English
Related papers

Related papers: Scalable Autoregressive Deep Surrogates for Dendri…

200 papers

Accurate yet efficient surrogate models are essential for large-scale simulations of partial differential equations (PDEs), particularly for uncertainty quantification (UQ) tasks that demand hundreds or thousands of evaluations. We develop…

Mesh-based numerical solvers are an important part in many design tool chains. However, accurate simulations like computational fluid dynamics are time and resource consuming which is why surrogate models are employed to speed-up the…

Machine Learning · Computer Science 2023-07-27 Sebastian Strönisch , Maximilian Sander , Andreas Knüpfer , Marcus Meyer

It is not uncommon that meta-heuristic algorithms contain some intrinsic parameters, the optimal configuration of which is crucial for achieving their peak performance. However, evaluating the effectiveness of a configuration is expensive,…

Neural and Evolutionary Computing · Computer Science 2019-02-01 Ke Li , Zilin Xiang , Kay Chen Tan

Phase-field models of microstructural pattern formation during alloy solidification are commonly solved numerically using the finite-difference method, which is ideally suited to carry out computationally efficient simulations on massively…

Materials Science · Physics 2022-02-17 Kaihua Ji , Amirhossein Molavi Tabrizi , Alain Karma

Recent advancements in Markov chain Monte Carlo (MCMC) sampling and surrogate modelling have significantly enhanced the feasibility of Bayesian analysis across engineering fields. However, the selection and integration of surrogate models…

Computational Physics · Physics 2024-11-22 Leon Riccius , Iuri B. C. M. Rocha , Joris Bierkens , Hanne Kekkonen , Frans P. van der Meer

Distributed energy storage devices can be aggregated to provide operational flexibility for power systems. This requires representing a massive device population as a single, tractable surrogate that is computationally efficient and…

Systems and Control · Electrical Eng. & Systems 2026-04-17 Jingguan Liu , Cong Chen , Xiaomeng Ai , Jiakun Fang , Jinsong Wang , Jinyu Wen

Computational fluid dynamics (CFD) provides high-fidelity simulations of fluid flows but remains computationally expensive for many-query applications. In recent years deep learning (DL) has been used to construct data-driven fluid-dynamic…

Machine Learning · Computer Science 2026-04-13 David Ramos , Lucas Lacasa , Fermín Gutiérrez , Eusebio Valero , Gonzalo Rubio

High-fidelity simulation models are widely used to analyze complex stochastic systems, but their high computational cost motivates the development of cheaper surrogate models that approximate the simulation model's input-output…

Machine Learning · Statistics 2026-05-28 Mohammadmahdi Ghasemloo , David J. Eckman , Yaxian Li

Many subsurface formations, including some of those under consideration for large-scale geological carbon storage, include extensive faults that can strongly impact fluid flow. In this study, we develop a new recurrent transformer U-Net…

Machine Learning · Computer Science 2025-08-26 Yifu Han , Louis J. Durlofsky

Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors. This approach introduces a trade-off between…

Phase-field-based models have become common in material science, mechanics, physics, biology, chemistry, and engineering for the simulation of microstructure evolution. Yet, they suffer from the drawback of being computationally very costly…

Localized deformation patterns are a common motif in morphogenesis and are increasingly finding widespread applications in materials science, for instance as memory devices. Here we describe the emergence of spatially localized deformations…

Soft Condensed Matter · Physics 2019-06-12 Thomas C. T. Michaels , Remy Kusters , Alexander J. Dear , Cornelis Storm , James C. Weaver , L. Mahadevan

Understanding the microstuctural evolution during the sintering process is of high relevance as it is a key part in many industrial manufacturing processes. Simulations are one avenue to achieve this understanding, especially field-resolved…

Materials Science · Physics 2023-05-17 Marco Seiz , Henrik Hierl , Britta Nestler

In this paper, we develop a mean-field model for simulating the microstructure evolution of crystalline materials during static recrystallization. The model considers a population of individual cells (i.e. grains and subgrains) growing in a…

Materials Science · Physics 2020-05-18 Arthur Després , Michael Greenwood , Chad Sinclair

Transitions between distinct dynamical regimes are ubiquitous in nonequilibrium systems. As a prototypical example, deposition growth is often accompanied by irreversible morphological instabilities. Forecasting such transitions from…

Chemical Physics · Physics 2026-02-16 Hyunjun Jang , Chung Bin Park , Jeonghoon Kim , Jeongmin Kim

The effectiveness of machine learning in metallographic microstructure segmentation is often constrained by the lack of human-annotated phase masks, particularly for rare or compositionally complex morphologies within the metal alloy. We…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Hoang Hai Nam Nguyen , Minh Tien Tran , Hoheok Kim , Ho Won Lee

This study addresses ductile fracture of single grains in metals by modeling of the formation and propagation of transgranular cracks. A proposed model integrates gradient extended hardening, phase-field modeling for fracture, and crystal…

Numerical Analysis · Mathematics 2024-11-01 Kim Louisa Auth , Jim Brouzoulis , Magnus Ekh

The large time and length scales and, not least, the vast number of particles involved in industrial-scale simulations inflate the computational costs of the Discrete Element Method (DEM) excessively. Coarse grain models can help to lower…

Computational Physics · Physics 2017-05-11 Daniel Queteschiner , Thomas Lichtenegger , Simon Schneiderbauer , Stefan Pirker

Cellular or dendritic microstructures that result as a function of additive manufacturing solidification conditions in a Ni-based melt pool are simulated in the present work using three-dimensional phase-field simulations. A macroscopic…

Materials Science · Physics 2017-12-29 Supriyo Ghosh , Nana Ofori-Opoku , Jonathan E. Guyer

Materials which can undergo slow diffusive transformations as well as fast displacive transformations are studied using the phase-field method. The model captures the essential features of the time-temperature-transformation (TTT) diagrams,…

Materials Science · Physics 2007-05-23 Mathieu Bouville , Rajeev Ahluwalia
‹ Prev 1 8 9 10 Next ›