The Ametis II project


Recognition of Cloud Amounts with Neural Networks

Objective

The aim of the project is to build an automatic system capable of recognizing the cloud amounts (during the night), from data collected by various meteorological instruments including pyrgeometers and ceilometers. More precisely, the system must detect the number of cloud layers, and for each layer it must give its height and cloudiness. This software is to be part of a global automatic system, developed by the Swiss Meteorological Institute, in the project Ametis II. The aim of the Ametis II system is to automate, during night time, the generation of standardized messages (METARs) containing information about the meteorological situation in the immediate vicinity of airports. The first Ametis II prototype is being installed at the Zurich airport.


The Ametis II system

Results

The first results obtained were on the recognition of the total cloudiness, which is a meteorological value of interest. The neural network performs a recognition rate of 90% on the training set and 88% on a test set of unlearned examples, with 9 hidden neurons.

The whole system detects in addition the heights of several cloud layers and estimates the cloud amount of each one separately. It performs a recognition rate of 81% on a one-year test set.

Methods

The heart of the system is a feedforward multilayer neural network, trained to recognize the cloud amount of a cloud layer. We developed and used a quasi-Newtonian second order optimization method to perform training. Special attention was devoted to the preprocessing of the large amount of heterogeneous data available.


Architecture of the neural network based Clouds Recognition Module

The rest of the system consists in processings by rules to detect the number and heights of the cloud layers, and to produce a METAR compliant output.

Partners

This project is part of the Ametis II project of the Swiss Institute of Meteorology (ISM), which aims at generating automatically complete METAR messages. The current project designed the Clouds module of this global system. Collaboration with Technikum Rapperswil took place for the integration of our module into the Ametis II system. All data was provided by the ISM.

Validation

The validation of the Clouds module is in progress, as the development of the Ametis II system. It will be tested at Zurich airport from summer 1996 while the whole system will be completed. In 1997 the fully automated observations will be operationally displayed.

Future perspectives

The next step will be the developpement of an automated observation system at Geneva airport (1998-2001). According to the success of this transfer of technology to another airport, the AMETIS 2 concept could be generalised to other secondary airports in Switzerland, after year 2000.

Publications

F. Aviolat, D. Cattani, and T. Cornu. Recognition of meteorological situations with neural networks. In Proceedings of the Third Biennial Joint Conference on Engineering systems Design & Analysis, ESDA'96, Montpellier, July 1996. Available on-line. Abstract.


Thierry Cornu
Tue Aug 6 19:42:28 MET DST 1996