Automatic Clouds Observation Improved by an Artificial Neural Network

Abstract

This paper refers to a project aimed at building a device able to generate fully automatic meteorological weather reports (METAR) during the night at Swiss airports. Such reports include the description of sky conditions, namely, the heights and the amount of clouds at different layers, which may not be directly measured by conventional instruments. The authors present a cloud module that is specifically designed to provide the information on the clouds present in the sky. The originality of the present work is the use of a longwave radiometer, a pyrgeometer, to estimate the cloud amounts, whose processing is performed by an artificial neural network instead of empirical rules. Laser ceilometers are used to extract the bases of cloud layers by means of a heuristic processing. Results of this module show that information automatically produced by the module can be used as a good estimate of the clouds in a completely automatic METAR generator.