Editorial Type:
Article
Article Type:
Research Article

The Use of Sounding-Derived Indices for a Neural Network Short-Term Thunderstorm Forecast

Agostino Manzato Osservatorio Meteorologico Regionale, Agenzia Regionale per la Protezione dell’Ambiente del Friuli Venezia Giulia, Visco, Italy

Search for other papers by Agostino Manzato in
Current site
Google Scholar
PubMed Close
Print Publication:
01 Dec 2005
DOI:
https://doi.org/10.1175/WAF898.1
Page(s):
896–917
Restricted access

Abstract

In this paper several indices derived from atmospheric sounding data are used to develop a short-term thunderstorm forecast tool. The Udine (Italy) sounding (WMO code 16044, taken every 6 h, hereafter 6 h) is used to describe the initial conditions in which a thunderstorm may develop in the Friuli Venezia Giulia region. The tool forecasts the convective activity in the 6 h after the sounding is launched.

Sounding, lightning, and mesonet station data, from April to September of the years 1995–2002, were used to train and validate artificial neural networks (ANNs) and the data of 2003 were used as an independent test sample. Special emphasis was given to avoid one of the major ANN problems, that of data overfitting, which requires limiting the possible complexity of the ANN, that is, the total number of inputs (predictors) and of hidden neurons. To select the best input set, the training–validation mechanism was repeated in eight different ways.

Two types of ANNs were developed: the first is a classification model and is built for forecasting the thunderstorm occurrence, defined as the report of at least one cloud-to-ground lightning strike. If this first ANN forecasts convective activity, then a second ANN, built as a regression model, is used for forecasting the thunderstorm intensity. The relative operating characteristic (ROC) diagram and some parameters derived from a contingency table were used to compare the different classification performances. The linear cross-correlation coefficient, R2, was used to assess the performance of the regression ANNs.

The ANN inputs were not the only “raw” sounding-derived index values; in addition, two derived sets of variables, corresponding to the z scores and the “posterior probability” transformed data, were used as preprocessing methods. The last method yields the best results. The tool reported on here has been used operationally since 2001 in the regional meteorological office of the Friuli Venezia Giulia region [Osservatorio Meteorologico Regionale/Agenzia Regionale per la Protezione dell’Ambiente (OSMER/ARPA)].

Corresponding author address: Agostino Manzato, Osservatorio Meteorologico Regionale/Agenzia Regionale per la Protezione dell’Ambiente Friuli Venezia Giulia (OSMER/ARPA), Via Oberdan, 18/a, I-33040 Visco (UD), Italy. Email: agostino.manzato@osmer.fvg.it

Abstract

In this paper several indices derived from atmospheric sounding data are used to develop a short-term thunderstorm forecast tool. The Udine (Italy) sounding (WMO code 16044, taken every 6 h, hereafter 6 h) is used to describe the initial conditions in which a thunderstorm may develop in the Friuli Venezia Giulia region. The tool forecasts the convective activity in the 6 h after the sounding is launched.

Sounding, lightning, and mesonet station data, from April to September of the years 1995–2002, were used to train and validate artificial neural networks (ANNs) and the data of 2003 were used as an independent test sample. Special emphasis was given to avoid one of the major ANN problems, that of data overfitting, which requires limiting the possible complexity of the ANN, that is, the total number of inputs (predictors) and of hidden neurons. To select the best input set, the training–validation mechanism was repeated in eight different ways.

Two types of ANNs were developed: the first is a classification model and is built for forecasting the thunderstorm occurrence, defined as the report of at least one cloud-to-ground lightning strike. If this first ANN forecasts convective activity, then a second ANN, built as a regression model, is used for forecasting the thunderstorm intensity. The relative operating characteristic (ROC) diagram and some parameters derived from a contingency table were used to compare the different classification performances. The linear cross-correlation coefficient, R2, was used to assess the performance of the regression ANNs.

The ANN inputs were not the only “raw” sounding-derived index values; in addition, two derived sets of variables, corresponding to the z scores and the “posterior probability” transformed data, were used as preprocessing methods. The last method yields the best results. The tool reported on here has been used operationally since 2001 in the regional meteorological office of the Friuli Venezia Giulia region [Osservatorio Meteorologico Regionale/Agenzia Regionale per la Protezione dell’Ambiente (OSMER/ARPA)].

Corresponding author address: Agostino Manzato, Osservatorio Meteorologico Regionale/Agenzia Regionale per la Protezione dell’Ambiente Friuli Venezia Giulia (OSMER/ARPA), Via Oberdan, 18/a, I-33040 Visco (UD), Italy. Email: agostino.manzato@osmer.fvg.it

Save
Cover Weather and Forecasting
Weather and Forecasting

  • Amari, S., Murata N. , Müller K. R. , Finke M. , and Yang H. , 1996: Statistical theory of overtraining—Is cross-validation asymptotically effective? Advances in Neural Information Processing Systems, D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, Eds., Vol. 8, MIT Press, 176–182.

