Accelerating Computational Materials Discovery with Machine Learning and Cloud High-Performance Computing: from Large-Scale Screening to Experimental ValidationClick to copy article linkArticle link copied!
- Chi ChenChi ChenAzure Quantum, Microsoft, One Microsoft Way, Redmond, Washington 98052, United StatesMore by Chi Chen
- Dan Thien NguyenDan Thien NguyenPacific Northwest National Laboratory, Physical and Computational Sciences Directorate, 902 Battelle Blvd., Richland, Washington 99352, United StatesMore by Dan Thien Nguyen
- Shannon J. LeeShannon J. LeePacific Northwest National Laboratory, Physical and Computational Sciences Directorate, 902 Battelle Blvd., Richland, Washington 99352, United StatesMore by Shannon J. Lee
- Nathan A. BakerNathan A. BakerAzure Quantum, Microsoft, One Microsoft Way, Redmond, Washington 98052, United StatesMore by Nathan A. Baker
- Ajay S. KarakotiAjay S. KarakotiPacific Northwest National Laboratory, Physical and Computational Sciences Directorate, 902 Battelle Blvd., Richland, Washington 99352, United StatesMore by Ajay S. Karakoti
- Linda LauwLinda LauwAzure Quantum, Microsoft, One Microsoft Way, Redmond, Washington 98052, United StatesMore by Linda Lauw
- Craig OwenCraig OwenMicrosoft Surface, Microsoft, One Microsoft Way, Redmond, Washington 98052, United StatesMore by Craig Owen
- Karl T. MuellerKarl T. MuellerPacific Northwest National Laboratory, Physical and Computational Sciences Directorate, 902 Battelle Blvd., Richland, Washington 99352, United StatesMore by Karl T. Mueller
- Brian A. BilodeauBrian A. BilodeauAzure Quantum, Microsoft, One Microsoft Way, Redmond, Washington 98052, United StatesMore by Brian A. Bilodeau
- Vijayakumar Murugesan*Vijayakumar Murugesan*Email: [email protected]Pacific Northwest National Laboratory, Physical and Computational Sciences Directorate, 902 Battelle Blvd., Richland, Washington 99352, United StatesMore by Vijayakumar Murugesan
- Matthias Troyer*Matthias Troyer*Email: [email protected]Azure Quantum, Microsoft, One Microsoft Way, Redmond, Washington 98052, United StatesMore by Matthias Troyer
Abstract
High-throughput computational materials discovery has promised significant acceleration of the design and discovery of new materials for many years. Despite a surge in interest and activity, the constraints imposed by large-scale computational resources present a significant bottleneck. Furthermore, examples of very large-scale computational discovery carried out through experimental validation remain scarce, especially for materials with product applicability. Here, we demonstrate how this vision became reality by combining state-of-the-art machine learning (ML) models and traditional physics-based models on cloud high-performance computing (HPC) resources to quickly navigate through more than 32 million candidates and predict around half a million potentially stable materials. By focusing on solid-state electrolytes for battery applications, our discovery pipeline further identified 18 promising candidates with new compositions and rediscovered a decade’s worth of collective knowledge in the field as a byproduct. We then synthesized and experimentally characterized the structures and conductivities of our top candidates, the NaxLi3–xYCl6 (0≤ x≤ 3) series, demonstrating the potential of these compounds to serve as solid electrolytes. Additional candidate materials that are currently under experimental investigation could offer more examples of the computational discovery of new phases of Li- and Na-conducting solid electrolytes. The showcased screening of millions of materials candidates highlights the transformative potential of advanced ML and HPC methodologies, propelling materials discovery into a new era of efficiency and innovation.
Cited By
This article is cited by 7 publications.
- Alexander B. Bard, Robert G. Felsted, Abbie S. Ganas, Anupum Pant, Chaman Gupta, Ying Chen, Elias Nakouzi, Biao Jin, Nancy M. Washton, Michael D. LaCount, Christopher J. Mundy, Gregory K. Schenter, Jaehun Chun, Steven R. Spurgeon, Guesang K. Lee, Vincent C. Holmberg, Lucien N. Brush, James J. De Yoreo, Peter J. Pauzauskie. Chemically Driven Multistep Crystallization in the Synthesis of Sodium Yttrium Fluoride Via a Porous, Electrochemically Active Intermediate. The Journal of Physical Chemistry C 2024, 128
(31)
, 13034-13044. https://doi.org/10.1021/acs.jpcc.4c01281
- Tianfu Zhang, Keliang Wang, Hengwei Wang, Manhui Wei, Zhuo Chen, Daiyuan Zhong, Yunxiang Chen, Pucheng Pei. Polymer gels for aqueous metal batteries. Progress in Materials Science 2025, 151 , 101426. https://doi.org/10.1016/j.pmatsci.2025.101426
- Asif Iqbal Bhatti, Sandeep Kumar, Catharina Jaeken, Michael Sluydts, Danny E. P. Vanpoucke, Stefaan Cottenier. The devil in the details: lessons from Li
6
PS
5
X for robust high-throughput workflows. Journal of Materials Chemistry A 2024, 13
(1)
, 526-539. https://doi.org/10.1039/D4TA06603K
- Sai Krishna Gunda. Accelerating Scientific Discovery With Machine Learning and HPC-Based Simulations. 2024, 229-252. https://doi.org/10.4018/978-1-6684-3795-7.ch009
- Chi Chen. AI in materials science: Charting the course to Nobel-worthy breakthroughs. Matter 2024, 7
(12)
, 4123-4125. https://doi.org/10.1016/j.matt.2024.11.012
- Xi Yang, Yuting Li, Yitao Liu, Qian Li, Tingna Yang, Hongxing Jia. Crystal Structure Prediction and Performance Assessment of Hydrogen Storage Materials: Insights from Computational Materials Science. Energies 2024, 17
(14)
, 3591. https://doi.org/10.3390/en17143591
- Nanping Deng, Wenwen Duan, Wen Yu, Yang Feng, Zichun Feng, Xiaofan Feng, Zhaozhao Peng, Hengying Xiang, Yong Liu, Weimin Kang. Progress and perspectives on the development of inorganic nanofibres/nanowires for functional electrolytes of solid-state lithium metal batteries. Inorganic Chemistry Frontiers 2024, 82 https://doi.org/10.1039/D4QI01831A
Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to reflect usage leading up to the last few days.
Citations are the number of other articles citing this article, calculated by Crossref and updated daily. Find more information about Crossref citation counts.
The Altmetric Attention Score is a quantitative measure of the attention that a research article has received online. Clicking on the donut icon will load a page at altmetric.com with additional details about the score and the social media presence for the given article. Find more information on the Altmetric Attention Score and how the score is calculated.