Latency in the control loop of adaptive optics (AO) systems can severely limit performance. Under the frozen flow hypothesis linear predictive control techniques can overcome this; however, identification and tracking of relevant turbulent parameters (such as wind speeds) is required for such parametric techniques. This can complicate practical implementations and introduce stability issues when encountering variable conditions. Here, we present a non-linear wavefront predictor using a long short-term memory (LSTM) artificial neural network (ANN) that assumes no prior knowledge of the atmosphere and thus requires no user input. The ANN is designed to predict the open-loop wavefront slope measurements of a Shack–Hartmann wavefront sensor (SH-WFS) one frame in advance to compensate for a single-frame delay in a simulated 7 × 7 single-conjugate adaptive optics system operating at 150 Hz. We describe how the training regime of the LSTM ANN affects prediction performance and show how the performance of the predictor varies under various guide star magnitudes. We show that the prediction remains stable when both wind speed and direction are varying. We then extend our approach to a more realistic two-frame latency system. AO system performance when using the LSTM predictor is enhanced for all simulated conditions with prediction errors within 19.9–40.0 nm RMS of a latency-free system operating under the same conditions compared to a bandwidth error of 78.3 ± 4.4 nm RMS.

中文翻译：

---

使用人工神经网络进行开环自适应光学的波前预测

自适应光学 (AO) 系统控制回路中的延迟会严重限制性能。在冻结流假设下线性预测控制技术可以克服这个问题；然而，此类参数化技术需要识别和跟踪相关湍流参数（如风速）。这会使实际实现复杂化，并在遇到可变条件时引入稳定性问题。在这里，我们使用长短期记忆 (LSTM) 人工神经网络 (ANN) 提出了一种非线性波前预测器，该网络假设没有大气的先验知识，因此不需要用户输入。ANN 旨在提前一帧预测 Shack-Hartmann 波前传感器 (SH-WFS) 的开环波前斜率测量值，以补偿模拟 7 × 7 单共轭自适应光学系统运行中的单帧延迟在 150 赫兹。我们描述了 LSTM ANN 的训练机制如何影响预测性能，并展示了预测器的性能如何在不同的引导星星等下变化。我们表明，当风速和风向都在变化时，预测仍然保持稳定。然后我们将我们的方法扩展到更现实的两帧延迟系统。使用 LSTM 预测器时的 AO 系统性能在所有模拟条件下都得到增强，与 78.3 ± 4.4 nm RMS 的带宽误差相比，在相同条件下运行的无延迟系统的预测误差在 19.9–40.0 nm RMS 范围内。