Ξ -ML: a dimensional analysis-based machine learning parameterization of optical turbulence in the atmospheric surface layer

Journal Article (2023)
Author(s)

M. Pierzyna (TU Delft - Atmospheric Remote Sensing)

R Saathof (TU Delft - Space Systems Egineering)

Sukanta Basu (University at Albany)

Research Group
Atmospheric Remote Sensing
Copyright
Β© 2023 Maximilian Pierzyna, R. Saathof, S. Basu
DOI related publication
https://doi.org/10.1364/OL.492652
More Info
expand_more
Publication Year
2023
Language
English
Copyright
Β© 2023 Maximilian Pierzyna, R. Saathof, S. Basu
Research Group
Atmospheric Remote Sensing
Issue number
17
Volume number
48
Pages (from-to)
4484-4487
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Turbulent fluctuations of the atmospheric refraction index, so-called optical turbulence, can significantly distort propagating laser beams. Therefore, modeling the strength of these fluctuations (𝐢2𝑛) is highly relevant for the successful development and deployment of future free-space optical communication links. In this Letter, we propose a physics-informed machine learning (ML) methodology, Ξ -ML, based on dimensional analysis and gradient boosting to estimate 𝐢2𝑛. Through a systematic feature importance analysis, we identify the normalized variance of potential temperature as the dominating feature for predicting 𝐢2𝑛. For statistical robustness, we train an ensemble of models which yields high performance on the out-of-sample data of R2 = 0.958 ± 0.001.

Files

Ol_48_17_4484.pdf
(pdf | 3.45 Mb)
- Embargo expired in 19-02-2024
License info not available