Materials Discovery With Machine Learning and Knowledge Discovery

Osvaldo N Oliveira Jr; Maria Cristina F Oliveira

doi:10.3389/fchem.2022.930369

Materials Discovery With Machine Learning and Knowledge Discovery

Front Chem. 2022 Jul 7:10:930369. doi: 10.3389/fchem.2022.930369. eCollection 2022.

Authors

Osvaldo N Oliveira Jr¹, Maria Cristina F Oliveira²

Affiliations

¹ Sao Carlos Institute of Physics (IFSC), University of Sao Paulo, Sao Paulo, Brazil.
² Institute of Mathematics and Computer Science (ICMC), University of Sao Paulo, Sao Paulo, Brazil.

Abstract

Machine learning and other artificial intelligence methods are gaining increasing prominence in chemistry and materials sciences, especially for materials design and discovery, and in data analysis of results generated by sensors and biosensors. In this paper, we present a perspective on this current use of machine learning, and discuss the prospects of the future impact of extending the use of machine learning to encompass knowledge discovery as an essential step towards a new paradigm of machine-generated knowledge. The reasons why results so far have been limited are given with a discussion of the limitations of machine learning in tasks requiring interpretation. Also discussed is the need to adapt the training of students and scientists in chemistry and materials sciences, to better explore the potential of artificial intelligence capabilities.

Keywords: computational chemistry; data analytics; knowledge discovery; machine learning; materials discovery.