Research Progress on Atmospheric Turbulence Perception and Correction Based on Adaptive Optics and Deep Learning

Abstract

Atmospheric turbulence constitutes a fundamental limiting factor in astronomical observation systems and laser communication architectures. During atmospheric propagation of optical beams, dynamically evolving wavefront aberrations are inevitably induced, rendering precise turbulence characterization and mitigation critical for optimizing operational performance of terrestrial telescopes and satellite-ground optical links. Adaptive optics (AO) represents a sophisticated methodology for optical enhancement through real-time wavefront measurement and adaptive compensation of medium-induced phase distortions. Recent years have witnessed substantial advancements in AO technology, driven by synergistic progress in fundamental theories, optoelectronic devices, and computational algorithms. Furthermore, artificial intelligence-driven turbulence processing frameworks leveraging deep neural networks have emerged as a prominent research frontier, demonstrating remarkable potential in intelligent wavefront sensing and nonlinear compensation. This work presents a systematic review of atmospheric turbulence fundamentals, including theoretical formulations and AO-based mitigation strategies. Particular emphasis is placed on deep learning-enabled intelligent correction paradigms, while critical analysis is provided regarding prospective research trajectories and implementation challenges.