Adaptive optics (AO) technology is an effective means to compensate for atmospheric turbulence, but the inherent delay error of an AO system will cause the compensation phase of the deformable mirror (DM) to lag behind the actual distortion, which limits the correction performance of the AO technology. Therefore, the feed-forward prediction of atmospheric turbulence has important research value and application significance to offset the inherent time delay and improve the correction bandwidth of the AO system. However, most prediction algorithms are limited to an open-loop system, and the deployment and the application in the actual AO system are rarely reported, so its correction performance improvement has not been verified in practice. We report, to our knowledge, the first successful test of a deep learning-based spatiotemporal prediction model in an actual 3 km laser atmospheric transport AO system and compare it with the traditional closed-loop control methods, demonstrating that the AO system with the prediction model has higher correction performance.

The precise estimation of fluid motion is critical across various fields, including aerodynamics, hydrodynamics, and industrial fluid mechanics. However, refraction at complex interfaces in the light path can cause image deterioration and lead to severe measurement errors if the aberration changes with time, e.g., at fluctuating air–water interfaces. This challenge is particularly pronounced in technical energy conversion processes such as bubble formation in electrolysis, droplet formation in fuel cells, or film flows. In this paper, a flow field estimation algorithm that can perform the aberration correction function is proposed, which integrates the flow field distribution estimation algorithm based on the Particle Image Velocimetry (PIV) technique and the novel actuator-free adaptive optics technique. Two different multi-input convolutional neural network (CNN) structures are established, with two frames of distorted PIV images and measured wavefront distortion information as inputs. The corrected flow field results are directly output, which are divided into two types based on different network structures: dense estimation and sparse estimation. Based on a series of models, a corresponding dataset synthesis model is established to generate training datasets. Finally, the algorithm performance is evaluated from different perspectives. Compared with traditional algorithms, the two proposed algorithms achieves reductions in the root mean square value of velocity residual error by 84% and 89%, respectively. By integrating both flow field measurement and novel adaptive optics technique into deep CNNs, this method lays a foundation for future research aimed at exploring more intricate distortion phenomena in flow field measurement.

This Letter proposes a universal wavefront reconstruction approach based on a coupled data set and neural network, aiming to overcome the limitations of current algorithms in terms of universality and wavefront sensing accuracy for variable imaging objects. First, a novel data set, Multi-Object Wavefront Coupling Dataset (MOCD-Dataset), is developed to provide diverse data and enable the network to learn universal wavefront features. Next, a new universal wavefront reconstruction network called Object-Independent Wavefront Decoupling Network (OIWD-Net) is introduced, aiming to separate imaging object information from multiple variable images. Our algorithm eliminates the need for specialized wavefront sensors, has a simple system, high light energy utilization, and does not require customized models for each different type of imaging objects, making it highly practical. By combining the MOCD-Dataset and the OIWD-Net, excellent accuracy in wavefront reconstruction of different imaging objects has been achieved. This research provides a new solution for high-resolution image restoration in fields such as solar structure observation and astronomical high-resolution imaging.

This research presents a practical approach for wavefront reconstruction and correction adaptable to variable targets, with the aim of constructing a high-precision, general extended target adaptive optical system. Firstly, we delve into the detailed design of a crucial component, the distorted grating, simplifying the optical system implementation while circumventing potential issues in traditional phase difference-based collection methods. Subsequently, normalized fine features (NFFs) and structure focus features (SFFs) which both are independent of the imaging target but corresponded precisely to the wavefront aberration are proposed. The two features provide a more accurate and robust characterization of the wavefront aberrations. Then, a Noise-to-Denoised Generative Adversarial Network (N2D-GAN) is employed for denoising real images. And a lightweight network, Attention Mechanism-based Efficient Network (AM-EffNet), is applied to achieve efficient and high-precision mapping between features and wavefronts. A prototype of object-independent adaptive optics system is demonstrated by experimental setup, and the effectiveness of this method in wavefront reconstruction for different imaging targets has been verified. This research holds significant relevance for engineering applications of adaptive optics, providing robust support for addressing challenges within practical systems.

In adaptive optics systems, high spatial resolution detection is a core prerequisite for achieving accurate wavefront correction. High spatial resolution wavefront measurement based on the traditional Shack-Hartmann technique is limited by the density of the microlens array. In contrast, off-axis digital holography technology is applied in wavefront measurement systems of adaptive optics systems due to its advantages of high spatial resolution, non-contact measurement, and full-field measurement. However, during the demodulation of its interference fringes, the accurate extraction of the complex amplitude of the +1st-order diffraction order directly determines the precision of wavefront reconstruction. Traditional frequency-domain filtering methods suffer from drawbacks such as reliance on manual threshold setting, poor adaptability to irregular spectra, and localization deviations caused by multi-region interference, making it difficult to meet the dynamic application requirements of adaptive optics. To address these issues, this study proposes a spectrum extraction method based on the Canny operator for adaptive edge extraction and centroid localization. The method first locks the rough range of the +1st-order spectrum through multi-stage peak screening, then achieves complete segmentation of spectrum spots by combining adaptive histogram equalization with edge closing and filling, resolves centroid indexing errors via maximum connected component screening, and ultimately accomplishes accurate extraction through Gaussian window filtering. Simulation experimental results show that, in comparison with two classical spectrum filtering methods, the centroid estimation error of the proposed method remains below 0.245 pixels under different noise intensity conditions. Moreover, the root mean square error of the residual wavefront corresponding to the reconstructed wavefront of the proposed method is reduced by 89.0% and 87.2% compared with those of the two classical methods, respectively. We further carried out measurement experiments based on a self-developed atmospheric turbulence test bench. The experimental results demonstrate that the proposed method exhibits higher-precision spectral centroid localization capability, which provides a reliable technical support for the high-precision measurement of dynamic distortion induced by atmospheric turbulence.

The inherent latency of adaptive optics (AO) systems can amplify residual errors and limit correction bandwidth under rapidly varying turbulence. This work proposes a continuous-time predictive framework, LZCP-Net (Liquid Zernike Coefficient Prediction Network), which predicts future Zernike coefficients from a short history to pre-drive deformable mirrors for compensation. LZCP-Net integrates a 1-D temporal convolutional front-end with liquid time-constant (LTC) units featuring learnable and bounded time constants, enabling stable ODE-based dynamics that capture both short-term transients and long-term dependencies. Simulations show that LZCP-Net achieves up to 57% lower residual RMS than conventional AO under strong turbulence and reduced sampling, outperforming LSTM and Kalman predictors, especially in the prediction of mid and high-order Zernike mode turbulence. Trained with 10-frame input sequences, the model retains near-optimal accuracy even when using only seven frames, ensuring flexibility for real-time inference. Without any fine-tuning, it also generalizes across different Shack–Hartmann WFS configurations, demonstrating strong robustness to system variations. Experimental results confirm that a model trained solely on simulated data achieves 34.7% RMS reduction and 32.3% smaller EE80 radius, validating its real-world applicability. These results establish LZCP-Net as a lightweight and adaptive predictive module that enables adaptive optics systems to achieve high-precision, low-latency correction in both simulation and experimental settings.