Hopkins Extreme Materials Institute(霍普金斯极端材料研究所);Dept. of Civil and Systems Engineering(土木与系统工程系);Johns Hopkins University(约翰·霍普金斯大学);Dept. of Chemical and Biomolecular Engineering(化学与生物分子工程系);Dept. of Applied Mathematics and Statistics(应用数学与统计学系)
Bahador Bahmani, Somdatta Goswami, Ioannis G. Kevrekidis, Michael D. Shields
发表信息:
Journal of Computational Physics, 539, 2025, 114233
The Deep Operator Network (DeepONet) is a powerful neural operator architecture that uses two neural networks to map between infinite-dimensional function spaces. This architecture allows for the evaluation of the solution field at any location within the domain but requires input functions to be discretized at identical locations, limiting practical applications. We introduce a general framework for operator learning from input-output data with arbitrary sensor locations and counts. This begins by introducing a resolution-independent DeepONet (RI-DeepONet), which handles input functions discretized arbitrarily but sufficiently finely. To achieve this, we propose two dictionary learning algorithms that adaptively learn continuous basis functions, parameterized as implicit neural representations (INRs), from correlated signals on arbitrary point clouds. These basis functions project input function data onto a finite-dimensional embedding space, making it compatible with DeepONet without architectural changes. We specifically use sinusoidal representation networks (SIRENs) as trainable INR basis functions. Similarly, the dictionary learning algorithms identify basis functions for output data, defining a new neural operator architecture: the Resolution Independent Neural Operator (RINO). In RINO, the operator learning task reduces to mapping coefficients of input basis functions to output basis functions. We demonstrate RINO's robustness and applicability in handling arbitrarily sampled input and output functions during both training and inference through several numerical examples.
A Physics-informed Multi-resolution Neural Operator
Dept. of Civil and Systems Engineering Johns Hopkins University(土木与系统工程系约翰霍普金斯大学);Dept. of Chemical and Biomolecular Engineering Dept. of Applied Mathematics and Statistics Johns Hopkins University(化学与生物分子工程系应用数学与统计学系约翰霍普金斯大学)
Equilibrium Conserving Neural Operators for Super-Resolution Learning
School of Engineering, Brown University(布朗大学工程学院);Center for Integrated Nanotechnologies, Sandia National Laboratories(沙利文国家实验室集成纳米技术中心);Department of Materials Science and Engineering, Carnegie Mellon University(卡内基梅隆大学材料科学与工程系);Mechanics of Materials Department, Sandia National Laboratories(沙利文国家实验室力学材料系);Division of Applied Mathematics, Brown University(布朗大学应用数学系)
Multi-Resolution Active Learning of Fourier Neural Operators
Kahlert School of Computing, University of Utah(犹他大学卡勒特计算学院);Scientific Computing and Imaging (SCI) Institute, University of Utah(犹他大学科学计算与成像研究所);School of Mathematics and Statistics, University of Sheffield(谢菲尔德大学数学与统计学院)
The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators
University of Chicago(芝加哥大学);Lawrence Berkeley National Laboratory(伯克利国家实验室);University of Stuttgart(斯图加特大学);Dartmouth College(达特茅斯学院);International Computer Science Institute(国际计算机科学研究所);University of California, Berkeley(加州大学伯克利分校)
Multi-Level Monte Carlo Training of Neural Operators
Department of Applied Mathematics and Theoretical Physics, University of Cambridge(应用数学与理论物理系,剑桥大学);Department of Mechanical Engineering, University of Washington(机械工程系,华盛顿大学);Department of Computer Science and Technology, University of Cambridge(计算机科学与技术系,剑桥大学);Department of Mathematics, Imperial College London(数学系,伦敦帝国学院)
M2NO: An Efficient Multi-Resolution Operator Framework for Dynamic Multi-Scale PDE Solvers
The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));The Hong Kong University of Science and Technology(香港科学与技术大学);Southwest Jiaotong University(西南交通大学)
Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling
Mila Quebec AI Institute(米拉魁北克人工智能研究所);New York University(纽约大学);University of Montreal(蒙特利尔大学);Fraunhofer ITWM(弗劳恩霍夫工业数学研究所);IBM Research(IBM研究院);McGill University(麦吉尔大学)
MultiAuto-DeepONet: A Multi-resolution Autoencoder DeepONet for Nonlinear Dimension Reduction, Uncertainty Quantification and Operator Learning of Forward and Inverse Stochastic Problems
Global Stress Generation and Spatiotemporal Super-Resolution Physics-Informed Operator under Dynamic Loading for Two-Phase Random Materials
School of Civil Engineering, Tongji University(同济大学土木工程学院);The State Key Laboratory on Disaster Reduction in Civil Engineering, Tongji University(同济大学土木工程防灾国家重点实验室)