aiqbench analysis
This paper addresses the limitations of existing neural operators in modeling ultrasonic wave propagation, specifically highlighting failures in capturing reflections and handling multi-scale information within heterogeneous media. The authors propose a novel architecture that integrates Fourier Neural Operators with local-integral resampling into a U-Net framework to achieve robust, data-efficient predictions across varying spatial scales. This advancement directly targets the computational efficiency required for fast inverse solutions in complex sensing environments.
Neural Surrogate Modeling of Ultrasonic Wave Propagation in Heterogeneous Media
arXiv:2610.13258v1 Announce Type: new Abstract: Neural surrogates provide computationally efficient auto-regressive modeling of wave propagation, enabling e.g. fast inverse solutions. Despite recent progress, the current surrogates are not yet sufficient for the needs of ultrasonic sensing, characterized by high frequency and heterogeneous propagation media. We show how methods building on Fourier Neural Operators (FNO) fail to capture essential signal features, such as reflections, whereas U-Net -based methods learn the wave fields well but lack the ability to transfer information across different spatial scales. We then propose a new surrogate that captures the best of the two worlds, by integrating FNOs and local-integral resampling into a U-Net architecture. We show it can be trained on limited data, and that the predictions are robust to input noise and work across spatial scales.
Abstract:Neural surrogates provide computationally efficient auto-regressive modeling of wave propagation, enabling e.g. fast inverse solutions. Despite recent progress, the current surrogates are not yet sufficient for the needs of ultrasonic sensing, characterized by high frequency and heterogeneous propagation media. We show how methods building on Fourier Neural Operators (FNO) fail to capture essential signal features, such as reflections, whereas U-Net -based methods learn the wave fields well but lack the ability to transfer information across different spatial scales. We then propose a new surrogate that captures the best of the two worlds, by integrating FNOs and local-integral resampling into a U-Net architecture. We show it can be trained on limited data, and that the predictions are robust to input noise and work across spatial scales.
Machine Learning (cs.LG)
arXiv:2610.13258 [cs.LG]
(or arXiv:2610.13258v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.13258 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 219 words
Related coverage
Self-composing neural operators for high-frequency and multiscale PDE surrogates
arXiv · Aug 4, 2026
ROMNet: a hybrid reduced order modeling and machine learning approach to waveform inversion
arXiv · Aug 27, 2026
From Physics to Surrogate Intelligence: A Unified Electro-Thermo-Optimization Framework for TSV Networks
arXiv · Jul 28, 2026
Learning Metamaterial Eigenmodes with Wavelet-Encoded Fourier Neural Operators
arXiv · Sep 9, 2026