|About this Abstract
||2019 TMS Annual Meeting & Exhibition
||Computational Approaches for Big Data, Artificial Intelligence and Uncertainty Quantification in Computational Materials Science
||Materials Platform for Data Science: From Big Data towards Materials Genome
||Evgeny Blokhin, Pierre Villars
|On-Site Speaker (Planned)
Since 1993 the PAULING FILE project team led by Pierre Villars (Switzerland) extracts materials data from the peer-reviewed literature in materials science. As of 2018, nearly 300k publications have been processed, and about 400k crystal structures, 60k phase diagrams, and 1M other property sets were extracted. All data have been systematized and critically evaluated. Today PAULING FILE backs up such commercial products as Springer Materials and MedeA Materials Design. The Materials Platform for Data Science (MPDS, www.mpds.io) is an online edition of the PAULING FILE, providing the data in machine-readable format via the REST API. Using the PAULING FILE data, we present a holistic vision for all the inorganic substances. Coupled with the high-throughput ab initio simulations and the top-down/bottom-up artificial intelligence techniques, our vision provides a key to the discovery of materials genome, playing a role of the periodic table for the entire set of materials.
||Planned: Supplemental Proceedings volume