Open-loop tomography with artificial neural networks on CANARY: on-sky results

TL;DR

This paper evaluates an ANN-based tomographic reconstructor, CARMEN, on the Canary adaptive optics system, comparing its on-sky performance with the traditional Learn and Apply method, and discusses its potential advantages and limitations.

Contribution

It introduces CARMEN, an ANN-based reconstructor, and provides the first on-sky performance comparison with established methods in adaptive optics.

Findings

L&A reconstructor outperforms CARMEN by ~5% in Strehl ratio.

CARMEN's performance is limited by training data quality.

ANN can outperform L&A under certain atmospheric change conditions.

Abstract

We present recent results from the initial testing of an Artificial Neural Network (ANN) based tomographic reconstructor Complex Atmospheric Reconstructor based on Machine lEarNing (CARMEN) on Canary, an Adaptive Optics demonstrator operated on the 4.2m William Herschel Telescope, La Palma. The reconstructor was compared with contemporaneous data using the Learn and Apply (L&A) tomographic reconstructor. We find that the fully optimised L&A tomographic reconstructor outperforms CARMEN by approximately 5% in Strehl ratio or 15nm rms in wavefront error. We also present results for Canary in Ground Layer Adaptive Optics mode to show that the reconstructors are tomographic. The results are comparable and this small deficit is attributed to limitations in the training data used to build the ANN. Laboratory bench tests show that the ANN can out perform L&A under certain conditions, e.g. if the higher layer of a model two layer atmosphere was to change in altitude by ~300~m (equivalent to a shift of approximately one tenth of a subaperture).