.png){kind=icon}
Return
Optimizing cross-domain transfer for universal machine learning interatomic potentials
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-026-70195-8.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate yet transferable machine-learning interatomic potentials are essential for accelerating materials and chemical discovery. However, many existing universal models are overfitted to narrow chemical spaces or computational protocols, limiting their reliability across diverse chemical and functional domains. Here, we introduce a transferable multi-domain training strategy that jointly optimizes parameters through selective regularization, coupled with a domain-bridging set that aligns potential-energy surfaces across datasets. Systematic ablation experiments show that suggested strategies synergistically enhance out-of-distribution generalization while preserving in-domain fidelity. Based on our observation, we train SevenNet-Omni on 15 open datasets spanning molecules, crystals, and surfaces. Our model achieves state-of-the-art accuracy in cross-domain benchmarks, reaching chemical accuracy in various scenarios including adsorption-energy in catalytic surfaces and metal–organic frameworks. SevenNet-Omni also accurately reproduces high-fidelity properties by effectively transferring knowledge learned from larger, lower-accuracy databases. This framework offers a scalable route toward universal, transferable models that bridge quantum-mechanical fidelities and chemical domains. This work presents a machine-learning approach that optimizes the learning of atomic interactions across diverse materials. By integrating heterogeneous data, it delivers accurate and transferable predictions beyond its training domain.
Keywords:
Atomistic models
Computational methods
Method development
Science
Humanities and Social Sciences
multidisciplinary
Journal
IF:
15.7
Papers:
9.3W
Citations:
91.2W
Organization
Cited Papers
E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAIShareSaveData-Efficient Multifidelity Training for High-Fidelity Machine Learning Interatomic Potentials
PREAI
ShareSaveAb initio study of solute transition-metal interactions with point defects in bcc FePHYSICAL REVIEW BOAAI
PHYSICAL REVIEW BIF3.7
OAAIShareSaveShareSaveFrom Data to Discovery: Recent Trends of Machine Learning in Metal-Organic FrameworksJACS AUOAAI
JACS AUIF8.7
OAAIShareSaveShareSave
View more