Physics

Meteorology

Atmospheric turbulence

Optics

Adaptive optics

Wavefront

Artificial intelligence

Turbulence

Computer science

Phase (matter)

Quantum mechanics

Artificial neural network

Zernike polynomials

Wavefront sensor

PhotoniX

Deep learning neural networks are used for wavefront sensing and aberration correction in atmospheric turbulence without any wavefront sensor (i.e. reconstruction of the wavefront aberration phase from the distorted image of the object). We compared and found the characteristics of the direct and indirect reconstruction ways: (i) directly reconstructing the aberration phase; (ii) reconstructing the Zernike coefficients and then calculating the aberration phase. We verified the generalization ability and performance of the network for a single object and multiple objects. What’s more, we verified the correction effect for a turbulence pool and the feasibility for a real atmospheric turbulence environment.

Deep learning wavefront sensing and aberration correction in atmospheric turbulence