A grand challenge of materials science is predicting synthesis pathways for novel compounds. Data-driven approaches have made significant progress in predicting a compound’s synthesizability; however, some recent attempts ignore phase stability information. Here, we combine thermodynamic stability calculated using density functional theory with composition-based features to train a machine learning model that predicts a material’s synthesizability. Our model predicts the synthesizability of ternary 1:1:1 compositions in the half-Heusler structure, achieving a cross-validated precision of 0.82 and recall of 0.82. Our model shows improvement in predicting non-half-Heuslers compared to a previous study’s model, and identifies 121 synthesizable candidates out of 4141 unreported ternary compositions. More notably, 39 stable compositions are predicted unsynthesizable while 62 unstable compositions are predicted synthesizable; these findings otherwise cannot be made using density functional theory stability alone. This study presents a new approach for accurately predicting synthesizability, and identifies new half-Heuslers for experimental synthesis.
Lee, Andrew, Sarker, Suchismita, Saal, James E., et al., "Machine learned synthesizability predictions aided by density functional theory," Communications Materials 3, no. 1 (2022), https://doi.org/10.1038/s43246-022-00295-7
@article{osti_1891929,
author = {Lee, Andrew and Sarker, Suchismita and Saal, James E. and Ward, Logan and Borg, Christopher and Mehta, Apurva and Wolverton, Christopher},
title = {Machine learned synthesizability predictions aided by density functional theory},
annote = {Abstract A grand challenge of materials science is predicting synthesis pathways for novel compounds. Data-driven approaches have made significant progress in predicting a compound’s synthesizability; however, some recent attempts ignore phase stability information. Here, we combine thermodynamic stability calculated using density functional theory with composition-based features to train a machine learning model that predicts a material’s synthesizability. Our model predicts the synthesizability of ternary 1:1:1 compositions in the half-Heusler structure, achieving a cross-validated precision of 0.82 and recall of 0.82. Our model shows improvement in predicting non-half-Heuslers compared to a previous study’s model, and identifies 121 synthesizable candidates out of 4141 unreported ternary compositions. More notably, 39 stable compositions are predicted unsynthesizable while 62 unstable compositions are predicted synthesizable; these findings otherwise cannot be made using density functional theory stability alone. This study presents a new approach for accurately predicting synthesizability, and identifies new half-Heuslers for experimental synthesis.},
doi = {10.1038/s43246-022-00295-7},
url = {https://www.osti.gov/biblio/1891929},
journal = {Communications Materials},
issn = {ISSN 2662-4443},
number = {1},
volume = {3},
place = {United Kingdom},
publisher = {Nature Publishing Group},
year = {2022},
month = {10}}
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 233, Issue 721-730https://doi.org/10.1098/rsta.1934.0014