论文信息 - Data-centric approach to improve machine learning models for inorganic materials - 字舞流文

Data-centric approach to improve machine learning models for inorganic materials

Pandey et al. (2021) demonstrate the importance of diversifying training data to make balanced predictions of thermodynamic properties for inorganic crystals.

Christopher J. Bartel

[1] Jeffrey C Grossman,et al. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. , 2017, Physical review letters.

[2] Kristin A. Persson,et al. Commentary: The Materials Project: A materials genome approach to accelerating materials innovation , 2013 .

[3] Matthew K. Horton,et al. Promises and perils of computational materials databases , 2021, Nature Computational Science.

[4] Vladan Stevanovic,et al. Predicting energy and stability of known and hypothetical crystals using graph neural network , 2021, Patterns.

[5] Mariette Hellenbrandt,et al. The Inorganic Crystal Structure Database (ICSD)—Present and Future , 2004 .

[6] Christopher J. Bartel,et al. A critical examination of compound stability predictions from machine-learned formation energies , 2020, npj Computational Materials.

[7] Gerbrand Ceder,et al. Efficient first-principles prediction of solid stability: Towards chemical accuracy , 2018, npj Computational Materials.