Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials

• URL: http://arxiv.org/abs/2410.01464v4
• Date: Fri, 17 Oct 2025 22:34:26 GMT
• Title: Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials
• Authors: Juno Nam, Sulin Liu, Gavin Winter, KyuJung Jun, Soojung Yang, Rafael Gómez-Bombarelli,
• Abstract summary: Atomic transport underpins the performance of materials in technologies such as energy storage and electronics.<n>We introduce LiFlow, a generative framework to accelerate MD simulations for crystalline materials.<n>We benchmark LiFlow on a dataset comprising 25-ps trajectories of lithium diffusion across 4,186 SSE candidates at four temperatures.
• Score: 6.6716708904054896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Atomic transport underpins the performance of materials in technologies such as energy storage and electronics, yet its simulation remains computationally demanding. In particular, modeling ionic diffusion in solid-state electrolytes (SSEs) requires methods that can overcome the scale limitations of traditional ab initio molecular dynamics (AIMD). We introduce LiFlow, a generative framework to accelerate MD simulations for crystalline materials that formulates the task as conditional generation of atomic displacements. The model uses flow matching, with a Propagator submodel to generate atomic displacements and a Corrector to locally correct unphysical geometries, and incorporates an adaptive prior based on the Maxwell-Boltzmann distribution to account for chemical and thermal conditions. We benchmark LiFlow on a dataset comprising 25-ps trajectories of lithium diffusion across 4,186 SSE candidates at four temperatures. The model obtains a consistent Spearman rank correlation of 0.7-0.8 for lithium mean squared displacement (MSD) predictions on unseen compositions. Furthermore, LiFlow generalizes from short training trajectories to larger supercells and longer simulations while maintaining high accuracy. With speed-ups of up to 600,000$\times$ compared to first-principles methods, LiFlow enables scalable simulations at significantly larger length and time scales.

