Chemically intuited, large-scale screening of MOFs by machine learning techniques

• Published in: npj computational materials Vol. 3; no. 1; pp. 1 - 7
• Main Authors: Borboudakis, Giorgos, Stergiannakos, Taxiarchis, Frysali, Maria, Klontzas, Emmanuel, Tsamardinos, Ioannis, Froudakis, George E.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 02.10.2017; Nature Publishing Group
• Subjects: 639/638/298/921; 639/638/563; Artificial intelligence; Carbon dioxide; Catalysis; Characterization and Evaluation of Materials; Chemical properties; Chemistry and Materials Science; Coding; Colleges & universities; Computational Intelligence; Computer applications; Feature recognition; Hydrogen storage; Learning algorithms; Machine learning; Materials Science; Mathematical and Computational Engineering; Mathematical and Computational Physics; Mathematical Modeling and Industrial Mathematics; Metal-organic frameworks; Porous materials; Predictions; Screening; Test procedures; Theoretical
• ISSN: 2057-3960; 2057-3960
• DOI: 10.1038/s41524-017-0045-8

A novel computational methodology for large-scale screening of MOFs is applied to gas storage with the use of machine learning technologies. This approach is a promising trade-off between the accuracy of ab initio methods and the speed of classical approaches, strategically combined with chemical intuition. The results demonstrate that the chemical properties of MOFs are indeed predictable (stochastically, not deterministically) using machine learning methods and automated analysis protocols, with the accuracy of predictions increasing with sample size. Our initial results indicate that this methodology is promising to apply not only to gas storage in MOFs but in many other material science projects. Machine learning: Quickly screening materials for effective gas storage The gas storage properties of metal-organic frameworks can now be quickly and accurately predicted by artificial intelligence. George Froudakis at the University of Crete has developed a machine learning approach to predict the H 2 /CO 2 adsorption properties of metal-organic frameworks (MOFs), highly porous materials promising for catalysis and gas storage, based on their chemical structure. Previous methods were either too slow, or not accurate enough. Here, Froudakis and his team encoded ‘chemical intuition’ into their algorithm by training it to recognize certain structural features in MOFs with known properties. Then, when they applied the method to large-scale screening tests of new MOFs they found their predictions matched with experimental data. With this technique, it is hoped that new materials for CO 2 sequestration or hydrogen storage will be discovered more quickly.