Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.11063 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908895686950912 |
|---|---|
| author | Shinagawa, Chikashi Takamoto, So Shintani, Daiki Zhuang, Yong-Bin Tsuboi, Yuta Nishimra, Katsuhiko Shinohara, Kohei Iwase, Shigeru Tanaka, Yuta Li, Ju |
| author_facet | Shinagawa, Chikashi Takamoto, So Shintani, Daiki Zhuang, Yong-Bin Tsuboi, Yuta Nishimra, Katsuhiko Shinohara, Kohei Iwase, Shigeru Tanaka, Yuta Li, Ju |
| contents | Universal Machine Learning Interatomic Potentials (uMLIPs) enable atomistic simulations and high-throughput screening at scales far beyond those accessible with density functional theory (DFT). However, most existing uMLIPs are trained on Perdew--Burke--Ernzerhof (PBE) generalized gradient approximation (GGA) data and are therefore fundamentally limited by PBE-level accuracy. In this paper, we argue that better zero-shot predictions versus experiments must be an explicit design target for uMLIPs and present PFP v8, a uMLIP available on the Matlantis service that overcomes the inherent limitations of the PBE functional by being trained to reproduce the regularized-restored strongly constrained and appropriately normed (r2SCAN) meta-GGA potential-energy surface across a wide range of chemical domains. Without requiring domain-specific fine-tuning, PFP v8 delivers systematically improved agreement with experimental data or high-accuracy references for crystals, molecules, and surfaces, outperforming PBE-based DFT calculations. Crucially, in long-time molecular dynamics simulations that are computationally impractical with DFT, PFP v8 predicts melting points with an average error of approximately 130 K, halving the error relative to PBE-trained models. These results establish that uMLIPs can move beyond the limitations of their training approximations and achieve substantially improved agreement with experiment across diverse chemical domains, further narrowing the gap between simulation and reality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11063 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Matlantis-PFP v8: Universal Machine Learning Interatomic Potential with Better Experimental Agreements via r2SCAN Functional Shinagawa, Chikashi Takamoto, So Shintani, Daiki Zhuang, Yong-Bin Tsuboi, Yuta Nishimra, Katsuhiko Shinohara, Kohei Iwase, Shigeru Tanaka, Yuta Li, Ju Chemical Physics Materials Science Computational Physics Universal Machine Learning Interatomic Potentials (uMLIPs) enable atomistic simulations and high-throughput screening at scales far beyond those accessible with density functional theory (DFT). However, most existing uMLIPs are trained on Perdew--Burke--Ernzerhof (PBE) generalized gradient approximation (GGA) data and are therefore fundamentally limited by PBE-level accuracy. In this paper, we argue that better zero-shot predictions versus experiments must be an explicit design target for uMLIPs and present PFP v8, a uMLIP available on the Matlantis service that overcomes the inherent limitations of the PBE functional by being trained to reproduce the regularized-restored strongly constrained and appropriately normed (r2SCAN) meta-GGA potential-energy surface across a wide range of chemical domains. Without requiring domain-specific fine-tuning, PFP v8 delivers systematically improved agreement with experimental data or high-accuracy references for crystals, molecules, and surfaces, outperforming PBE-based DFT calculations. Crucially, in long-time molecular dynamics simulations that are computationally impractical with DFT, PFP v8 predicts melting points with an average error of approximately 130 K, halving the error relative to PBE-trained models. These results establish that uMLIPs can move beyond the limitations of their training approximations and achieve substantially improved agreement with experiment across diverse chemical domains, further narrowing the gap between simulation and reality. |
| title | Matlantis-PFP v8: Universal Machine Learning Interatomic Potential with Better Experimental Agreements via r2SCAN Functional |
| topic | Chemical Physics Materials Science Computational Physics |
| url | https://arxiv.org/abs/2603.11063 |