Preprint · 2025 · Open access

Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials

Santiago Miret, Kin Long Kelvin Lee, Carmelo Gonzales, Sajid Mannan, N. M. Anoop Krishnan

arXiv (Cornell University) · Published 5 February 2025 · DOI 10.48550/arxiv.2502.03660

Open PDFView at the publisherCite this paper

In brief

“Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials” is a 2025 preprint by Santiago Miret and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 12 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
12
Most cited in
2026 (7)
References
102
Authors
5

Abstract

Universal Machine Learning Interactomic Potentials (MLIPs) enable accelerated simulations for materials discovery. However, current research efforts fail to impactfully utilize MLIPs due to: 1. Overreliance on Density Functional Theory (DFT) for MLIP training data creation; 2. MLIPs' inability to reliably and accurately perform large-scale molecular dynamics (MD) simulations for diverse materials; 3. Limited understanding of MLIPs' underlying capabilities. To address these shortcomings, we aargue that MLIP research efforts should prioritize: 1. Employing more accurate simulation methods for large-scale MLIP training data creation (e.g. Coupled Cluster Theory) that cover a wide range of materials design spaces; 2. Creating MLIP metrology tools that leverage large-scale benchmarking, visualization, and interpretability analyses to provide a deeper understanding of MLIPs' inner workings; 3. Developing computationally efficient MLIPs to execute MD simulations that accurately model a broad set of materials properties. Together, these interdisciplinary research directions can help further the real-world application of MLIPs to accurately model complex materials at device scale.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Miret, S., Lee, K. L. K., Gonzales, C., Mannan, S., & Krishnan, N. M. A. (2025). Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2502.03660

MLA 9

Miret, Santiago, et al. “Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2502.03660.

Chicago

Miret, Santiago, Kin Long Kelvin Lee, Carmelo Gonzales, Sajid Mannan, and N. M. Anoop Krishnan. 2025. “Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2502.03660.

Harvard

Miret, S. et al. (2025) ‘Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials’, arXiv (Cornell University). doi:10.48550/arxiv.2502.03660.

IEEE

S. Miret, K. L. K. Lee, C. Gonzales, S. Mannan, and N. M. A. Krishnan, “Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2502.03660.

BibTeX

@misc{miret2025energy,
  title     = {{Energy \& Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials}},
  author    = {Miret, Santiago and Lee, Kin Long Kelvin and Gonzales, Carmelo and Mannan, Sajid and Krishnan, N. M. Anoop},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2502.03660},
  url       = {https://doi.org/10.48550/arxiv.2502.03660}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science

  • machine learning interatomic potentials
  • coupled-cluster theory
  • training data generation
  • large-scale molecular dynamics
  • interpretability
  • computational efficiency
  • materials discovery

Work with this paper

Most-cited papers in Materials Science

All highly cited Materials Science papers

Questions about this paper

How do I cite this paper in APA style?

Miret, S., Lee, K. L. K., Gonzales, C., Mannan, S., & Krishnan, N. M. A. (2025). Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2502.03660

How many times has this paper been cited?

12 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Santiago Miret, Kin Long Kelvin Lee, Carmelo Gonzales, Sajid Mannan, N. M. Anoop Krishnan.

What is the DOI of this paper?

10.48550/arxiv.2502.03660, permanently at https://doi.org/10.48550/arxiv.2502.03660. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.