Interpolation and differentiation of alchemical degrees of freedom in machine learning interatomic potentials

• URL: http://arxiv.org/abs/2404.10746v3
• Date: Tue, 03 Dec 2024 09:47:45 GMT
• Title: Interpolation and differentiation of alchemical degrees of freedom in machine learning interatomic potentials
• Authors: Juno Nam, Jiayu Peng, Rafael Gómez-Bombarelli,
• Abstract summary: We report the use of continuous and differentiable alchemical degrees of freedom in atomistic materials simulations.<n>The proposed method introduces alchemical atoms with corresponding weights into the input graph, alongside modifications to the message-passing and readout mechanisms of MLIPs.<n>The end-to-end differentiability of MLIPs enables efficient calculation of the gradient of energy with respect to the compositional weights.
• Score: 0.980222898148295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning interatomic potentials (MLIPs) have become a workhorse of modern atomistic simulations, and recently published universal MLIPs, pre-trained on large datasets, have demonstrated remarkable accuracy and generalizability. However, the computational cost of MLIPs limits their applicability to chemically disordered systems requiring large simulation cells or to sample-intensive statistical methods. Here, we report the use of continuous and differentiable alchemical degrees of freedom in atomistic materials simulations, exploiting the fact that graph neural network MLIPs represent discrete elements as real-valued tensors. The proposed method introduces alchemical atoms with corresponding weights into the input graph, alongside modifications to the message-passing and readout mechanisms of MLIPs, and allows smooth interpolation between the compositional states of materials. The end-to-end differentiability of MLIPs enables efficient calculation of the gradient of energy with respect to the compositional weights. With this modification, we propose methodologies for optimizing the composition of solid solutions towards target macroscopic properties, characterizing order and disorder in multicomponent oxides, and conducting alchemical free energy simulations to quantify the free energy of vacancy formation and composition changes. The approach offers an avenue for extending the capabilities of universal MLIPs in the modeling of compositional disorder and characterizing the phase stability of complex materials systems.

