Predicting Optical Turbulence using Machine Learning Methodology

Abstract

Measuring and predicting optical turbulence is difficult and requires specialized equipment. The NPS Meteorology Department has previously developed a model (NAVSLaM) to predict optical turbulence in the surface layer (up to tilde100 m above the ocean or land) based upon atmospheric measurements using simple, robust sensors. On the other hand, the Physics Department has developed machine learning models of optical turbulence using atmospheric measurements. This research involves measurements of optical turbulence over many months using sonic anemometers that served as the baseline to compare prediction from the models. Atmospheric parameters such as air temperature, wind speed, humidity at two different heights as well as solar flux and ground temperature were simultaneously collected. Those data were used as inputs for NAVSLaM and the machine learning models to predict optical turbulence. We then compared the performance of these prediction models to each other by calculating the root-mean-square error with respect to the baseline data from the sonic anemometers. The results from this research will help determine which model is more reliable for the given environment. Overall, the ML model appeared to work better than NAVSLaM for predicting the optical turbulence values that we observed. However, NAVSLaM is a more general model that should work well in a variety of environments. An accurate machine learning model of optical turbulence could significantly improve forecasts of directed energy weapon effectiveness. Eventually, it could even be used in an operational scenario to make real-time predictions of turbulence and its impact on directed energy weapon performance.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 21, 2023
Accession Number
AD1224314

Entities

People

  • Joseph Blau

Organizations

  • Naval Postgraduate School

Tags

Fields of Study

  • Environmental science
  • Physics

Readers

  • Atmospheric Remote Sensing.
  • Atmospheric Science / Meteorology, specifically Wind Wave Turbulence.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks
  • Directed Energy