A Spectral Model-Informed Neural Network for Inverse Source Problems

DOI10.48550/arXiv.2609.33062MaRDI QIDQ7365564arXivFDO

Authors Dinh Liem Nguyen, Nhung Hong Nguyen, Aravinth Ravi, Dinh-Liem Nguyen, Nhung H. Nguyen

Publication date 2026

Published in arXiv

Tldr A spectral model-informed neural network for inverse source problems; This paper presents a novel deep learning framework that leverages information extracted from boundary measurements through a Fourier-based model equation to improve the speed, robustness, and accuracy of source function recovery.

Full work available at URL https://doi.org/10.48550/arXiv.2609.33062

arXiv classification

math.NA

Cites work

• A convergent numerical method for a multi-frequency inverse source problem in inhomogenous media
• A Direct Sampling Method and Its Integration with Deep Learning for Inverse Scattering Problems with Phaseless Data
• A factorization method for multifrequency inverse source problems with sparse far field measurements
• A multi-frequency inverse source problem
• A neural network scheme for recovering scattering obstacles with limited phaseless far-field data
• A neural network warm-start approach for the inverse acoustic obstacle scattering problem
• A Recursive Algorithm for MultiFrequency Acoustic Inverse Source Problems
• Acoustic source identification using multiple frequency information
• An algebraic method for identification of dipoles and quadrupoles
• An introduction to the mathematical theory of inverse problems
• An inverse source problem for Helmholtz's equation from the Cauchy data with a single wave number
• Conservative physics-informed neural networks on discrete domains for conservation laws: applications to forward and inverse problems
• Coupling Deep Learning with Full Waveform Inversion
• Deep-plug-and-play proximal Gauss-Newton method with applications to nonlinear, ill-posed inverse problems
• Fast acoustic source imaging using multi-frequency sparse data
• Fourier method for solving the multi-frequency inverse source problem for the Helmholtz equation
• Hidden physics models: machine learning of nonlinear partial differential equations
• Increasing stability in the inverse source problem with many frequencies
• Inverse electromagnetic source scattering problems with multifrequency sparse phased and phaseless far field data
• Lipschitz stability for an inverse source scattering problem at a fixed frequency
• Locating multiple multipolar acoustic sources using the direct sampling method
• On reconstruction of small sources from Cauchy data at a fixed frequency
• On the multi-frequency inverse source problem in heterogeneous media
• PFWNN: A deep learning method for solving forward and inverse problems of phase-field models
• Reconstructing a space-dependent source term via the quasi-reversibility method
• Sampling type method combined with deep learning for inverse scattering with one incident wave
• Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next
• Solving an inverse source problem by deep neural network method with convergence and error analysis
• Solving the wide-band inverse scattering problem via equivariant neural networks
• Stability estimates for an inverse source problem of Helmholtz’s equation from single Cauchy data at a fixed frequency
• SwitchNet: a neural Network Model for forward and inverse scattering problems
• The learned range test method for the inverse inclusion problem
• The learned range test method for the inverse inclusion problem

This page was built for publication: A Spectral Model-Informed Neural Network for Inverse Source Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7365564)