DeePAW: A universal machine learning model for orbital-free ab initio calculations

TL;DR

DeePAW is a novel universal machine learning model for orbital-free ab initio calculations based on DFT, achieving high accuracy, broad element coverage, and diverse structure applicability, advancing multiscale materials modeling.

Contribution

The paper introduces DeePAW, a new SE(3)-equivariant neural network architecture that significantly improves the accuracy and applicability of ML-based orbital-free DFT calculations.

Findings

DeePAW outperforms existing models in element coverage and accuracy.

It can predict electron densities and formation energies effectively.

The model enables efficient multiscale materials simulations.

Abstract

Developing universal machine learning models for ab initio calculations is the frontier of materials cutting edge research in the new era of artificial intelligence. Here, we present the Deep Augment Way model (DeePAW) that is a universal machine learning (ML) model for orbital-free (OF) ab initio calculations, based on the density functional theory (DFT). DeePAW is currently the best OFDFT ML model according to the three criterions, 1) covering the largest number of elements, 2) having the widest application capability to diverse crystal structures, and 3) achieving the highest prediction accuracy without further fine-tuning. These scientific merits and innovations of DeePAW are stemmed from the novel SE(3)-equivariant double massage passing neuron networks. Besides predicting electron density distributions, DeePAW predicts formation energies of crystals as well and therefore paves an efficient avenue for multiscale materials modeling beyond conventional electronic structure calculation methods.