Dynamical recurrent neural networks and pattern recognition methods for time series prediction: Application to seeing and temperature forecasting in the context of ESO's VLT astronomical weather station

A. Aussem, F. Murtagh, M. Sarazin

Research output: Contribution to journalArticle

9 Citations (Scopus)


The European Southern Observatory's planned Astronomical Weather Station for the Very Large Telescope which is currently under construction at Cerro Paranal in Chile includes (i) advance temperature prediction, which would permit air conditioning in the telescope enclosure to be preset as a function of the next night's expected temperature; and (ii) prediction of seeing, a few hours in advance, to allow flexible scheduling of the most appropriate instrumentation. Extensive data, collected since 1985, are being used to appraise various methodologies. A recurrent neural network is described, which uses arbitrary time-delayed connections to capture the dynamic of time series. This endows the model with a memory of its previous states. The resulting network is time- and space-recurrent, and generalizes most recurrent architectures. The performance of this network is discussed. The results are compared with the k-nearest neighbors method.

Original languageEnglish
Pages (from-to)357-374
Number of pages18
JournalVistas in Astronomy
Issue numberPart 3
Publication statusPublished - 1994
Externally publishedYes


Cite this