Monterey, CA; Naval Postgraduate School
AI/DEEP LEARNING WAVEFRONT SENSING FOR HEL USING TARGET IMAGE TO SIMPLIFY ADAPTIVE OPTICS SYSTEMS
Abstract
dc:description.abstractAtmospheric turbulence significantly limits the performance of imaging and high-energy laser (HEL) systems by distorting the wavefront as it propagates through the atmosphere. Traditional correction methods use wavefront sensors with adaptive optics, which can be expensive, complex, and resource-intensive. This thesis was focused on using machine learning (ML) models to predict atmospheric turbulence parameters, to be used as another method to correct for distortion within the atmosphere. ML models could decrease the complexity normally required for systems with turbulence correction methods. This was done by conducting a transfer learning experiment with a convolutional neural network (CNN) specialized in image classification. It was modified to fit a regression problem of characterizing the Zernike polynomials corresponding to the turbulence. Large datasets of turbulent images were created, and multiple models were tested to find what parameters lead to better performance and a lower mean squared error (MSE). Ultimately, a combined turbulence model yielded superior performance at high turbulence. Also, new untested images were introduced to gauge the model’s success against unseen data. By improving on modern artificial intelligence (AI) techniques, the project aimed to enhance the Navy’s capabilities and provide a path for future turbulence correction innovation in other optics and laser systems.
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Astronautical Engineering
- Level thesis:degree_level
- Masters
- Discipline thesis:degree_discipline
- Astronautical Engineering
- Department dc:contributor.department
- Mechanical and Aerospace Engineering (MAE)
- Grantor dc:publisher
- Monterey, CA; Naval Postgraduate School
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Messina, Nicholas A.
- Advisors dc:contributor.advisor
-
- Agrawal, Brij N.
- Herrera, Leonardo E.
Rights
dc:rights- Statement dc:rights
-
- This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
- Distribution Statement A. Approved for public release: Distribution is unlimited.
Identifiers
dc:identifier.*- Dc Identifier Programcode
- 566, Space Systems Operations and Engineering
- Thesis Thesis Identifier
- 40830