Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks

@article{Xie2018HierarchicalVO,
  title={Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks},
  author={Tian Xie and Jeffrey C. Grossman},
  journal={The Journal of chemical physics},
  year={2018},
  volume={149 17},
  pages={
          174111
        }
}
  • T. XieJ. Grossman
  • Published 9 July 2018
  • Materials Science
  • The Journal of chemical physics
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 structural, chemical, and property spaces. The use of these powerful techniques leads to the generation of enormous amounts of data, which in turn calls for new techniques to efficiently explore and visualize the materials space to help identify underlying patterns. In this work, we develop a unified framework to… 

Figures and Tables from this paper

Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery

An improved variant of the CGCNN model (iCGCNN) is developed that outperforms the original by incorporating information of the Voronoi tessellated crystal structure, explicit 3-body correlations of neighboring constituent atoms, and an optimized chemical representation of interatomic bonds in the crystal graphs.

CEGANN: Crystal Edge Graph Attention Neural Network for multiscale classification of materials environment

The Crystal Edge Graph Attention Neural Network (CEGANN) workflow is introduced that uses graph attention-based architecture to learn unique feature representations and perform classification of materials across multiple scales (from atomic to mesoscale) and diverse classes ranging from metals, oxides, non-metals and even hierarchical materials.

CEGAN: Crystal Edge Graph Attention Network for multiscale classification of materials environment

The Crystal Edge Graph Attention Network (CEGAN) workflow is introduced that uses graph attention-based architecture to learn unique feature representations and perform classification of materials across multiple scales and diverse classes ranging from metals, oxides, non-metals and even hierarchical materials such as zeolites.

PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials

In PiNN, a new interpretable and high-performing graph convolutional neural network variant, PiNet, is designed as well as implemented the established Behler-Parrinello high-dimensional neural network.

Big-Data Science in Porous Materials: Materials Genomics and Machine Learning

It is shown that having so many materials allows us to use big-data methods as a powerful technique to study these materials and to discover complex correlations.

Materials Representation and Transfer Learning for Multi-Property Prediction

The Hierarchical Correlation Learning for Multi-property Prediction (H-CLMP) framework is introduced that seamlessly integrates prediction using only a material’s composition, learning and exploitation of correlations among target properties in multitarget regression, and leveraging training data from tangential domains via generative transfer learning.

Graph representation-based machine learning framework for predicting electronic band structures of quantum-confined nanostructures

This paper presents an ML framework for predicting band structures of quantum-confined nanostructures from their geometries, and shows how the framework is constructed and its excellent performance on band structure prediction with a tiny data set.

Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals

This work develops, for the first time, universal MatErials Graph Network (MEGNet) models for accurate property prediction in both molecules and crystals and demonstrates the transfer learning of elemental embeddings from a property model trained on a larger data set to accelerate the training of property models with smaller amounts of data.

Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials

This work develops graph dynamical networks, an unsupervised learning approach for understanding atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations and shows that important dynamical information, which would be difficult to obtain otherwise, can be learned for various multi-component amorphous material systems.

Predicting charge density distribution of materials using a local-environment-based graph convolutional network

The electron charge density distribution of materials is one of the key quantities in computational materials science as theoretically it determines the ground state energy and practically it is used

References

SHOWING 1-10 OF 65 REFERENCES

Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties.

A crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials.

SchNet - A deep learning architecture for molecules and materials.

The deep learning architecture SchNet is presented that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers and employs SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules.

Comparing molecules and solids across structural and alchemical space.

This work discusses how one can combine such local descriptors using a regularized entropy match (REMatch) approach to describe the similarity of both whole molecular and bulk periodic structures, introducing powerful metrics that enable the navigation of alchemical and structural complexities within a unified framework.

A Data-Driven Construction of the Periodic Table of the Elements

This work shows how one can generalize the SOAP kernel to introduce a distance-dependent weight that accounts for the multi-scale nature of the interactions, and a description of correlations between chemical species, to improve substantially the performance of ML models of molecular and materials stability.

Quantum-chemical insights from deep tensor neural networks

An efficient deep learning approach is developed that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems, and unifies concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate chemical space predictions.

A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials

This manuscript has created a framework capable of being applied to a broad range of materials data, and demonstrates how this new method can be used to predict diverse properties of crystalline and amorphous materials, such as band gap energy and glass-forming ability.

Learning atoms for materials discovery

The unsupervised machines (Atom2Vec) can learn the basic properties of atoms by themselves from the extensive database of known compounds and materials, represented in terms of high-dimensional vectors, and clustering of atoms in vector space classifies them into meaningful groups consistent with human knowledge.

Accelerating materials property predictions using machine learning

It is shown that fingerprints based on either chemo-structural (compositional and configurational information) or the electronic charge density distribution can be used to make ultra-fast, yet accurate, property predictions.

Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints

The issue of scientific discovery in materials databases is addressed by introducing novel analytical approaches based on structural and electronic materials fingerprints, which contribute to the emerging field of materials informati...

Combinatorial screening for new materials in unconstrained composition space with machine learning

A machine learning model is constructed from a database of thousands of density functional theory calculations that can predict the thermodynamic stability of arbitrary compositions without any other input and with six orders of magnitude less computer time than DFT.
...