The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering inverse problems with tens of thousands of controllable variables. By dynamically generating training examples through gradient ascent and using a replay dataset with normalization, the authors achieve a surrogate that accurately models two‑dimensional wave scattering for up to 41,772 variables and can generalize to over 3 million variables without retraining. The surrogate demonstrates comparable or better performance than traditional FDTD simulations for large‑scale forward simulations and inverse design of photonic devices, achieving speedups up to 26.5×.
arXiv:2608. 09382v1 Announce Type: cross Abstract: Electromagnetic inverse scattering is a nonlinear and ill-posed problem, where accurate reconstruction is challenging due to measurement limitations, noise, and high computational costs, especially for 3-D imaging.
By Yutong Du, Zicheng Liu, Bo Qi, Yali Zong, Peixian Han
arXiv:2608. 02937v1 Announce Type: cross Abstract: Designing an effective electromagnetic inverse-scattering solver requires faithful enforcement of nonlinear full-wave physics together with an expressive prior on the unknown permittivity contrast.
By Wenhan Guo, Yuan Gao, Yu Sun
The paper introduces a coordinate-residual physics-driven neural network (CRPDNN) for 3‑D electromagnetic inverse scattering. CRPDNN models the unknown contrast distribution using normalized spatial coordinates and a residual convolutional network, optimizing parameters by enforcing consistency between measured and predicted scattered fields. It eliminates the need for preliminary reconstruction, achieving lower relative error and significant speedups compared to existing methods, while maintaining stability under noisy measurements and showing promise in practical imaging experiments.
By Yutong Du, Zicheng Liu, Bo Qi, Yali Zong, Peixian Han
arXiv:2606. 01110v1 Announce Type: cross Abstract: Full waveform inversion (FWI) reconstructs heterogeneous material properties from receiver data but remains computationally demanding.
By Hoang Anh Nguyen, Divakar Vashisth, Ali Tura
arXiv:2606. 18305v1 Announce Type: cross Abstract: Operator learning is an emerging interdisciplinary field that integrates machine learning with scientific computing.
By Kuilin Qin, Lianfang Wang, Xu Sun, Jiwei Jia, Yu Wang, Yong Wang, Yuping Duan
The paper presents a collaborative on‑sensor array camera that uses a distributed meta‑optics learning method to jointly optimize a 100‑million‑nanopost metasurface array for broadband visible imaging. By training the array end‑to‑end with a learned meta‑atom proxy and a parallax‑aware, noise‑aware reconstruction algorithm, the design overcomes the wavelength‑dependent limitations of traditional metalenses. Experimental results show that the camera delivers consistent image quality across varying scene illumination spectra without relying on generative reconstruction.
By Jipeng Sun, Kaixuan Wei, Thomas Eboli, Congli Wang, Cheng Zheng, Zhihao Zhou, Arka Majumdar, Wolfgang Heidrich, Felix Heide
arXiv:2609. 38023v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) embed governing equations into deep learning, but enforce them only through loss residuals, leaving highly oscillatory wave behavior to be discovered by optimization.
By Huiwen Zhang, Feng Ye, Chu Ma
arXiv:2609.07983v1 Announce Type: new
Abstract: Physics-Informed Neural Networks (PINNs) have recently emerged as a promising approach for solving Partial Differential Equations (PDEs), offering a me...
By Davide Staub, Ben Moseley
ROMNet is a hybrid reduced‑order modeling and machine‑learning framework designed to improve waveform inversion for acoustic waves. It replaces the costly nonlinear mapping from a reduced‑order model (ROM) matrix to wave speed with a neural network that outputs a simpler ROM matrix, thereby reducing computational effort. The method is validated on two training datasets—random Gaussian‑based media and the GeoFWI benchmark—and compared against direct ROM inversion and two deep‑learning FWI approaches, Fourier‑DeepONet and InversionNet.
By Liliana Borcea, Alexander Mamonov, Kui Ren, Haizhao Yang, Chugang Yi
arXiv:2606. 03262v1 Announce Type: new Abstract: Neural operators learn mappings between infinite-dimensional function spaces and provide a data-driven surrogate modeling paradigm for parametric partial differential equations (PDEs).
By Keke Wu, Yixuan Zhang, Jingrun Chen
The paper presents a conditional diffusion framework for the inverse design of dielectric resonator metasurfaces based on target angular scattering patterns. Trained on T‑matrix simulated geometry‑response pairs, the model learns a distribution of feasible geometries, allowing multiple candidate designs for the ill‑posed inverse problem. The best generated metasurface achieves a mean percentage error of 1.39%, outperforming CMA‑ES optimization and deterministic neural baselines, and can be inferred in about one minute after training.
By M. Tsukerman, K. Grotov, D. Vovchuk, P. Ginzburg