Growing field of materials informatics: databases and artificial intelligence
- PDF / 601,477 Bytes
- 10 Pages / 612 x 792 pts (letter) Page_size
- 93 Downloads / 202 Views
Artificial Intelligence Prospective Article
Growing field of materials informatics: databases and artificial intelligence Alejandro Lopez-Bezanilla , Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM 87545, USA Peter B. Littlewood , Argonne National Laboratory, Lemont, IL 60439, USA; James Franck Institute, University of Chicago, Chicago, IL 60637, USA Address all correspondence to Alejandro Lopez-Bezanilla at [email protected] (Received 30 June 2019; accepted 23 December 2019)
Abstract The paradigm of molecular discovery in the chemical and pharmaceutical industry has followed a repetitive succession of screening and synthesis, involving the analysis of individual molecules that were both natural and produced. This ability to generate and screen libraries of compounds has found an echo in solid-state physics with the demand to explore and produce new materials for testing. In response to this demand, a golden age of materials discovery is being developed, with progress on important areas of both basic science and device applications. The confluence of theoretical and simulation methods, together with the availability of computation resources, has established the “materials genome” approach that is used by a growing number of research groups around the world with the goal of innovating on materials through systematic discovery. In this Prospective, an overview of this group of methodologies in tackling the ever-increasing complexity of computational materials science simulations is provided. Computational simulation is highlighted as a major component of rational design and synthesis of new materials with targeted properties, describing progress on databases and large data treatment. Tools for new materials discovery, including progress on the deployment of new data repositories, the implementation of high-throughput simulation approaches, and the development of artificial intelligence algorithms, are discussed.
Introduction Over the last decades, an extraordinary ability at generating and accumulating a growing amount of data has characterized modern society’s progress. Ranging from commercial transactions of individuals to advertisers, data are being saved with the increasing certainty that it may contain information not yet unveiled. The scientific community has not stayed out of this trend, and records are being broken in science in many aspects of data acquisition, data rates, and data volumes, with increasing levels of computing and storage resources utilization. To give an example, the Large Hadron Collider experiments at CERN have produced unprecedented volumes of data thanks to the increasingly sophisticated data reconstruction and storage devices, which in 2017 alone collected a total of 200 petabytes,[1] with an upward trend in the future. A multibeam scanning electron microscope can routinely produce 30–50 terabytes of data per day. Similar or larger data rates are expected from imaging beamlines on next-generation synchrotron sources. Scientists face the challenge of making sense of
Data Loading...
