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 ($C_n^2$) 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, Π-ML, based on dimensional analysis and gradient boosting to estimate $C_n^2$. Through a systematic feature importance analysis, we identify the normalized variance of potential temperature as the dominating feature for predicting $C_n^2$. 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.

© 2023 Optica Publishing Group

Using an artificial neural network approach to estimate surface-layer optical turbulence at Mauna Loa, Hawaii

Yao Wang and Sukanta Basu
Opt. Lett. 41(10) 2334-2337 (2016)

Intercomparison of flux-, gradient-, and variance-based optical turbulence (C n2) parameterizations

Maximilian Pierzyna, Oscar Hartogensis, Sukanta Basu, and Rudolf Saathof
Appl. Opt. 63(16) E107-E119 (2024)

Atmospheric turbulence characterization with simultaneous measurement of phase, angle of arrival, and intensity in a retroreflected optical link

Benjamin P. Dix-Matthews, Skevos F. E. Karpathakis, and Sascha W. Schediwy
Opt. Lett. 48(21) 5519-5522 (2023)

Machine learning for a Vernier-effect-based optical fiber sensor

Chen Zhu, Osamah Alsalman, and Wassana Naku
Opt. Lett. 48(9) 2488-2491 (2023)

Machine-learning-based method for fiber-bending eavesdropping detection

Haokun Song, Rui Lin, Yajie Li, Qing Lei, Yongli Zhao, Lena Wosinska, Paolo Monti, and Jie Zhang
Opt. Lett. 48(12) 3183-3186 (2023)