Extreme time extrapolation capabilities and thermodynamic consistency of physics-inspired Neural Networks for the 3D microstructure evolution of materials via Cahn-Hilliard flow

• URL: http://arxiv.org/abs/2407.20126v2
• Date: Wed, 16 Oct 2024 16:20:44 GMT
• Title: Extreme time extrapolation capabilities and thermodynamic consistency of physics-inspired Neural Networks for the 3D microstructure evolution of materials via Cahn-Hilliard flow
• Authors: Daniele Lanzoni, Andrea Fantasia, Roberto Bergamaschini, Olivier Pierre-Louis, Francesco Montalenti,
• Abstract summary: A Convolutional Recurrent Neural Network (CRNN) is trained to reproduce the evolution of the spinodal decomposition process in three dimensions. A specialized, physics-inspired architecture is proven to provide close accordance between the predicted evolutions and the ground truth ones.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A Convolutional Recurrent Neural Network (CRNN) is trained to reproduce the evolution of the spinodal decomposition process in three dimensions as described by the Cahn-Hilliard equation. A specialized, physics-inspired architecture is proven to provide close accordance between the predicted evolutions and the ground truth ones obtained via conventional integration schemes. The method can accurately reproduce the evolution of microstructures not represented in the training set at a fraction of the computational costs. Extremely long-time extrapolation capabilities are achieved, up to reaching the theoretically expected equilibrium state of the system, consisting of a layered, phase-separated morphology, despite the training set containing only relatively-short, initial phases of the evolution. Quantitative accordance with the decay rate of the Free energy is also demonstrated up to the late coarsening stages, proving that this class of Machine Learning approaches can become a new and powerful tool for the long timescale and high throughput simulation of materials, while retaining thermodynamic consistency and high-accuracy.

