A new workflow for materials discovery bridging the gap between experimental databases and Graph Neural Networks
Authors:
- Brandon SchoenerBSBrandon Schoener
- Yuting HuYHYuting Hu
- Pasit WanlaphaPWPasit Wanlapha
- Akshay RengarajanARAkshay Rengarajan
- Ian MoogIMIan Moog
- Michael WangMWMichael Wang
- Peihong ZhangPZPeihong Zhang
- Jinjun XiongJXJinjun Xiong
- Hao ZengHZHao Zeng
- 18 April 2026
- journal article
- Published by Elsevier in Journal of Magnetism and Magnetic Materials
- Vol. 650
Abstract
No abstract availableFunding Information
- University at Buffalo
- National Science Foundation (DMR-2242796)
This publication has 51 references indexed in Scilit:
- Predicting the Curie temperature of Sm-Co-based alloys via data-driven strategyActa Materialia, 2024
- GPTArticleExtractor: An automated workflow for magnetic material database constructionJournal of Magnetism and Magnetic Materials, 2024
- Machine learning magnetism classifiers from atomic coordinatesiScience, 2022
- On-the-fly interpretable machine learning for rapid discovery of two-dimensional ferromagnets with high Curie temperatureChem, 2022
- Machine Learning in Magnetic MaterialsPhysica Status Solidi (b), 2021
- Curie temperature modeling of magnetocaloric lanthanum manganites using Gaussian process regressionJournal of Magnetism and Magnetic Materials, 2020
- Machine learning in materials scienceInfoMat, 2019
- Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD)JOM, 2013
- AFLOW: An automatic framework for high-throughput materials discoveryComputational Materials Science, 2012
- Local spin density functional approach to the theory of exchange interactions in ferromagnetic metals and alloysJournal of Magnetism and Magnetic Materials, 1987