TY - JOUR
T1 - Data-Driven Discovery of Photoactive Quaternary Oxides Using First-Principles Machine Learning
AU - Davies, Daniel W.
AU - Butler, Keith T.
AU - Walsh, Aron
N1 - Funding Information:
Via our membership of the UK's HEC Materials Chemistry Consortium, which is funded by EPSRC (EP/L000202), this work used the ARCHER UK National Supercomputing Service (http://www.archer.ac.uk) for all DFT calculations. D.W.D. is supported by the EPSRC via the Doctoral Prize Fellowship, and A.W. is supported by a Royal Society University Research Fellowship. This research was also supported by the Creative Materials Discovery Program through the National Research Foundation of Korea (NRF) funded by Ministry of Science and ICT (2018M3D1A1058536).
Funding Information:
Via our membership of the UK’s HEC Materials Chemistry Consortium, which is funded by EPSRC (EP/L000202), this work used the ARCHER UK National Supercomputing Service ( http://www.archer.ac.uk ) for all DFT calculations. D.W.D. is supported by the EPSRC via the Doctoral Prize Fellowship, and A.W. is supported by a Royal Society University Research Fellowship. This research was also supported by the Creative Materials Discovery Program through the National Research Foundation of Korea (NRF) funded by Ministry of Science and ICT (2018M3D1A1058536).
Publisher Copyright:
© 2019 American Chemical Society.
PY - 2019/9/24
Y1 - 2019/9/24
N2 - We present a low-cost, virtual high-throughput materials design workflow and use it to identify earth-abundant materials for solar energy applications from the quaternary oxide chemical space. A statistical model that predicts bandgap from chemical composition is built using supervised machine learning. The trained model forms the first in a hierarchy of screening steps. An ionic substitution algorithm is used to assign crystal structures, and an oxidation state probability model is used to discard unlikely chemistries. We demonstrate the utility of this process for screening over 1 million oxide compositions. We find that, despite the difficulties inherent to identifying stable multicomponent inorganic materials, several compounds produced by our workflow are calculated to be thermodynamically stable or metastable and have desirable optoelectronic properties according to first-principles calculations. The predicted oxides are Li2MnSiO5, MnAg(SeO3)2, and two polymorphs of MnCdGe2O6, all four of which are found to have direct electronic bandgaps in the visible range of the solar spectrum.
AB - We present a low-cost, virtual high-throughput materials design workflow and use it to identify earth-abundant materials for solar energy applications from the quaternary oxide chemical space. A statistical model that predicts bandgap from chemical composition is built using supervised machine learning. The trained model forms the first in a hierarchy of screening steps. An ionic substitution algorithm is used to assign crystal structures, and an oxidation state probability model is used to discard unlikely chemistries. We demonstrate the utility of this process for screening over 1 million oxide compositions. We find that, despite the difficulties inherent to identifying stable multicomponent inorganic materials, several compounds produced by our workflow are calculated to be thermodynamically stable or metastable and have desirable optoelectronic properties according to first-principles calculations. The predicted oxides are Li2MnSiO5, MnAg(SeO3)2, and two polymorphs of MnCdGe2O6, all four of which are found to have direct electronic bandgaps in the visible range of the solar spectrum.
UR - http://www.scopus.com/inward/record.url?scp=85072640847&partnerID=8YFLogxK
U2 - 10.1021/acs.chemmater.9b01519
DO - 10.1021/acs.chemmater.9b01519
M3 - Article
AN - SCOPUS:85072640847
VL - 31
SP - 7221
EP - 7230
JO - Chemistry of Materials
JF - Chemistry of Materials
SN - 0897-4756
IS - 18
ER -