Predictive wavefront control is an important and rapidly developing field of adaptive optics (AO). Through the prediction of future wavefront effects, the inherent AO system servo-lag caused by the measurement, computation, and application of the wavefront correction can be significantly mitigated. This lag can impact the final delivered science image, including reduced strehl and contrast, and inhibits our ability to reliably use faint guide stars. We summarize here a novel method for training deep neural networks for predictive control based on an adversarial prior. Unlike previous methods in the literature, which have shown results based on previously generated data or for open-loop systems, we demonstrate our network’s performance simulated in closed loop. Our models are able to both reduce effects induced by servo-lag and push the faint end of reliable control with natural guide stars, improving K-band Strehl performance compared to classical methods by over 55 per cent for 16th magnitude guide stars on an 8-m telescope. We further show that LSTM based approaches may be better suited in high-contrast scenarios where servo-lag error is most pronounced, while traditional feed forward models are better suited for high noise scenarios. Finally, we discuss future strategies for implementing our system in real-time and on astronomical telescope systems.

中文翻译：

---

卷积神经网络自适应光学系统的闭环预测控制

预测波前控制是自适应光学（AO）的一个重要且快速发展的领域。通过对未来波前效应的预测，可以显着减轻由波前校正的测量、计算和应用引起的固有 AO 系统伺服滞后。这种滞后会影响最终交付的科学图像，包括降低强度和对比度，并抑制我们可靠使用微弱引导星的能力。我们在这里总结了一种基于对抗性先验训练深度神经网络进行预测控制的新方法。与文献中先前的方法不同，这些方法基于先前生成的数据或开环系统显示结果，我们展示了我们的网络在闭环中模拟的性能。我们的模型既能减少伺服滞后引起的影响，又能用自然导星推动可靠控制的微弱末端，与经典方法相比，将 K 波段 Strehl 性能提高 55% 以上，用于 8- 星等 16 等导星米望远镜。我们进一步表明，基于 LSTM 的方法可能更适合伺服滞后误差最明显的高对比度场景，而传统的前馈模型更适合高噪声场景。最后，我们讨论了在实时和天文望远镜系统上实施我们的系统的未来策略。我们进一步表明，基于 LSTM 的方法可能更适合伺服滞后误差最明显的高对比度场景，而传统的前馈模型更适合高噪声场景。最后，我们讨论了在实时和天文望远镜系统上实施我们的系统的未来策略。我们进一步表明，基于 LSTM 的方法可能更适合伺服滞后误差最明显的高对比度场景，而传统的前馈模型更适合高噪声场景。最后，我们讨论了在实时和天文望远镜系统上实施我们的系统的未来策略。