Weddell, S.J.Webb, R.Y.2009-06-152009-06-152008Weddell, S.J., Webb, R.Y. (2008) Reservoir Computing for Prediction of the Spatially-Variant Point Spread Function. IEEE Journal of Selected Topics in Signal Processing, 2(5), pp. 624-634.1932-4553http://hdl.handle.net/10092/2555A new method is presented which provides prediction of the spatially variant point spread function for the restoration of astronomical images, distorted by atmospheric turbulence when viewed using ground-based telescopes. Our approach uses reservoir computing to firstly learn the spatio-temporal evolution of aberrations caused by turbulence, and secondly, predicts the space-varying point spread function (PSF) for application of widely-used deconvolution algorithms, resulting in the restoration of astronomical images. In this article, a reservoir-based, recurrent neural network is used to predict modal aberrations that comprise the spatially variant PSF over a wide field-of-view using a time-series ensemble from multiple reference beacons.enSignal ProcessingAdaptive OpticsNeural NetworksFields of Research::240000 Physical Sciences::240100 Astronomical Sciences::240199 Astronomical sciences not elsewhere classifiedJournal ArticleFields of Research::240000 Physical Sciences::240400 Optical Physics::240401 Optics and opto-electronic physicshttps://doi.org/10.1109/JSTSP.2008.2004218