Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Machine learned synthesizability predictions aided by density functional theory

Journal Article · · Communications Materials

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.

Sponsoring Organization:
USDOE
Grant/Contract Number:
AC02-76SF00515
OSTI ID:
1891929
Journal Information:
Communications Materials, Journal Name: Communications Materials Journal Issue: 1 Vol. 3; ISSN 2662-4443
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (69)

Crystal Structures, Bonding and Electronic Structures of MM′As, a Series of New Ternary Arsenides (M = Zr, Hf; M′ = Fe, Co, Ni) journal January 1998
Design of High‐Performance Disordered Half‐Heusler Thermoelectric Materials Using 18‐Electron Rule journal August 2019
Machine Learning Stability and Bandgaps of Lead‐Free Perovskites for Photovoltaics journal November 2019
Polymorphic Metastability in Colloidal Semiconductor Nanocrystals journal September 2020
Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) journal September 2013
The alloy theoretic automated toolkit: A user guide journal December 2002
A machine learning approach for engineering bulk metallic glass alloys journal October 2018
AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations journal June 2012
Data-driven atomic environment prediction for binaries using the Mendeleev number journal March 2004
Magnetic properties of Mn 2 PdSn and Mn 2 PdIn journal March 2016
Machine learning-guided synthesis of advanced inorganic materials journal December 2020
Simple rules for the understanding of Heusler compounds journal May 2011
Half-Heusler Structures with Full-Heusler Counterparts: Machine-Learning Predictions and Experimental Validation journal September 2020
Vibrational Entropy Stabilizes Distorted Half-Heusler Structures journal May 2020
From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown journal February 2016
High-Throughput Machine-Learning-Driven Synthesis of Full-Heusler Compounds journal October 2016
Using the 18-Electron Rule To Understand the Nominal 19-Electron Half-Heusler NbCoSb with Nb Vacancies journal January 2017
Elaborating the Crystal Structures of MgAgSb Thermoelectric Compound: Polymorphs and Atomic Disorders journal July 2017
Designing High-Efficiency Nanostructured Two-Phase Heusler Thermoelectrics journal October 2017
Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning journal October 2017
Designing and Discovering a New Family of Semiconducting Quaternary Heusler Compounds Based on the 18-Electron Rule journal June 2018
Materials Screening for the Discovery of New Half-Heuslers: Machine Learning versus ab Initio Methods journal August 2017
Accelerated Discovery of New 8-Electron Half-Heusler Compounds as Promising Energy and Topological Quantum Materials journal March 2019
Structure-Based Synthesizability Prediction of Crystals Using Partially Supervised Learning journal October 2020
Machine Learning Guided Synthesis of Multinary Chevrel Phase Chalcogenides journal June 2021
Discovery of a useful thin-film dielectric using a composition-spread approach journal March 1998
Engineering half-Heusler thermoelectric materials using Zintl chemistry journal May 2016
Machine-learning-assisted materials discovery using failed experiments journal May 2016
Prediction and accelerated laboratory discovery of previously unknown 18-electron ABX compounds journal March 2015
Combinatorial solid-state chemistry of inorganic materials journal July 2004
The high-throughput highway to computational materials design journal February 2013
A general-purpose machine learning framework for predicting properties of inorganic materials journal August 2016
Double-slit photoelectron interference in strong-field ionization of the neon dimer journal January 2019
Network analysis of synthesizable materials discovery journal May 2019
Recent advances and applications of machine learning in solid-state materials science journal August 2019
Machine learning for perovskite materials design and discovery journal January 2021
Accurate and scalable graph neural network force field and molecular dynamics with direct force architecture journal May 2021
Unsupervised machine learning for discovery of promising half-Heusler thermoelectric materials journal March 2022
Electronic-structure methods for materials design journal May 2021
Structure prediction drives materials discovery journal April 2019
New Heusler compounds in Ni-Mn-In and Ni-Mn-Sn alloys journal May 2019
Predicting synthesizability of crystalline materials via deep learning journal November 2021
Learning properties of ordered and disordered materials from multi-fidelity data journal January 2021
Materials Prediction via Classification Learning journal August 2015
Computational and experimental investigation of TmAgTe 2 and XYZ 2 compounds, a new group of thermoelectric materials identified by first-principles high-throughput screening journal January 2015
A valence balanced rule for discovery of 18-electron half-Heuslers with defects journal January 2018
A low-loss composition region identified from a thin-film composition spread of (Ba1−x−ySrxCay)TiO3 journal February 1999
Ferromagnetism in Mn doped half-Heusler NiTiSn: Theory and experiment journal November 2006
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation journal July 2013
Heusler alloys for spintronic devices: review on recent development and future perspectives journal March 2021
Half-Heusler compounds: novel materials for energy and spintronic applications journal April 2012
Ferromagnetic half-metallicity in half-Heusler AuMnSn:Te Alloy journal July 2020
The Freezing Points, Melting Points, and Solid Solubility Limits of the Alloys of Silver, and Copper with the Elements of the B Sub-Groups
  • Hume-Rothery, W.; Mabbott, G. W.; Evans, K. M. C.
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 233, Issue 721-730 https://doi.org/10.1098/rsta.1934.0014
journal January 1934
Combinatorial screening for new materials in unconstrained composition space with machine learning journal March 2014
Computational investigation of half-Heusler compounds for spintronics applications journal January 2017
Ultralow Thermal Conductivity in Full Heusler Semiconductors journal July 2016
Special quasirandom structures journal July 1990
Entropically Favored Ordering: The Metallurgy of Al 2 Cu Revisited journal June 2001
Predictions of new AB O 3 perovskite compounds by combining machine learning and density functional theory journal April 2018
Machine-learning-accelerated high-throughput materials screening: Discovery of novel quaternary Heusler compounds journal December 2018
Deposition of uniform Zr-Sn-Ti-O films by on-axis reactive sputtering journal September 1998
The thermodynamic scale of inorganic crystalline metastability journal November 2016
Accelerated discovery of new magnets in the Heusler alloy family journal April 2017
Thermodynamic limit for synthesis of metastable inorganic materials journal April 2018
Machine learning–accelerated design and synthesis of polyelemental heterostructures journal December 2021
The Statistical Mechanics of Dynamic Pathways to Self-Assembly journal April 2015
New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships journal April 2016
Finding New Perovskite Halides via Machine Learning journal April 2016
Original Papers journal January 2005

Similar Records

Predicting the synthesizability of crystalline inorganic materials from the data of known material compositions
Journal Article · Fri Aug 25 00:00:00 EDT 2023 · npj Computational Materials · OSTI ID:1996869

Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry
Journal Article · Tue Oct 09 00:00:00 EDT 2018 · Nature Communications · OSTI ID:1619800

Predicting synthesizable multi-functional edge reconstructions in two-dimensional transition metal dichalcogenides
Journal Article · Tue May 05 00:00:00 EDT 2020 · npj Computational Materials · OSTI ID:1765415

Related Subjects