals and pharmaceuticals. The inherent complexity of catalytic reactions quests for machine learning methods to efficiently navigate through the high‐dimensional hyper‐surfaces in structure optimization problems to determine relevant chemical structures and transition states. In this review, we show how cutting edge data infrastructures and machine learning methods are being used to address problems in computational heterogeneous catalysis. Abstract : Advances in machine learning and data science hold great potential for the rapid computational screening of solid‐state catalyst materials candidates and to accelerate the computation of potential energy landscapes. In this review, we outline important data science and machine learning concepts and show how these are applied in the field of computational heterogeneous catalysis. We cover topics like data storage and sharing, materials featurization and using machine learning models for predictive and mechanistic studies.