Neural network predicts material charge densities faster and accurately
Neural-Network Solutions to Real-Space Charge Density and Generalization
Artificial Intelligence
Summary
Computing the detailed distribution of electrons in materials is usually slow and needs many steps. The authors created AIDEN, a smart neural network that learns to predict these electron patterns directly and quickly without repeated calculations. AIDEN breaks down the problem by focusing on individual atoms and their connections, making it adaptable to new materials it hasn't seen before. This method is both accurate and much faster than traditional approaches, helping speed up materials design.
What this means in practice
- •For materials scientists: Generate accurate electron density maps quickly to accelerate computational material discovery pipelines.
- •For computational chemists: Obtain fast and reliable charge densities for molecules to reduce time in electronic structure simulations.
Authors
Yuxuan Zeng, Taoyuze Lv, Zhicheng Zhong
Abstract
The Hohenberg-Kohn theorem establishes that, in principle, the ground state (GS) charge density contains all GS information of a many-electron system, such that all GS observables can be expressed as functionals of the GS charge density. Conventional Kohn-Sham density functional theory requires iterative solution of the self-consistent-field equations at substantial computational cost, motivating the development of deep learning surrogates for electronic structure calculations and, in turn, accelerating computer-aided materials design. Here, we propose \textbf{AIDEN}, an \underline{A}tomic-\underline{I}nteraction \underline{D}ensity \underline{E}quivariant \underline{N}etwork for solving real-space charge density. AIDEN separates the element-dependent one-center density from environment-induced density redistribution and represents the latter through complementary atom- and edge-centered tensor correlations. A continuous low-rank Gaussian decoder then reconstructs the density at arbitrary spatial coordinates while reusing atomic encodings independently of the evaluation grid. AIDEN achieves state-of-the-art accuracy on periodic crystal benchmarks while remaining competitive for molecular systems, and further demonstrates zero-shot transferability across several structurally distinct out-of-distribution case studies. Furthermore, AIDEN provides substantially faster inference than both baseline models and full SCF calculations, enabling efficient charge density reconstruction for large-scale electronic structure calculations.