    • Search Google Scholar
    • Export Citation

  • Bishop, C. M., 1996: Neural Networks for Pattern Recognition. Clarendon Press, 482 pp.

  • Boyden, C. J., 1963: A simple instability index for use as a synoptic parameter. Meteor. Mag., 92 , 198–210.

  • Cherkassky, V., and Mulier F. , 1998: Learning from Data: Concepts, Theory, and Methods. John Wiley, 441 pp.

  • Corbet, J. M., Mueller C. , Burghart C. , Gould K. , and Granger G. , 1994: ZEB: Software for integration, display, and management of diverse environmental datasets. Bull. Amer. Meteor. Soc., 75 , 783–792.

    • Crossref
    • Search Google Scholar
    • Export Citation

  • Doswell C. A. III, , and Rasmussen E. , 1994: The effect of neglecting the virtual temperature correction on CAPE calculations. Wea. Forecasting, 9 , 625–629.

    • Crossref
    • Search Google Scholar
    • Export Citation

  • Duda, R. O., Hart P. E. , and Stork D. G. , 2000: Pattern Classification. 2d ed. John Wiley, 680 pp.

  • Efron, B., and Tibshirani R. , 1993: An Introduction to the Bootstrap. Chapman and Hall, 456 pp.

  • Flueck, J. A., 1987: A study of some measures of forecast verification. Preprints, 10th Conf. on Probability and Statistics in Atmospheric Sciences, Edmonton, AB, Canada, Amer. Meteor. Soc., 69–73.

  • Iorio, R., and Ferrari D. , 1996: 1995 descriptive statistics on lightning activity over Italy obtained by means of the Italian lightning detection system “CESI SIRF.” Proc. 23d Int. Conf. on Lightning Protection, Florence, Italy, 191–196.

  • Manzato, A., 2003: A climatology of instability indices derived from Friuli Venezia Giulia soundings, using three different methods. Atmos. Res., 67–68 , 417–454.

    • Search Google Scholar
    • Export Citation

  • Manzato, A., 2005: An odds ratio parameterization for ROC diagram and skill score indices. Wea. Forecasting, 20 , 918–930.

  • Manzato, A., and Morgan G. M. , 2003: Evaluating the sounding instability with the lifted parcel theory. Atmos. Res., 67–68 , 455–473.

    • Search Google Scholar
    • Export Citation

  • Marzban, C., 2000: A neural network for tornado diagnosis. Neural Comput. Appl., 9 , 133–141.

  • Marzban, C., cited. 2002: Neural network short course. [Available online at http://www.nhn.ou.edu/marzban.].

  • Marzban, C., and Witt A. , 2001: A Bayesian neural network for hail size prediction. Wea. Forecasting, 16 , 600–610.

  • Masters, T., 1993: Practical Neural Network Recipes in C++. Academic Press, 493 pp.

  • Masters, T., 1995: Neural, Novel and Hybrid Algorithms for Time Series Prediction. John Wiley, 514 pp.

  • McCann, D. W., 1992: A neural network short-term forecast of significant thunderstorms. Wea. Forecasting, 7 , 525–534.

  • Moninger, W. R., and Coathors, 1991: Shootout-89: A comparative evaluation of knowledge-based systems that forecast severe weather. Bull. Amer. Meteor. Soc., 72 , 1339–1354.

    • Crossref
    • Search Google Scholar
    • Export Citation

  • Richard, M. D., and Lippmann R. P. , 1991: Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Comput., 3 , 461–483.

    • Crossref
    • Search Google Scholar
    • Export Citation

  • Ripley, B. D., 1996: Pattern Recognition and Neural Networks. Cambridge University Press, 416 pp.

  • Rosenblatt, F., 1958: The Perceptron: A probabilistic model for information storage and organization in the brain. Psychol. Rev., 65 , 386–408.

  • Sarle, W., cited. 2002: Should I normalize/standardize/rescale the data? [Available online at http://www.faqs.org/faqs/ai-faq/neural-nets/part2/section-16.html.].

  • Stephenson, D. B., 2000: Use of the “odds ratio” for diagnosing forecast skill. Wea. Forecasting, 15 , 221–232.

  • Swets, J. A., 1973: The relative operating characteristic in psychology. Science, 182 , 900–1000.

  • Venables, W. N., and Ripley B. D. , 2002: Modern Applied Statistics with S-PLUS. 4th ed. Springer-Verlag, 495 pp.

  • Wilks, D. S., 1995: Statistical Methods in the Atmospheric Sciences. Academic Press, 467 pp.

All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 300 90 11
PDF Downloads 219 54 8