中文
相关论文

相关论文: Towards General Neural Surrogate Solvers with Spec…

200 篇论文

Simulation is a powerful tool to better understand physical systems, but generally requires computationally expensive numerical methods. Downstream applications of such simulations can become computationally infeasible if they require many…

机器学习 · 计算机科学 2024-07-17 Yoeri Poels , Koen Minartz , Harshit Bansal , Vlado Menkovski

In recent work, Li et al.\ (Comm.\ Math.\ Sci., 7:81-107, 2009) developed a diffuse-domain method (DDM) for solving partial differential equations in complex, dynamic geometries with Dirichlet, Neumann, and Robin boundary conditions. The…

数值分析 · 数学 2015-05-18 Karl Yngve Lervåg , John Lowengrub

The numerical solution of high dimensional partial differential equations (PDEs) is severely constrained by the curse of dimensionality (CoD), rendering classical grid--based methods impractical beyond a few dimensions. In recent years,…

数值分析 · 数学 2026-01-27 Wenzhong Zhang , Zheyuan Hu , Wei Cai , George EM Karniadakis

Accurately solving partial differential equations (PDEs) is critical to understanding complex scientific and engineering phenomena, yet traditional numerical solvers are computationally expensive. Surrogate models offer a more efficient…

机器学习 · 计算机科学 2026-04-17 Yegon Kim , Hyunsu Kim , Gyeonghoon Ko , Juho Lee

Neural network based methods have emerged as a promising paradigm for scientific computing, yet they face critical bottlenecks in high frequency function approximation and partial differential equation (PDE) solving.

数值分析 · 数学 2026-04-06 Xuyang Gao , Liang Chen , Minqiang Xu , Jing Niu

Computational astrochemical models are essential for helping us interpret and understand the observations of different astrophysical environments. In the age of high-resolution telescopes such as JWST and ALMA, the substructure of many…

星系天体物理 · 物理学 2025-06-18 Gijs Vermariën , Thomas G. Bisbas , Serena Viti , Yue Zhao , Xuefei Tang , Rahul Ravichandran

Domain decomposition methods (DDMs) are popular solvers for discretized systems of partial differential equations (PDEs), with one-level and multilevel variants. These solvers rely on several algorithmic and mathematical parameters,…

机器学习 · 计算机科学 2023-03-03 Ali Taghibakhshi , Nicolas Nytko , Tareq Uz Zaman , Scott MacLachlan , Luke Olson , Matthew West

Deep neural networks have recently achieved significant advancements in remote sensing superresolu-tion (SR). However, most existing methods are limited to low magnification rates (e.g., 2 or 4) due to the escalating ill-posedness at higher…

图像与视频处理 · 电气工程与系统科学 2024-12-30 Yue Shi , Liangxiu Han , Darren Dancy , Lianghao Han

The scientific computation methods development in conjunction with artificial intelligence technologies remains a hot research topic. Finding a balance between lightweight and accurate computations is a solid foundation for this direction.…

机器学习 · 计算机科学 2025-07-03 Nikita Sakovich , Dmitry Aksenov , Ekaterina Pleshakova , Sergey Gataullin

Accurate modeling of physical systems governed by partial differential equations is a central challenge in scientific computing. In oceanography, high-resolution current data are critical for coastal management, environmental monitoring,…

机器学习 · 计算机科学 2025-10-21 Abdessamad El-Kabid , Loubna Benabbou , Redouane Lguensat , Alex Hernández-García

Operator learning has emerged as a promising paradigm for developing efficient surrogate models to solve partial differential equations (PDEs). However, existing approaches often overlook the domain knowledge inherent in the underlying PDEs…

机器学习 · 计算机科学 2025-10-20 Ziqian Li , Kang Liu , Yongcun Song , Hangrui Yue , Enrique Zuazua

In this paper, we present a deep learning-based numerical method for approximating high dimensional stochastic partial differential equations (SPDEs). At each time step, our method relies on a predictor-corrector procedure. More precisely,…

数值分析 · 数学 2022-09-13 He Zhang , Ran Zhang , Tao Zhou

We present a novel method for using Neural Networks (NNs) for finding solutions to a class of Partial Differential Equations (PDEs). Our method builds on recent advances in Neural Radiance Field research (NeRFs) and allows for a NN to…

机器学习 · 计算机科学 2022-05-31 Jaroslaw Rzepecki , Daniel Bates , Chris Doran

We propose a neural network-based algorithm for solving forward and inverse problems for partial differential equations in unsupervised fashion. The solution is approximated by a deep neural network which is the minimizer of a cost…

机器学习 · 计算机科学 2019-04-12 Leah Bar , Nir Sochen

Recently, researchers have utilized neural networks to accurately solve partial differential equations (PDEs), enabling the mesh-free method for scientific computation. Unfortunately, the network performance drops when encountering a high…

机器学习 · 计算机科学 2021-09-29 Pongpisit Thanasutives , Masayuki Numao , Ken-ichi Fukui

Solving high-dimensional partial differential equations (PDEs) is a critical challenge where modern data-driven solvers often lack reliability and rigorous error guarantees. We introduce Simulation-Calibrated Scientific Machine Learning…

数值分析 · 数学 2025-12-25 Zexi Fan , Yan Sun , Shihao Yang , Yiping Lu

In this paper, we consider a primal-dual domain decomposition method for total variation regularized problems appearing in mathematical image processing. The model problem is transformed into an equivalent constrained minimization problem…

数值分析 · 数学 2019-12-10 Chang-Ock Lee , Jongho Park

In Bayesian inverse problems, surrogate models are often constructed to speed up the computational procedure, as the parameter-to-data map can be very expensive to evaluate. However, due to the curse of dimensionality and the nonlinear…

数值分析 · 数学 2020-03-03 Liang Yan , Tao Zhou

A classic approach for solving differential equations with neural networks builds upon neural forms, which employ the differential equation with a discretisation of the solution domain. Making use of neural forms for time-dependent…

神经与进化计算 · 计算机科学 2022-09-02 Toni Schneidereit , Michael Breuß

The high computational cost of kinetic solvers such as DSMC remains a major challenge in rarefied flow simulations. This work presents a unified framework combining deep neural networks and neural operators to accelerate kinetic and hybrid…

流体动力学 · 物理学 2025-12-18 Ehsan Roohi