Ground-based remote observation systems are vulnerable to atmospheric turbulence, which can lead to image degradation. While some methods can mitigate this turbulence distortion, many have issues such as long processing times and unstable restoration effects. Furthermore, the physics of turbulence is often not fully integrated into the image reconstruction algorithms, making their theoretical foundations weak. In this paper, we propose a method for atmospheric turbulence mitigation using optical flow and convolutional neural networks (CNN). We first employ robust principal component analysis (RPCA) to extract a reference frame from the images. With the help of optical flow and the reference frame, the tilt can be effectively corrected. After correcting the tilt, the turbulence mitigation problem can be simplified as a deblurring problem. Then, we use a trained CNN to remove blur. By utilizing (i) a dataset that conforms to the turbulence physical model to ensure the restoration effect of the CNN and (ii) the efficient parallel computing of the CNN to reduce computation time, we can achieve better results compared to existing methods. Experimental results based on actual observed turbulence images demonstrate the effectiveness of our method. In the future, with further improvements to the algorithm and updates to GPU technology, we expect even better performance.

Using a solar radiometer is an effective approach for improving the remote sensing of solar irradiance distribution and atmospheric composition. Long-term development of a solar scanning radiometer enables frequent and reliable measurement of atmospheric parameters such as the water vapor column and aerosol optical properties. However, the discrete wavelength radiometer has encountered a bottleneck with respect to its insufficient spectral resolution and limited observation waveband, and it has been unable to satisfy the needs of refined and intelligent on-site experiments. This study proposes a solar-skylight spectroradiometer for obtaining visible and near-IR fine spectrum with two types of measurement: direct-sun irradiance and diffuse-sky radiance. The instrument adopts distributed control architecture composed of the ARM-Linux embedded platform and sensor networks. The detailed design of the measuring light-path, two-axis turntable, and master control system will be addressed in this study. To determine all coefficients needed to convert instrument outputs to physical quantities, integrating sphere and Langley extrapolation methods are introduced for diffuse-sky and direct-sun calibration, respectively. Finally, the agreement of experimental results between spectroradiometers and measuring benchmarks (DTF sun-photometer, microwave radiometer, and Combined Atmospheric Radiative Transfer simulation) verifies the feasibility of the spectroradiometer system, and the radiation information of feature wavelengths can be used to retrieve the characteristics of atmospheric optics.