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)
• Fully Convolutional Spatiotemporal Learning for Microstructure Evolution Prediction [0.5437050212139087]
  Traditional simulation methods are expensive due to the need to solve complex partial differential equations at fine resolutions.<n>We propose a deep learning framework that governs microstructural evolution predictions while maintaining high accuracy.<n>Compared to recurrent neural architectures, our model state-of-the-art predictive performance with significantly reduced computational cost in both training and inference.
  arXiv  Detail & Related papers  (2026-02-23T14:55:28Z)
• SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers [50.18388227899971]
  We present SaDiT, a novel framework that accelerates protein backbone generation by integrating SaProt Tokenization with a Diffusion Transformer (DiT) architecture.<n>Experiments demonstrate that SaDiT outperforms state-of-the-art models, including RFDiffusion and Proteina, in both computational speed and structural viability.
  arXiv  Detail & Related papers  (2026-02-06T13:50:13Z)
• 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)
• Unified machine-learning framework for property prediction and time-evolution simulation of strained alloy microstructure [0.0]
  We introduce a unified machine-learning framework designed to tackle the temporal evolution of alloy microstructures under the influence of an elastic field.<n>This approach allows for the simultaneous extraction of elastic parameters from a short trajectory and for the prediction of further microstructure evolution under their influence.
  arXiv  Detail & Related papers  (2025-07-29T12:43:04Z)
• Models of Heavy-Tailed Mechanistic Universality [62.107333654304014]
  We propose a family of random matrix models to explore attributes that give rise to heavy-tailed behavior in trained neural networks.<n>Under this model, spectral densities with power laws on tails arise through a combination of three independent factors.<n> Implications of our model on other appearances of heavy tails, including neural scaling laws, trajectories, and the five-plus-one phases of neural network training, are discussed.
  arXiv  Detail & Related papers  (2025-06-04T00:55:01Z)
• Recurrent convolutional neural networks for modeling non-adiabatic dynamics of quantum-classical systems [1.23088383881821]
  We present a RNN model based on convolution neural networks for modeling the non-adiabatic dynamics of hybrid quantum-classical systems.<n>We demonstrate that the PARC-CNN architecture can effectively learn the statistical climate of the Holstein model under deep-quench conditions.
  arXiv  Detail & Related papers  (2024-12-09T16:23:25Z)
• Geometric Trajectory Diffusion Models [58.853975433383326]
  Generative models have shown great promise in generating 3D geometric systems. Existing approaches only operate on static structures, neglecting the fact that physical systems are always dynamic in nature. We propose geometric trajectory diffusion models (GeoTDM), the first diffusion model for modeling the temporal distribution of 3D geometric trajectories.
  arXiv  Detail & Related papers  (2024-10-16T20:36:41Z)
• Contrastive Learning in Memristor-based Neuromorphic Systems [55.11642177631929]
  Spiking neural networks have become an important family of neuron-based models that sidestep many of the key limitations facing modern-day backpropagation-trained deep networks. In this work, we design and investigate a proof-of-concept instantiation of contrastive-signal-dependent plasticity (CSDP), a neuromorphic form of forward-forward-based, backpropagation-free learning.
  arXiv  Detail & Related papers  (2024-09-17T04:48:45Z)
• Real-time chiral dynamics at finite temperature from quantum simulation [0.0]
  We explore the real-time dynamics of the chiral magnetic effect (CME) at a finite temperature in the (1+1)-dimensional QED. We employ the quantum imaginary time evolution (QITE) algorithm to study the thermal states, and utilize the Suzuki-Trotter decomposition for the real-time evolution.
  arXiv  Detail & Related papers  (2024-07-31T10:10:42Z)
• Ab-initio variational wave functions for the time-dependent many-electron Schrödinger equation [41.94295877935867]
  We introduce a variational approach for fermionic time-dependent wave functions, surpassing mean-field approximations. We use time-dependent Jastrow factors and backflow transformations, which are enhanced through neural networks parameterizations. The results showcase the ability of our variational approach to accurately capture the time evolution, providing insight into the quantum dynamics of interacting electronic systems.
  arXiv  Detail & Related papers  (2024-03-12T09:37:22Z)
• Towards Predicting Equilibrium Distributions for Molecular Systems with Deep Learning [60.02391969049972]
  We introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems. DiG employs deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system.
  arXiv  Detail & Related papers  (2023-06-08T17:12:08Z)
• Predictive Scale-Bridging Simulations through Active Learning [43.48102250786867]
  We use an active learning approach to optimize the use of local fine-scale simulations for informing coarse-scale hydrodynamics. Our approach addresses three challenges: forecasting continuum coarse-scale trajectory, dynamically updating coarse-scale from fine-scale calculations, and quantifying uncertainty in neural network models.
  arXiv  Detail & Related papers  (2022-09-20T15:58:50Z)
• Entanglement and correlations in fast collective neutrino flavor oscillations [68.8204255655161]
  Collective neutrino oscillations play a crucial role in transporting lepton flavor in astrophysical settings. We study the full out-of-equilibrium flavor dynamics in simple multi-angle geometries displaying fast oscillations. We present evidence that these fast collective modes are generated by the same dynamical phase transition.
  arXiv  Detail & Related papers  (2022-03-05T17:00:06Z)
• 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)
• Enhancement of quantum correlations and geometric phase for a driven bipartite quantum system in a structured environment [77.34726150561087]
  We study the role of driving in an initial maximally entangled state evolving under a structured environment. This knowledge can aid the search for physical setups that best retain quantum properties under dissipative dynamics.
  arXiv  Detail & Related papers  (2021-03-18T21:11:37Z)
• SE(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials [0.17590081165362778]
  NequIP is a SE(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations. The method achieves state-of-the-art accuracy on a challenging set of diverse molecules and materials while exhibiting remarkable data efficiency.
  arXiv  Detail & Related papers  (2021-01-08T18:49:10Z)
• Uncertainty estimation for molecular dynamics and sampling [0.0]
  Machine learning models have emerged as a very effective strategy to sidestep time-consuming electronic-structure calculations. It is crucial to obtain an estimate of the error that derives from the finite number of reference structures included during the training of the model. We present examples covering different types of structural and thermodynamic properties, and systems as diverse as water and liquid gallium.
  arXiv  Detail & Related papers  (2020-11-10T00:07:50Z)
• Sobolev training of thermodynamic-informed neural networks for smoothed elasto-plasticity models with level set hardening [0.0]
  We introduce a deep learning framework designed to train smoothed elastoplasticity models with interpretable components. By recasting the yield function as an evolving level set, we introduce a machine learning approach to predict the solutions of the Hamilton-Jacobi equation.
  arXiv  Detail & Related papers  (2020-10-15T22:43:32Z)
• Molecular Latent Space Simulators [8.274472944075713]
  We propose latent space simulators (LSS) to learn kinetic models for continuous all-atom simulation trajectories. We demonstrate the approach in an application to Trp-protein to produce novel ultra-long synthetic folding trajectories.
  arXiv  Detail & Related papers  (2020-07-01T20:05:27Z)

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.