Cartesian atomic cluster expansion for machine learning interatomic potentials

2024/02/12 by Bingqing Cheng, Cheng, Bingqing · 24 citations
Materials Science · #Chemical Physics (physics.chem-ph) #Computational Physics (physics.comp-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning in Materials Science

paper · pdf · doi:10.48550/arxiv.2402.07472

openalex publication_date 2024/02/12 · openalex created_date 2024/02/14 · openalex updated_date 2026/07/28

Abstract

Machine learning interatomic potentials are revolutionizing large-scale, accurate atomistic modelling in material science and chemistry. Many potentials use atomic cluster expansion or equivariant message passing frameworks. Such frameworks typically use spherical harmonics as angular basis functions, and then use Clebsch-Gordan contraction to maintain rotational symmetry, which may introduce redundancies in representations and computational overhead. We propose an alternative: a Cartesian-coordinates-based atomic density expansion. This approach provides a complete set of polynormially indepedent features of atomic environments while maintaining interaction body orders. Additionally, we integrate low-dimensional embeddings of various chemical elements and inter-atomic message passing. The resulting potential, named Cartesian Atomic Cluster Expansion (CACE), exhibits good accuracy, stability, and generalizability. We validate its performance in diverse systems, including bulk water, small molecules, and 25-element high-entropy alloys.

Cited by

• Long-range electrostatics for machine learning interatomic potentials is easier than we thought
• A Cartesian-3j Framework for Machine Learning Interatomic Potentials
• Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spaces
• Beyond Adam: Disentangling Optimizer Effects in the Fine-Tuning of Atomistic Foundation Models
• A Hybrid Physics-Driven Neural Network Force Field for Liquid Electrolytes
• Intrinsic structure of relaxor ferroelectrics from first principles
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Committors without Descriptors
• Achieving Empirical Potential Efficiency with DFT Accuracy: A Neuroevolution Potential for the α-Fe--C--H System
• Atomistic Machine Learning with Irreducible Cartesian Natural Tensors
• Extrapolation of Machine-Learning Interatomic Potentials for Organic and Polymeric Systems
• Incorporating Coulomb interactions with fixed charges in Moment Tensor Potentials and Equivariant Tensor Network Potentials
• Spectral/Spatial Tensor Atomic Cluster Expansion with Universal Embeddings in Cartesian Space
• Ion-modulated structure, proton transfer, and capacitance in the Pt(111)/water electric double layer
• Node-Equivariant Message Passing for Efficient and Accurate Machine Learning Interatomic Potentials
• Learning Long-Range Representations with Equivariant Messages
• A universal augmentation framework for long-range electrostatics in machine learning interatomic potentials
• Fine-Tuning Universal Machine-Learned Interatomic Potentials: A Tutorial on Methods and Applications
• INN-FF: A Scalable and Efficient Machine Learning Potential for Molecular Dynamics
• Efficient Parallelization of Message Passing Neural Network Potentials for Large-scale Molecular Dynamics
• AccelNet: Exact backward-compatible acceleration of polynomial angular descriptors through Cartesian moment factorization
• Scalable Data-Driven Basis Selection for Linear Machine Learning Interatomic Potentials
• High-performance training and inference for deep equivariant interatomic potentials
• Improving robustness and training efficiency of machine-learned potentials by incorporating short-range empirical potentials
• Cross-functional transferability in universal machine learning interatomic potentials

Related

• Cartesian atomic moment machine learning interatomic potentials
• Graph atomic cluster expansion for foundational machine learning interatomic potentials
• Scalable Data-Driven Basis Selection for Linear Machine Learning Interatomic Potentials
• Hyperparameter Optimization for Atomic Cluster Expansion Potentials
• Graph Atomic Cluster Expansion for semilocal interactions beyond equivariant message passing