Deep learning model for finding new superconductors
Authors:
Open Access
- 12 January 2021
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review B
- Vol. 103 (1) , 014509
Abstract
Exploration of new superconductors still relies on the experience and intuition of experts, and is largely a process of experimental trial and error. In one study, only 3% of the candidate materials showed superconductivity [Hosono et al., Sci. Technol. Adv. Mater. 16, (2015)]. Here, we report a deep learning model for finding new superconductors. We introduced the method named “reading periodic table” that represented the periodic table in a way that allows deep learning to learn to read the periodic table and to learn the law of elements for the purpose of discovering novel superconductors which are outside the training data. It is recognized that it is difficult for deep learning to predict something outside the training data. Although we used only the chemical composition of materials as information, we obtained an value of 0.92 for predicting for materials in a database of superconductors. We also introduced the method named “garbage-in” to create synthetic data of nonsuperconductors that do not exist. Nonsuperconductors are not reported, but the data must be required for deep learning to distinguish between superconductors and nonsuperconductors. We obtained three remarkable results. The deep learning can predict superconductivity for a material with a precision of 62%, which shows the usefulness of the model; it found the recently discovered superconductor and another one , neither of which is in the superconductor database; and it found Fe-based high-temperature superconductors (discovered in 2008) from the training data before 2008. These results open the way for the discovery of new high-temperature superconductor families. The candidate materials list, data, and method are openly available on the Internet.
Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Conventional superconductivity at 203 kelvin at high pressures in the sulfur hydride systemNature, 2015
- Exploration of new superconductors and functional materials, and fabrication of superconducting tapes and wires of iron pnictidesScience and Technology of Advanced Materials, 2015
- Commentary: The Materials Project: A materials genome approach to accelerating materials innovationAPL Materials, 2013
- AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculationsComputational Materials Science, 2012
- Crystallography Open Database (COD): an open-access collection of crystal structures and platform for world-wide collaborationNucleic Acids Research, 2011
- Crystallography Open Database – an open-access collection of crystal structuresJournal of Applied Crystallography, 2009
- Iron-Based Layered Superconductor La[O1-xFx]FeAs (x = 0.05−0.12) with Tc = 26 KJournal of the American Chemical Society, 2008
- Possible highT c superconductivity in the Ba?La?Cu?O systemZeitschrift für Physik B Condensed Matter, 1986
- Self-Consistent Equations Including Exchange and Correlation EffectsPhysical Review B, 1965
- Microscopic Theory of SuperconductivityPhysical Review B, 1957