Synthetic pre-training for neural-network interatomic potentials

Journal article

Machine-learned force fields have transformed the atomistic modelling of materials by enabling simulations of ab initio quality on unprecedented time and length scales. However, they are currently limited by: (i) the significant computational and human effort that must go into development and validation of potentials for each particular system of interest; and (ii) a general lack of transferability from one chemical system to the next. Here, using the state-of-the-art MACE architecture we introduce a single general-purpose ML model, trained on a public database of 150k inorganic crystals, that is capable of running stable molecular dynamics on molecules and materials. We demonstrate the power of the MACE-MP-0 model - and its qualitative and at times quantitative accuracy - on a diverse set problems in the physical sciences, including the properties of solids, liquids, gases, chemical reactions, interfaces and even the dynamics of a small protein. The model can be applied out of the box and as a starting or "foundation model" for any atomistic system of interest and is thus a step towards democratising the revolution of ML force fields by lowering the barriers to entry.Comment: 119 pages, 63 figures, 37MB PD

Authors: Gardner, JLA; Baker, KT; Deringer, VL

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IOP Publishing
• Journal: Machine Learning: Science and Technology
• Volume: 5
• Issue: 1
• Pages: 015003-015003
• Publication date: 2023-12-15
• DOI: 10.1088/2632-2153/ad1626
• EISSN: 2632-2153
• ISSN: 2632-2153
• Language: English
• Keywords: Quantum; Physics; Training (meteorology); Molecular dynamics; Theoretical computer science; Training set; Task (project management); Interatomic potential; Chemistry; Artificial neural network; Computational chemistry; Stability (learning theory); Machine learning; Computer science; Artificial intelligence; Graph