Related papers

• Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials [51.342983349686556]
  General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities.<n>We introduce Zatom-1, the first end-to-end, fully open-source foundation model that unifies generative and predictive learning of 3D molecules and materials.
  arXiv  Detail & Related papers  (2026-02-24T20:52:39Z)
• Atomistic Simulation Guided Convolutional Neural Networks for Thermal Modeling of Friction Stir Welding [0.33842793760651557]
  Molecular dynamics simulations were performed using LAMMPS to model aluminum friction stir welding at the atomic scale.<n>A two-dimensional convolutional neural network was developed to predict temperature directly from the spatially resolved atomistic data.
  arXiv  Detail & Related papers  (2025-12-15T16:41:42Z)
• Efficient Exploration of Chemical Kinetics [0.0]
  Estimating reaction rates and chemical stability is fundamental, yet efficient methods for large-scale simulations remain out of reach.<n>This dissertation presents a holistic solution, co-designing physical representations, statistical models, and systems architecture in the Optimal Transport Gaussian Process framework.
  arXiv  Detail & Related papers  (2025-10-24T11:52:08Z)
• Machine Learning-Integrated Hybrid Fluid-Kinetic Framework for Quantum Electrodynamic Laser Plasma Simulations [0.0]
  The research introduces a machine learning-based three-dimensional hybrid fluid-particle-in-cell (PIC) system.<n>The technique employs fluid approximations for stable areas but activates the PIC solver when SwitchNet directs it to unstable sections.<n>The model produces precise predictions with coefficient of determination (R2) values above 0.95 and mean squared errors below 10-4 for all field components.
  arXiv  Detail & Related papers  (2025-10-13T09:07:59Z)
• Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models [52.74448905289362]
  EqM is a generative modeling framework built from an equilibrium dynamics perspective.<n>By replacing time-conditional velocities with a unified equilibrium landscape, EqM offers a tighter bridge between flow and energy-based models.
  arXiv  Detail & Related papers  (2025-10-02T17:59:06Z)
• Universal Machine Learning Interatomic Potentials are Ready for Solid Ion Conductors [4.7376603774180515]
  Universal machine learning interatomic potentials (uMLIPs) offer a promising solution with their efficiency and near-DFT-level accuracy.<n>This study systematically evaluates six advanced uMLIP models in terms of energy, forces, thermodynamic properties, elastic moduli, and lithium-ion diffusion behavior.<n>The results show that MatterSim outperforms others in nearly all metrics, particularly in complex material systems.
  arXiv  Detail & Related papers  (2025-02-14T07:55:53Z)
• EquiFlow: Equivariant Conditional Flow Matching with Optimal Transport for 3D Molecular Conformation Prediction [14.664189950787739]
  We propose EquiFlow, an equivariant conditional flow matching model with optimal transport. It uses a modified Equiformer model to encode molecular conformations along with their atomic and bond properties into higher-degree embeddings. Experiments on the QM9 dataset show that EquiFlow predicts small molecule conformations more accurately than current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-12-15T06:48:22Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space. For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets. For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• Predicting ionic conductivity in solids from the machine-learned potential energy landscape [68.25662704255433]
  Superionic materials are essential for advancing solid-state batteries, which offer improved energy density and safety. Conventional computational methods for identifying such materials are resource-intensive and not easily scalable. We propose an approach for the quick and reliable evaluation of ionic conductivity through the analysis of a universal interatomic potential.
  arXiv  Detail & Related papers  (2024-11-11T09:01:36Z)
• Improving and generalizing flow-based generative models with minibatch optimal transport [90.01613198337833]
  We introduce the generalized conditional flow matching (CFM) technique for continuous normalizing flows (CNFs) CFM features a stable regression objective like that used to train the flow in diffusion models but enjoys the efficient inference of deterministic flow models. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference.
  arXiv  Detail & Related papers  (2023-02-01T14:47:17Z)
• Adaptive physics-informed neural operator for coarse-grained non-equilibrium flows [0.0]
  The framework combines dimensionality reduction and neural operators through a hierarchical and adaptive deep learning strategy. The proposed surrogate's architecture is structured as a tree, with leaf nodes representing separate neural operator blocks. In 0-D scenarios, the proposed ML framework can adaptively predict the dynamics of almost thirty species with a maximum relative error of 4.5%.
  arXiv  Detail & Related papers  (2022-10-27T23:26:57Z)
• Manifold Interpolating Optimal-Transport Flows for Trajectory Inference [64.94020639760026]
  We present a method called Manifold Interpolating Optimal-Transport Flow (MIOFlow) MIOFlow learns, continuous population dynamics from static snapshot samples taken at sporadic timepoints. We evaluate our method on simulated data with bifurcations and merges, as well as scRNA-seq data from embryoid body differentiation, and acute myeloid leukemia treatment.
  arXiv  Detail & Related papers  (2022-06-29T22:19:03Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Constructing Sub-scale Surrogate Model for Proppant Settling in Inclined Fractures from Simulation Data with Multi-fidelity Neural Network [1.045294624175056]
  Particle settling in inclined channels is an important phenomenon that occurs during hydraulic fracturing of shale gas production. In this work, a new method is proposed and utilized, i.e., the multi-fidelity neural network (MFNN), to construct a settling surrogate model. The results demonstrate that constructing the settling surrogate with the MFNN can reduce the need for high-fidelity data and thus computational cost by 80%. This opens novel pathways for rapidly predicting proppant settling velocity in reservoir applications.
  arXiv  Detail & Related papers  (2021-09-25T08:31:33Z)
• Physics-informed CoKriging model of a redox flow battery [68.8204255655161]
  Redox flow batteries (RFBs) offer the capability to store large amounts of energy cheaply and efficiently. There is a need for fast and accurate models of the charge-discharge curve of a RFB to potentially improve the battery capacity and performance. We develop a multifidelity model for predicting the charge-discharge curve of a RFB.
  arXiv  Detail & Related papers  (2021-06-17T00:49:55Z)
• 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)
• Li$_x$CoO$_2$ phase stability studied by machine learning-enabled scale bridging between electronic structure, statistical mechanics and phase field theories [0.0]
  Li$_xTM$O$$$ (TM=Ni, Co, Mn) are promising cathodes for Li-ion batteries, whose electrochemical cycling performance is strongly governed by crystal structure and phase stability as a function of Li content at the atomistic scale. Here, we use Li$_x$CoO$$ (LCO) as a model system to benchmark a scale-bridging framework that combines density functional theory calculations at the atomistic scale with phase field modeling at the continuum scale.
  arXiv  Detail & Related papers  (2021-04-16T19:00:59Z)
• ML-LBM: Machine Learning Aided Flow Simulation in Porous Media [0.0]
  Direct simulation of fluid flow in porous media requires significant computational resources to solve within reasonable timeframes. An integrated method combining predictions of fluid flow with direct flow simulation is outlined. Deep Learning techniques based on Convolutional Neural Networks (CNNs) are shown to give an accurate estimate of the steady state velocity fields.
  arXiv  Detail & Related papers  (2020-04-22T01:55:59Z)
• Automated discovery of a robust interatomic potential for aluminum [4.6028828826414925]
  Machine learning (ML) based potentials aim for faithful emulation of quantum mechanics (QM) calculations at drastically reduced computational cost. We present a highly automated approach to dataset construction using the principles of active learning (AL) We demonstrate this approach by building an ML potential for aluminum (ANI-Al) To demonstrate transferability, we perform a 1.3M atom shock simulation, and show that ANI-Al predictions agree very well with DFT calculations on local atomic environments sampled from the nonequilibrium dynamics.
  arXiv  Detail & Related papers  (2020-03-10T19:06:32Z)

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.