Design Space of Self--Consistent Electrostatic Machine Learning Interatomic Potentials

• URL: http://arxiv.org/abs/2603.14700v1
• Date: Mon, 16 Mar 2026 01:16:08 GMT
• Title: Design Space of Self--Consistent Electrostatic Machine Learning Interatomic Potentials
• Abstract summary: We present a framework for treating electrostatics in machine learning interatomic potentials (MLIPs)<n>We identify key design choices that define a broader design space of self-consistent electrostatic MLIPs.<n>Our results demonstrate how more expressive self-consistent models are needed to resolve failures.
• Score: 3.9364243535886985
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning interatomic potentials (MLIPs) have become widely used tools in atomistic simulations. For much of the history of this field, the most commonly employed architectures were based on short-ranged atomic energy contributions, and the assumption of locality still persists in many modern foundation models. While this approach has enabled efficient and accurate modelling for many use cases, it poses intrinsic limitations for systems where long-range electrostatics, charge transfer, or induced polarization play a central role. A growing body of work has proposed extensions that incorporate electrostatic effects, ranging from locally predicted atomic charges to self-consistent models. While these models have demonstrated success for specific examples, their underlying assumptions, and fundamental limitations are not yet well understood. In this work, we present a framework for treating electrostatics in MLIPs by viewing existing models as coarse-grained approximations to density functional theory (DFT). This perspective makes explicit the approximations involved, clarifies the physical meaning of the learned quantities, and reveals connections and equivalences between several previously proposed models. Using this formalism, we identify key design choices that define a broader design space of self-consistent electrostatic MLIPs. We implement salient points in this space using the MACE architecture and a shared representation of the charge density, enabling controlled comparisons between different approaches. Finally, we evaluate these models on two instructive test cases: metal-water interfaces, which probe the contrasting electrostatic response of conducting and insulating systems, and charged vacancies in silicon dioxide. Our results highlight the limitations of existing approaches and demonstrate how more expressive self-consistent models are needed to resolve failures.

Related papers

• Foundation Models for Discovery and Exploration in Chemical Space [57.97784111110166]
  MIST is a family of molecular foundation models trained on large unlabeled datasets.<n>We demonstrate the ability of these models to solve real-world problems across chemical space.
  arXiv  Detail & Related papers  (2025-10-20T17:56:01Z)
• Multi-Photon Quantum Rabi Models with Center-of-Mass Motion [45.73541813564926]
  We introduce a rigorous, second-quantized framework for describing multi-$Lambda$-atoms in a cavity.<n>A key feature of our approach is the systematic application of a Hamiltonian averaging theory to the atomic field operators.<n>A significant finding is the emergence of a particle-particle interaction mediated by ancillary states.
  arXiv  Detail & Related papers  (2025-07-07T09:50:48Z)
• Modeling Membrane Degradation in PEM Electrolyzers with Physics-Informed Neural Networks [45.32169712547367]
  Proton exchange membrane (PEM) electrolyzers are pivotal for sustainable hydrogen production.<n>Their long-term performance is hindered by membrane degradation, which poses reliability and safety challenges.<n>Traditional physics-based models have been developed, offering interpretability but requiring numerous parameters that are often difficult to measure and calibrate.<n>This study presents the first application of Physics-Informed Neural Networks (PINNs) to model membrane degradation in PEM electrolyzers.
  arXiv  Detail & Related papers  (2025-06-19T15:46:49Z)
• Nonlinear Model Order Reduction of Dynamical Systems in Process Engineering: Review and Comparison [50.0791489606211]
  We review state-of-the-art nonlinear model order reduction methods.<n>We discuss both general-purpose methods and tailored approaches for (chemical) process systems.
  arXiv  Detail & Related papers  (2025-06-15T11:39:12Z)
• Interaction Field Matching: Overcoming Limitations of Electrostatic Models [85.87349969357068]
  Electrostatic field matching (EFM) has recently appeared as a physics-inspired paradigm for data generation and transfer using the idea of an electric capacitor.<n>We propose Interaction Field Matching (IFM), a generalization of EFM which allows using general interaction fields beyond the electrostatic one.<n>We show the performance on a series of toy and image data transfer problems.
  arXiv  Detail & Related papers  (2025-06-03T14:45:14Z)
• Are Foundational Atomistic Models Reliable for Finite-Temperature Molecular Dynamics? [5.017458218949553]
  Machine learning force fields have emerged as promising tools for molecular dynamics (MD) simulations.<n>This Perspective adopts a practitioner's viewpoint to ask a critical question: Are these foundational atomistic models reliable for one of their most compelling applications?
  arXiv  Detail & Related papers  (2025-03-11T09:23:01Z)
• A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators [46.348283638884425]
  We propose a two-step unsupervised deep learning framework named as Latent Autoregressive Recurrent Model (CLARM) for learning dynamics of charged particles in accelerators. The CLARM can generate projections at various accelerator sampling modules by capturing and decoding the latent space representation. The results demonstrate that the generative and forecasting ability of the proposed approach is promising when tested against a variety of evaluation metrics.
  arXiv  Detail & Related papers  (2024-03-19T22:05:17Z)
• Deciphering diffuse scattering with machine learning and the equivariant foundation model: The case of molten FeO [5.643890195191516]
  Bridging the gap between diffuse x-ray or neutron scattering measurements and predicted structures from atom-atom pair potentials in disordered materials has been a longstanding challenge in condensed matter physics. The use of machine learned interatomic potentials has grown in the past few years, and has been particularly successful in the cases of ionic and oxide systems. Here we leverage MACE-MP-0; a newly introduced equivariant foundation model and validate the results against high-quality experimental scattering data for the case of molten iron(II) oxide (FeO)
  arXiv  Detail & Related papers  (2024-03-01T03:50:03Z)
• The Role of Reference Points in Machine-Learned Atomistic Simulation Models [0.0]
  Chemical Environment Modeling Theory (CEMT) is designed to overcome the limitations inherent in traditional atom-centered Machine Learning Force Field (MLFF) models. It allows the leveraging of spatially-resolved energy densities and charge densities from FE-DFT calculations.
  arXiv  Detail & Related papers  (2023-10-28T01:02:14Z)
• Physics-inspired Equivariant Descriptors of Non-bonded Interactions [0.0]
  We present an extension of the long distance equivariant (LODE) framework that can handle diverse LR interactions in a consistent way. We provide a direct physical interpretation of these using the multipole expansion which allows for simpler and more efficient implementations.
  arXiv  Detail & Related papers  (2023-08-25T07:04:16Z)
• Two dimensional momentum state lattices [0.0]
  Building on the development of momentum state lattices (MSLs) over the past decade, we introduce a simple extension of this technique to higher dimensions. MSLs have enabled the realization of tight-binding models with tunable disorder, gauge fields, non-Hermiticity, and other features. We discuss many of the direct extensions to this model, including the introduction of disorder and non-Hermiticity, which will enable the exploration of new transport and localization phenomena in higher dimensions.
  arXiv  Detail & Related papers  (2023-05-29T09:57:56Z)
• Multi-scale approach for the prediction of atomic scale properties [0.0]
  Locality underlies machine-learning schemes that predict quantum mechanical observables. One of the main shortcomings of these approaches is their inability to capture physical effects. We show how to build a multi-scale scheme that combines in the same framework local and non-local information.
  arXiv  Detail & Related papers  (2020-08-27T14:01:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.