Latent Ewald summation for machine learning of long-range interactions

• URL: http://arxiv.org/abs/2408.15165v2
• Date: Thu, 19 Dec 2024 17:11:11 GMT
• Title: Latent Ewald summation for machine learning of long-range interactions
• Authors: Bingqing Cheng,
• Abstract summary: We introduce a straightforward and efficient method to account for long-range interactions by learning a latent variable from local atomic descriptors. We demonstrate that in systems including charged and polar molecular dimers, bulk water, and water-vapor interface, standard short-ranged MLIPs can lead to unphysical predictions. The long-range models effectively eliminate these artifacts, with only about twice the computational cost of short-range MLIPs.
• Score: 0.0
• License:
• Abstract: Machine learning interatomic potentials (MLIPs) often neglect long-range interactions, such as electrostatic and dispersion forces. In this work, we introduce a straightforward and efficient method to account for long-range interactions by learning a latent variable from local atomic descriptors and applying an Ewald summation to this variable. We demonstrate that in systems including charged and polar molecular dimers, bulk water, and water-vapor interface, standard short-ranged MLIPs can lead to unphysical predictions even when employing message passing. The long-range models effectively eliminate these artifacts, with only about twice the computational cost of short-range MLIPs.

Related papers

• Out-of-time-order correlator computation based on discrete truncated Wigner approximation [4.604003661048267]
  We propose a method based on the discrete truncated Wigner approximation (DTWA) for computing out-of-time-order correlators. This work provides a new technique to study scrambling dynamics in long-range interacting quantum spin systems.
  arXiv  Detail & Related papers  (2025-01-24T03:55:12Z)
• Learning charges and long-range interactions from energies and forces [3.502816712907136]
  We introduce the Latent Ewald Summation method, which captures long-range electrostatics without explicitly learning atomic charges or charge equilibration. We benchmark LES on diverse and challenging systems, including charged molecules, ionic liquid, electrolyte solution, polar dipeptides, surface adsorber, electrolyte/solid interfaces, and solid-solid interfaces. Our results show that LES can effectively infer physical partial charges, dipole and quadrupole moments, as well as achieve better accuracy compared to methods that explicitly learn charges.
  arXiv  Detail & Related papers  (2024-12-19T23:24:44Z)
• Electron-Electron Interactions in Device Simulation via Non-equilibrium Green's Functions and the GW Approximation [71.63026504030766]
  electron-electron (e-e) interactions must be explicitly incorporated in quantum transport simulation. This study is the first one reporting large-scale atomistic quantum transport simulations of nano-devices under non-equilibrium conditions.
  arXiv  Detail & Related papers  (2024-12-17T15:05:33Z)
• Learning Interatomic Potentials at Multiple Scales [1.2162698943818964]
  The need to use a short time step is a key limit on the speed of molecular dynamics (MD) simulations. This work introduces a method to learn a scale separation in complex interatomic interactions by co-training two MLIPs.
  arXiv  Detail & Related papers  (2023-10-20T18:34:32Z)
• 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)
• Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations [51.68332623405432]
  Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes. Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations. This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations.
  arXiv  Detail & Related papers  (2022-05-17T13:08:28Z)
• Tuning long-range fermion-mediated interactions in cold-atom quantum simulators [68.8204255655161]
  Engineering long-range interactions in cold-atom quantum simulators can lead to exotic quantum many-body behavior. Here, we propose several tuning knobs, accessible in current experimental platforms, that allow to further control the range and shape of the mediated interactions.
  arXiv  Detail & Related papers  (2022-03-31T13:32:12Z)
• BIGDML: Towards Exact Machine Learning Force Fields for Materials [55.944221055171276]
  Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 atoms.
  arXiv  Detail & Related papers  (2021-06-08T10:14:57Z)
• Controlled coherent dynamics of [VO(TPP)], a prototype molecular nuclear qudit with an electronic ancilla [50.002949299918136]
  We show that [VO(TPP)] (vanadyl tetraphenylporphyrinate) is a promising system suitable to implement quantum computation algorithms. It embeds an electronic spin 1/2 coupled through hyperfine interaction to a nuclear spin 7/2, both characterized by remarkable coherence.
  arXiv  Detail & Related papers  (2021-03-15T21:38:41Z)
• A Universal Framework for Featurization of Atomistic Systems [0.0]
  Reactive force fields based on physics or machine learning can be used to bridge the gap in time and length scales. We introduce the Gaussian multi-pole (GMP) featurization scheme that utilizes physically-relevant multi-pole expansions of the electron density around atoms. We demonstrate that GMP-based models can achieve chemical accuracy for the QM9 dataset, and their accuracy remains reasonable even when extrapolating to new elements.
  arXiv  Detail & Related papers  (2021-02-04T03:11:00Z)
• Data-Driven Discovery of Molecular Photoswitches with Multioutput Gaussian Processes [51.17758371472664]
  Photoswitchable molecules display two or more isomeric forms that may be accessed using light. We present a data-driven discovery pipeline for molecular photoswitches underpinned by dataset curation and multitask learning. We validate our proposed approach experimentally by screening a library of commercially available photoswitchable molecules.
  arXiv  Detail & Related papers  (2020-06-28T20:59:03Z)

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.