Related papers

• Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution [1.6112718683989882]
  Machine learning interatomic potentials (MLIPs) provide a computationally efficient alternative to quantum mechanical simulations for predicting material properties. We develop a new equivariant MLIP incorporating long-range Coulomb interactions through explicit treatment of electronic degrees of freedom. We systematically evaluate our model across a range of benchmark periodic and non-periodic datasets, demonstrating that it outperforms both short-range equivariant and long-range invariant MLIPs in energy and force predictions.
  arXiv  Detail & Related papers  (2025-03-23T05:26:55Z)
• Ensemble Knowledge Distillation for Machine Learning Interatomic Potentials [34.82692226532414]
  Machine learning interatomic potentials (MLIPs) are a promising tool to accelerate atomistic simulations and molecular property prediction. The quality of MLIPs depends on the quantity of available training data as well as the quantum chemistry (QC) level of theory used to generate that data. We present an ensemble knowledge distillation (EKD) method to improve MLIP accuracy when trained to energy-only datasets.
  arXiv  Detail & Related papers  (2025-03-18T14:32:51Z)
• Efficient and Accurate Spatial Mixing of Machine Learned Interatomic Potentials for Materials Science [0.0]
  Machine-learned interatomic potentials offer near first-principles accuracy but are computationally expensive. We present ML-mix, an efficient and flexible LAMMPS package for accelerating simulations by spatially mixing interatomic potentials. We show it is possible to generate a 'cheap' approximate model which closely matches an 'expensive' reference in relevant regions of configuration space.
  arXiv  Detail & Related papers  (2025-02-26T12:19:39Z)
• Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearity [8.605514384729469]
  We develop a Super-linear MLIP with both Ultra-Small parameterization and greatly expanded expressive capability, named SUS2-MLIP. SUS2-MLIP outperforms the state-of-the-art MLIP models with its exceptional computational efficiency. This work sheds light on incorporating physical constraints into artificial-intelligence-aided materials simulation.
  arXiv  Detail & Related papers  (2025-02-11T06:34:31Z)
• A POD-TANN approach for the multiscale modeling of materials and macroelement derivation in geomechanics [0.0]
  This paper introduces a novel approach that combines Proper Orthogonal Decomposition (POD) with Thermodynamics-based Artificial Neural Networks (TANN) to capture the macroscopic behavior of complex inelastic systems and derive macroelements in geomechanics. The results indicate that the POD-TANN approach not only offers accuracy reproducing in the studied responses, but also reduces computational costs, making it a practical tool for the multiscale modeling of heterogeneous inelastic geomechanical systems.
  arXiv  Detail & Related papers  (2024-08-13T19:08:56Z)
• Differentiable Neural-Integrated Meshfree Method for Forward and Inverse Modeling of Finite Strain Hyperelasticity [1.290382979353427]
  The present study aims to extend the novel physics-informed machine learning approach, specifically the neural-integrated meshfree (NIM) method, to model finite-strain problems. Thanks to the inherent differentiable programming capabilities, NIM can circumvent the need for derivation of Newton-Raphson linearization of the variational form. NIM is applied to identify heterogeneous mechanical properties of hyperelastic materials from strain data, validating its effectiveness in the inverse modeling of nonlinear materials.
  arXiv  Detail & Related papers  (2024-07-15T19:15:18Z)
• Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning [3.321322648845526]
  Machine learning interatomic potentials (MLIPs) have introduced a new paradigm for atomic simulations. Recent advancements have seen the emergence of universal MLIPs (uMLIPs) that are pre-trained on diverse materials datasets. We show that their performance in extrapolating to out-of-distribution complex atomic environments remains unclear.
  arXiv  Detail & Related papers  (2024-05-11T22:30:47Z)
• Active learning of Boltzmann samplers and potential energies with quantum mechanical accuracy [1.7633275579210346]
  We develop an approach combining enhanced sampling with deep generative models and active learning of a machine learning potential. We apply this method to study the isomerization of an ultrasmall silver nanocluster, belonging to a set of systems with diverse applications in the fields of medicine and biology.
  arXiv  Detail & Related papers  (2024-01-29T19:01:31Z)
• Electronic excited states from physically-constrained machine learning [0.0]
  We present an integrated modeling approach, in which a symmetry-adapted ML model of an effective Hamiltonian is trained to reproduce electronic excitations from a quantum-mechanical calculation. The resulting model can make predictions for molecules that are much larger and more complex than those that it is trained on.
  arXiv  Detail & Related papers  (2023-11-01T20:49:59Z)
• Discovering Interpretable Physical Models using Symbolic Regression and Discrete Exterior Calculus [55.2480439325792]
  We propose a framework that combines Symbolic Regression (SR) and Discrete Exterior Calculus (DEC) for the automated discovery of physical models. DEC provides building blocks for the discrete analogue of field theories, which are beyond the state-of-the-art applications of SR to physical problems. We prove the effectiveness of our methodology by re-discovering three models of Continuum Physics from synthetic experimental data.
  arXiv  Detail & Related papers  (2023-10-10T13:23:05Z)
• 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)
• A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures [68.8204255655161]
  It is shown that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches. It is shown, that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches.
  arXiv  Detail & Related papers  (2021-10-26T07:02:14Z)
• Hybridized Methods for Quantum Simulation in the Interaction Picture [69.02115180674885]
  We provide a framework that allows different simulation methods to be hybridized and thereby improve performance for interaction picture simulations. Physical applications of these hybridized methods yield a gate complexity scaling as $log2 Lambda$ in the electric cutoff. For the general problem of Hamiltonian simulation subject to dynamical constraints, these methods yield a query complexity independent of the penalty parameter $lambda$ used to impose an energy cost.
  arXiv  Detail & Related papers  (2021-09-07T20:01:22Z)
• Quantum-Classical Hybrid Algorithm for the Simulation of All-Electron Correlation [58.720142291102135]
  We present a novel hybrid-classical algorithm that computes a molecule's all-electron energy and properties on the classical computer. We demonstrate the ability of the quantum-classical hybrid algorithms to achieve chemically relevant results and accuracy on currently available quantum computers.
  arXiv  Detail & Related papers  (2021-06-22T18:00:00Z)
• 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)

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.