DeePAW: A universal machine learning model for orbital-free ab initio calculations
This provides a more efficient method for multiscale materials modeling, addressing a bottleneck in materials science research, though it appears incremental as an improvement over existing orbital-free DFT models.
The authors tackled the problem of developing a universal machine learning model for orbital-free ab initio calculations, resulting in DeePAW, which achieves the highest prediction accuracy, covers the largest number of elements, and has the widest application capability to diverse crystal structures without fine-tuning.
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.