Size and Temperature Transferability of Direct and Local Deep Neural Networks for Atomic Forces

Abstract

A direct and local deep learning (DL) model for atomic forces is presented. We demonstrate the model performance in bulk aluminum, sodium, and silicon; and show that its errors are comparable to those found in state-of-the-art machine learning and DL models. We then analyze the model's performance as a function of the number of neighbors included and show that one can ascertain physical attributes of the system from the analysis of the deep learning model's behavior. Finally, we test the size scaling performance of the model, and the transferability between different temperatures, and show that our model performs well in both scaling to larger systems and high-to-low temperature predictability.

References in corpus (20)

• Scikit-learn: Machine Learning in Python
• The NumPy array: a structure for efficient numerical computation
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• AFLOW: An automatic framework for high-throughput materials discovery
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Hierarchical modeling of molecular energies using a deep neural network
• Unified Representation of Molecules and Crystals for Machine Learning
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models
• Comparing the Accuracy of High-Dimensional Neural Network Potentials and the Systematic Molecular Fragmentation Method: A Benchmark Study for all-trans Alkanes
• Deep Learning for Computational Chemistry
• Machine Learning for Atomic Forces in a Crystalline Solid: Transferability to Various Temperatures
• Quantum Energy Regression using Scattering Transforms

Cited by in corpus (7)

• Atomistic Mechanism Underlying the Si(111)-(7\times7) Surface Reconstruction Revealed by Artificial Neural-network Potential
• Anharmonic Thermodynamics of Vacancies Using a Neural Network Potential
• Neural Networks Potential from the Bispectrum Component: A Case Study on Crystalline Silicon
• Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations
• Machine learning forces trained by Gaussian process in liquid states: Transferability to temperature and pressure
• Building nonparametric $n$-body force fields using Gaussian process regression
• A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics