{"ID":2877573,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19751","arxiv_id":"2508.19751","title":"High-Fidelity Prediction of Perturbed Optical Fields using Fourier Feature Networks","abstract":"Predicting the effects of physical perturbations on optical channels is critical for advanced photonic devices, but existing modelling techniques are often computationally intensive or require exhaustive characterisation. We present a novel data-efficient machine learning framework that learns the perturbation-dependent transmission matrix of a multimode fibre. To overcome the challenge of modelling the resulting highly oscillatory functions, we encode the perturbation into a Fourier Feature basis, enabling a compact multi-layer perceptron to learn the mapping with high fidelity. On experimental data from a compressed fibre, our model predicts the output field with a 0.995 complex correlation to the ground truth, improving accuracy by an order of magnitude over standard networks while using 85\\% fewer parameters. This approach provides a general tool for modelling complex optical systems from sparse measurements.","short_abstract":"Predicting the effects of physical perturbations on optical channels is critical for advanced photonic devices, but existing modelling techniques are often computationally intensive or require exhaustive characterisation. We present a novel data-efficient machine learning framework that learns the perturbation-dependen...","url_abs":"https://arxiv.org/abs/2508.19751","url_pdf":"https://arxiv.org/pdf/2508.19751v2","authors":"[\"Joshua R. Jandrell\",\"Mitchell A. Cox\"]","published":"2025-08-27T10:25:57Z","proceeding":"physics.optics","tasks":"[\"physics.optics\",\"cs.LG\",\"physics.comp-ph\"]","methods":"[]","has_code":false}