The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering problems with tens of thousands of controllable variables. By dynamically generating training examples that highlight surrogate errors and using a replay dataset with normalization, the authors achieve a surrogate that accurately simulates two‑dimensional wave scattering for up to 41,772 variables and generalizes to over 3 million variables without retraining. The surrogate is applied to forward simulations and inverse design of freeform beam splitters and gradient‑index lenses, achieving speedups up to 26.5× compared to traditional FDTD methods.
By Charles Dove, Laura Waller
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:2610.17221v1 Announce Type: cross
Abstract: Neural surrogates for Partial Differential Equations (PDEs) are usually trained on synthetic data from numerical simulators. As models grow and scali...
By Paul Setinek, Fabian Paischer, Nils Thuerey, Johannes Brandstetter, Felix Koehler
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: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 presents cross‑domain pretraining for neural surrogates in steady‑state computational fluid dynamics (CFD). By training models across varied geometries, boundary conditions, and fidelities, the authors show that such pretraining improves zero‑ and few‑shot performance compared to training from scratch or transferring from domain‑specific experts. Finetuning a pretrained cross‑domain model can reduce errors by 2–3× at the same sample size and require eight times fewer samples to reach the same error, with benefits that grow with model size and dataset diversity.
By Anthony Zhou, Amir Barati Farimani, Shirley Ho, Rudy Morel