Lean CNNs for mapping electron charge density fields to material properties

Abstract

This work introduces a lean CNN (convolutional neural network) framework, with a drastically reduced number of fittable parameters (<81K) compared to the benchmarks in current literature, to capture the underlying low-computational cost (i.e., surrogate) relationships between the electron charge density (ECD) fields and their associated effective properties. These lean CNNs are made possible by adding a pre-processing step (i.e., a feature engineering step) that involves the computation of the ECD fields' spatial correlations (specifically, 2-point spatial correlations). The viability and benefits of the proposed lean CNN framework are demonstrated by establishing robust structure-property relationships involving the prediction of effective material properties using the feature-engineered ECD fields as the only input. The framework is evaluated on a dataset of crystalline cubic systems consisting of 1410 molecular structures spanning 62 different elemental species and 3 space groups.

References in corpus (19)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• SchNet - a deep learning architecture for molecules and materials
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Comparing molecules and solids across structural and alchemical space
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• By-passing the Kohn-Sham equations with machine learning
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
• Deep Learning and Density Functional Theory
• Machine learning and density functional theory
• Toward Orbital-Free Density Functional Theory with Small Data Sets and Deep Learning
• Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks
• Accelerating Material Design with the Generative Toolkit for Scientific Discovery
• Deep Neural Network Computes Electron Densities and Energies of a Large Set of Organic Molecules Faster than Density Functional Theory (DFT)
• Machine Learning Diffusion Monte Carlo Energies
• Conditional probability density functional theory
• Recurrent Localization Networks applied to the Lippmann-Schwinger Equation
• Digital representation and quantification of discrete dislocation networks

Cited by in corpus (3)

• Refining Coarse-Grained Molecular Topologies: A Bayesian Optimization Approach
• Sequential Bayesian Inference of the GTN Damage Model Using Multimodal Experimental Data
• Physics Aware Representation Learning on Electronic Charge Density for Materials Property Prediction