A machine learning approach for forecasting the refractive index structure parameter

Rudiger, Joshua J.; Book, Kevin; deGrassie, J.S.; Hammel, Stephen M.; Baker, Brook K.

doi:10.1117/12.2323835

Cited by 3 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, overtraining is a known issue in ML, which would lead a model trained and tested on the same location to perform well, but to underperform or fail entirely when tested on new data. This work builds off the work of Sklavounos and of earlier machine learning analysis completed by Rudiger et al (2018) 5 .…”

Section: Introductionmentioning

confidence: 95%

Machine learning for optical turbulence prediction in geographically similar regions

Campbell,

McBryde,

Walter

et al. 2023

Laser Communication and Propagation Through the Atmosphere and Oceans XII

View full text Add to dashboard Cite

The refractive index structure parameter (Cn 2 ) is of interest because it characterizes turbulence, which affects optical propagation through the atmosphere, including free space optical communications, laser propagation, and imaging. This work seeks to develop a geography-agnostic model that can predict Cn 2 and received signal strength index (RSSI), with as few input parameters as possible. This work trains models including the Gaussian process regression, neural network, and bagged decision tree types, and use r-squared and root-mean squared error to compare model performance. Most of the data used to train and test the algorithms is collected in San Diego, a Csa-type climate (hot-summer Mediterranean climate) according to Köppen climate classification. We then demonstrate application of the trained models to a different site with similar climate, using available common input parameters, and quantitatively assess each model's respective efficacy.

show abstract

Section: Introductionmentioning

confidence: 95%

Machine learning for optical turbulence prediction in geographically similar regions

Campbell,

McBryde,

Walter

et al. 2023

Laser Communication and Propagation Through the Atmosphere and Oceans XII

View full text Add to dashboard Cite

show abstract

“…One of the major attractions of the machine learning approach for atmospheric turbulence characterization is that it offers a wide range of capabilities for real-time fusion of data flows coming from various optical and meteorological sensors [38,39]. To better reveal the complexity of atmospheric turbulence dynamics, the sensor outputs should be differently affected by atmospheric turbulence; e.g., have enhanced sensitivity to the location of turbulence layers, or to specific spatial and/or temporal characteristics of atmospheric refractive index inhomogeneities, or changes in atmospheric refractivity, visibility, etc.…”

Section: Concluding Remarks and Forthcoming Research Directionsmentioning

confidence: 99%

Atmospheric Turbulence Study with Deep Machine Learning of Intensity Scintillation Patterns

et al. 2020

View full text Add to dashboard Cite

A new paradigm for machine learning-inspired atmospheric turbulence sensing is developed and applied to predict the atmospheric turbulence refractive index structure parameter using deep neural network (DNN)-based processing of short-exposure laser beam intensity scintillation patterns obtained with both: experimental measurement trials conducted over a 7 km propagation path, and imitation of these trials using wave-optics numerical simulations. The developed DNN model was optimized and evaluated in a set of machine learning experiments. The results obtained demonstrate both good accuracy and high temporal resolution in sensing. The machine learning approach was also employed to challenge the validity of several eminent atmospheric turbulence theoretical models and to evaluate them against the experimentally measured data.

show abstract

Atmospheric Turbulence Identification in a multi-user FSOC using Supervised Machine Learning

Aveta

Chan

Asfari

et al. 2021

2021 IEEE 12th Annual Ubiquitous Computing, Electronics &Amp; Mobile Communication Conference (UEMCON)

View full text Add to dashboard Cite

A machine learning approach for forecasting the refractive index structure parameter

Cited by 3 publications

References 6 publications

Machine learning for optical turbulence prediction in geographically similar regions

Machine learning for optical turbulence prediction in geographically similar regions

Atmospheric Turbulence Study with Deep Machine Learning of Intensity Scintillation Patterns

Atmospheric Turbulence Identification in a multi-user FSOC using Supervised Machine Learning

Contact Info

Product

Resources

About