Learning the Lantern: Neural network applications to broadband photonic lantern modelling

Abstract

Photonic lanterns allow the decomposition of highly multimodal light into a simplified modal basis such as single-moded and/or few-moded. They are increasingly finding uses in astronomy, optics and telecommunications. Calculating propagation through a photonic lantern using traditional algorithms takes $\sim 1$ hour per simulation on a modern CPU. This paper demonstrates that neural networks can bridge the disparate opto-electronic systems, and when trained can achieve a speed-up of over 5 orders of magnitude. We show that this approach can be used to model photonic lanterns with manufacturing defects as well as successfully generalising to polychromatic data. We demonstrate two uses of these neural network models, propagating seeing through the photonic lantern as well as performing global optimisation for purposes such as photonic lantern funnels and photonic lantern nullers.

20 pages, 14 figures

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• First on-sky demonstration of an integrated-photonic nulling-interferometer: The GLINT instrument
• Enhancing stellar spectroscopy with extreme adaptive optics and photonics
• Demonstration of an efficient, photonic-based astronomical spectrograph on an 8-m telescope
• Starlight coupling through atmospheric turbulence into few-mode fibers and photonic lanterns in the presence of partial adaptive optics correction
• Modal noise in an integrated photonic lantern fed diffraction-limited spectrograph