Using artificial neural networks (ANN) for open-loop tomography
James Osborn, Francisco Javier De Cos Juez, Dani Guzman, Timothy Butterley, Richard Myers, Andres Guesalaga and Jesus Laine
Universidad Catolica, Univeristy of Durham and Universidad de Oviedo
The next generation of adaptive optics (AO) systems require tomographic techniques in order to correct for atmospheric turbulence along lines of sight separated from the guide stars. Multi-object adaptive optics (MOAO) is one such technique. Here, we present a method which uses an artificial neural network (ANN) to reconstruct the target phase given off-axis references sources. This method does not require any input of the turbulence profile and is therefore less susceptible to changing conditions than some existing methods. We compare our ANN method with a standard least squares type matrix multiplication method (MVM) in simulation and find that the tomographic error is similar to the MVM method. In changing conditions the tomographic error increases for MVM but remains constant with the ANN model and no large matrix inversions are required.