The Simons Observatory: HoloSim-ML: machine learning applied to the efficient analysis of radio holography measurements of complex optical systems

TL;DR

HoloSim-ML is a machine learning-based Python tool that efficiently analyzes radio holography data to accurately determine mirror adjuster positions in complex optical systems like the Simons Observatory telescope.

Contribution

The paper introduces HoloSim-ML, a novel machine learning approach for analyzing radio holography measurements in complex optical systems, improving efficiency and accuracy.

Findings

Accurately determines mirror adjuster positions with micron precision.

Reduces measurement and analysis time compared to traditional methods.

Successfully applied to the Simons Observatory 6m telescope.

Abstract

Near-field radio holography is a common method for measuring and aligning mirror surfaces for millimeter and sub-millimeter telescopes. In instruments with more than a single mirror, degeneracies arise in the holography measurement, requiring multiple measurements and new fitting methods. We present HoloSim-ML, a Python code for beam simulation and analysis of radio holography data from complex optical systems. This code uses machine learning to efficiently determine the position of hundreds of mirror adjusters on multiple mirrors with few micron accuracy. We apply this approach to the example of the Simons Observatory 6m telescope.