Graph networks as a universal machine learning framework for molecules and crystals

C Chen, W Ye, Y Zuo, C Zheng, SP Ong - Chemistry of Materials, 2019 - ACS Publications
Graph networks are a new machine learning (ML) paradigm that supports both relational
reasoning and combinatorial generalization. Here, we develop universal MatErials Graph …

Boosting quantum machine learning models with a multilevel combination technique: Pople diagrams revisited

P Zaspel, B Huang, H Harbrecht… - Journal of chemical …, 2018 - ACS Publications
Inspired by Pople diagrams popular in quantum chemistry, we introduce a hierarchical
scheme, based on the multilevel combination (C) technique, to combine various levels of …

Band gap prediction for large organic crystal structures with machine learning

B Olsthoorn, RM Geilhufe, SS Borysov… - Advanced Quantum …, 2019 - Wiley Online Library
Abstract Machine‐learning models are capable of capturing the structure–property
relationship from a dataset of computationally demanding ab initio calculations. Over the …

Hierarchical visualization of materials space with graph convolutional neural networks

T **e, JC Grossman - The Journal of chemical physics, 2018 - pubs.aip.org
The combination of high throughput computation and machine learning has led to a new
paradigm in materials design by allowing for the direct screening of vast portions of …

Machine learning of atomic-scale properties based on physical principles

M Ceriotti, MJ Willatt, G Csányi - Handbook of Materials Modeling: Methods …, 2020 - Springer
We briefly summarize the kernel regression approach, as used recently in materials
modeling, to fitting functions, particularly potential energy surfaces, and highlight how the …

Atomic descriptors generated from coordination polyhedra in crystal structures

Y Inada, Y Katsura, M Kumagai… - Science and Technology …, 2021 - Taylor & Francis
We developed atomic descriptors from local crystal structures, which will facilitate
researchers' use of machine learning to predict the properties of inorganic materials via …

Deep learning methods for the design and understanding of solid materials

T **e - 2020 - dspace.mit.edu
The trend of open material data and automation in the past decade offers a unique
opportunity for data-driven design of novel materials for various applications as well as …