Automatic Clouds Observation Improved by an Artificial Neural Network

Frédéric Aviolat Operations Research, Department of Mathematics, Swiss Federal Institute of Technology, Lausanne, Switzerland

Search for other papers by Frédéric Aviolat in
Current site
Google Scholar
PubMed
Close
,
Thierry Cornu MANTRA Centre for Neuromimetic Systems, Swiss Federal Institute of Technology, Lausanne, Switzerland

Search for other papers by Thierry Cornu in
Current site
Google Scholar
PubMed
Close
, and
Daniel Cattani Geneva Meteorological Centre, Swiss Meteorological Institute, Geneva, Switzerland

Search for other papers by Daniel Cattani in
Current site
Google Scholar
PubMed
Close
Restricted access

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.

Corresponding author address: Dr. Daniel Cattani, Geneva Meteorological Centre, SMI-Case Postale 176, 1215 Geneva 15, Switzerland.

Email: cat@cmg.sma.ch

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.

Corresponding author address: Dr. Daniel Cattani, Geneva Meteorological Centre, SMI-Case Postale 176, 1215 Geneva 15, Switzerland.

Email: cat@cmg.sma.ch

Save
  • Albisser, P., 1983: Abschätzung der nächtlichen; Gesamtbewölkung mit Hilfe yon ASTA-Daten (Estimation of nightly total cloudiness with the help of ASTA data). Swiss Meteorological Institute Tech. Rep. 116, 50 pp. [Available from Swiss Meteorological Institute, Postfach 514, CH-8044, Zürich, Switzerland.].

  • Ambrosetti, P., 1991: Einsatz eines Pyrgeometers zur Bestimmung des Bewölkungsverhä<nisse (Use of pyrgeometers for the determination of sky conditions). Swiss Meteorological Institute Tech. Rep. 168, 32 pp. [Available from Swiss Meteorological Institute, Postfach 514, CH-8044, Zürich, Switzerland.].

  • Bankert, R. L., 1994: Cloud classification of a AVHRR imagery in maritime regions using a probabilistic neural network. J. Appl. Meteor.,33, 909–918.

    • Crossref
    • Export Citation
  • Battiti, R., 1992: First- and second-order methods for learning: Between steepest descent and Newton’s method. Neural Comput.,4, 141–166.

    • Crossref
    • Export Citation
  • Bishop, M. A., 1995: Neural Networks for Pattern Recognition. Clarendon Press, 482 pp.

    • Crossref
    • Export Citation
  • Brunt, D., 1932: Notes on radiation in the atmosphere. Quart. J. Roy. Meteor. Soc.,58, 389–420.

    • Crossref
    • Export Citation
  • Cornelius, R., and R. Gagnon, 1993: Artificial neural networks for radar data feature recognition. Preprints, 26th Conf. on Radar Meteorology, Norman, OK, Amer. Meteor. Soc., 340–342.

  • Czeplak, G., and F. Kasten, 1987: Parametrisierung der atmosphärischen Wä®estrashlung bei bewölktem Himmel (Parameterization of the atmospheric heat radiation in cloudy sky conditions). Meteor. Rundsch.,40 (6), 184–187.

  • Frankel, D., I. Schiller, J. S. Draper, and A. A. Barnes, 1990: Investigation of the prediction of lightning strikes using neural networks. Preprints, 16th Conf. on Severe Local Storms, Kananaskis Provincial Park, AB, Canada, Amer. Meteor. Soc., 7–11.

  • Gulf, A. D., and J. H. Gash, 1993: Longwave radiation from clear skies in Niger: A comparison of observations with simple formulas. J. Appl. Meteor.,32, 539–;547.

    • Crossref
    • Export Citation
  • Hertz, J., A. Krogh, and R. G. Palmer, 1991: Introduction to the Theory of Neural Computation. Addison-Wesley, 327 pp.

  • Hornik, K., M. Stinchcombe, and H. White, 1989: Multilayer feedforward networks are universal approximators. Neural Networks,4, 251–257.

    • Crossref
    • Export Citation
  • Idso, S., and R. Jackson, 1969: Thermal radiation from the atmosphere. J. Geophys. Res.,74 (23), 5397–5403.

    • Crossref
    • Export Citation
  • Kasten, F., and G. Czeplak, 1980: Solar and terrestrial radiation dependent on the amount and type of cloud. Sol. Energy,24, 177–189.

    • Crossref
    • Export Citation
  • le Cun, Y., 1985: A learning scheme for asymmetric threshold networks. Proc. Cognitiva Conf. 85, Paris, France, CESTA, 599–604.

  • Leshno, M., V. Y. Lin, A. Pinkus, and S. Schocken, 1993: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks,6 (6), 861–867.

    • Crossref
    • Export Citation
  • Marzban, C., and G. Stumpf, 1995: A neural network for tornado prediction based on Doppler radar-derived attributes. J. Appl. Meteor.,35, 617–626.

    • Crossref
    • Export Citation
  • Nadolski, V., 1995: United States moves ahead with deployment of the Automated Surface Observing System. OACI J.,50 (8), 10–11.

  • Pankiewicz, G., 1995: Pattern recognition techniques for the identification of cloud and cloud systems. Meteor. Appl.,2, 257–271.

    • Crossref
    • Export Citation
  • Peak, J. E., and P. M. Tag, 1994: Segmentation of satellite imagery using hierarchical thresholding and neural networks. J. Appl. Meteor.,33, 605–616.

    • Crossref
    • Export Citation
  • Rumelhart, D., G. Hinton, and R. Williams, 1986: Learning internal representations by error propagation. Parallel Distributed Processings: Explorations in the Microstructure of Cognition, Vol. 1, Foundations, D. Rumelhart, J. McClelland, and the PDP Research Group, Eds., The MIT Press, 318–362.

    • Crossref
    • Export Citation
  • Shanno, D., 1978: Conjugate gradient methods with inexact searches. Math. Operations Res.,3 (3), 244–256.

    • Crossref
    • Export Citation
  • Steinhorst, G., and W. van Dijk, 1994: Automated weather observation systems find increasing acceptance at major airports. OACI J.,49 (8), 12–14.

  • WMO, 1993: Manual on codes. World Meteorological Organization Tech. Publ. 306, Vol. I, 46–66. [Available from World Meteorological Organization, 41 avenue Giuseppe Motta, CP-2300, CH-1211 Geneva, Switzerland.].

All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 254 45 2
PDF Downloads 63 23 2