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.

Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named “CARMEN” are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances.

Context. The statistical analysis of large sample of strong lensing events can be a powerful tool to extract astrophysical and/or cosmological valuable information. However, the number of such events is still relatively low, mostly because of the lengthily observational validation process on individual events. Aims. In this work we propose a new methodology with a statistical selection approach in order to increase by a factor of ∼ 5 the number of such events. Although the methodology can be applied to address several selection problems, it has particular benefits in the case of the identification of strongly lensed galaxies: objectivity, minimal initial constrains in the main parameter space, preservation of the statistical properties. Methods. The proposed methodology is based on the Bhattacharyya distance as a measure of the similarity between probability distributions of properties of two different cross-matched galaxies. The particular implementation for the aim of this work is called SHALOS and it combines the information of four different properties of the pair of galaxies: angular separation, luminosity percentile, redshift and optical/sub-mm flux density ratio. Results. The SHALOS method provided a ranked list of strongly lensed galaxies. The number of candidates for the final associated probability, P tot > 0.7, is 447 with an estimated mean amplification factor of 3.12 for an halo with a typical cluster mass. Additional statistical properties of the SHALOS candidates, as the correlation function or the source number counts, are in agreement with previous results indicating the statistical lensing nature of the selected sample.

No abstract