A physics-defined recurrent neural network to compute coherent light wave scattering on the millimetre scale

Abstract

Heterogeneous materials such as biological tissue scatter light in random, yet deterministic, ways. Wavefront shaping can reverse the effects of scattering to enable deep-tissue microscopy. Such methods require either invasive access to the internal field or the ability to numerically compute it. However, calculating the coherent field on a scale relevant to microscopy remains excessively demanding for consumer hardware. Here we show how a recurrent neural network can mirror Maxwell's equations without training. By harnessing public machine learning infrastructure, such \emph{Scattering Network} can compute the $633\text{nm}$-wavelength light field throughout a $25{\text{mm}}^2$ or $176^3\mu {\text{m}}^3$ scattering volume. The elimination of the training phase cuts the calculation time to a minimum and, importantly, it ensures a fully deterministic solution, free of any training bias. The integration with an open-source electromagnetic solver enables any researcher with an internet connection to calculate complex light-scattering in volumes that are larger by two orders of magnitude

8 pages, 3 figures

References in corpus (14)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Light fields in complex media: mesoscopic scattering meets wave control
• Roadmap on Wavefront Shaping and deep imaging in complex media
• Anderson localization of electromagnetic waves in three dimensions
• Depth-Targeted Energy Deposition Deep Inside Scattering Media
• Tracking moving objects through scattering media via speckle correlations
• Fast multi-source nanophotonic simulations using augmented partial factorization
• How to build the optical inverse of a multimode fibre
• Coherent enhancement of optical remission in diffusive media
• Calculating coherent light-wave propagation in large heterogeneous media
• MaxwellNet: Physics-driven deep neural network training based on Maxwell's equations
• A physics-defined recurrent neural network to compute coherent light wave scattering on the millimetre scale
• A universal matrix-free split preconditioner for the fixed-point iterative solution of non-symmetric linear systems
• Large area optimization of meta-lens via data-free machine learning

Cited by in corpus (2)

• A physics-defined recurrent neural network to compute coherent light wave scattering on the millimetre scale
• Domain decomposition of the modified Born series approach for large-scale wave propagation simulations