NPG Nonlinear Processes in Geophysics NPG Nonlin. Processes Geophys. 1607-7946 Copernicus Publications Göttingen, Germany 10.5194/npg-14-569-2007 An artificial neural network predictor for tropospheric surface duct phenomena Isaakidis S. A. 1 Dimou I. N. 2 Xenos T. D. 1 Dris N. A. 3 Aristotle University of Thessaloniki, Department of Electrical and Computer Engineering, 54006 Thessaloniki, Greece Technical University of Crete, Department of Electronics and Computer Engineering, 73100 Chania, Greece Hellenic National Meteorological Service (HNMS), 16777 Helliniko, Greece 03 09 2007 14 5 569 573 Copyright: © 2007 S. A. Isaakidis et al. 2007 This work is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Generic License. To view a copy of this licence, visit https://creativecommons.org/licenses/by-nc-sa/2.5/ This article is available from https://npg.copernicus.org/articles/14/569/2007/npg-14-569-2007.html The full text article is available as a PDF file from https://npg.copernicus.org/articles/14/569/2007/npg-14-569-2007.pdf

In this work, an artificial neural network (ANN) model is developed and used to predict the presence of ducting phenomena for a specific time, taking into account ground values of atmospheric pressure, relative humidity and temperature. A feed forward backpropagation ANN is implemented, which is trained, validated and tested using atmospheric radiosonde data from the Helliniko airport, for the period from 1991 to 2004. The network's quality and generality is assessed using the Area Under the Receiver Operating Characteristics (ROC) Curves (AUC), which resulted to a mean value of about 0.86 to 0.90, depending on the observation time. In order to validate the ANN results and to evaluate any further improvement options of the proposed method, the problem was additionally treated using Least Squares Support Vector Machine (LS-SVM) classifiers, trained and tested with identical data sets for direct performance comparison with the ANN. Furthermore, time series prediction and the effect of surface wind to the presence of tropospheric ducts appearance are discussed. The results show that the ANN model presented here performs efficiently and gives successful tropospheric ducts predictions.

 References Babin, S. M., Young, G. S., and Carton, J. E.: A New Model of the Oceanic Evaporation Duct. J. of Applied Meteorology, American Meteorological Society, 36, 193–204, 1997. Burges, C. J. C.: A Tutorial on Support Vector Machines for Pattern Recognition., Data Min. Knowl. Disc., 2, 121–167, 1998. Nello Cristianini, N. and Shawe-Taylor, J.: An Introduction to Support Vector Machines and other kernel-based learning methods, Cambridge University Press, 211–231, 2000. Fawcett, T.: ROC Graphs: Notes and Practical Considerations for Researchers. Technical Report, HP Laboratories, 16 March 2004. IEEE Std 211: IEEE Standard Definitions of Terms for Radio Wave Propagation, 29, 1997. Isaakidis S. A., Xenos T. D., and Dris N. A.: Tropospheric Ducting Phenomena over the Hellenic Region, Int. J. Commun. Syst., Wiley, 17, 337–346, 2004. Isaakidis, S. A. and Xenos, T. D.: "10 Years Analysis of Refractivity\indexRefractivity Variations", Ann. Geophys.-Italy (Annali di Geofisica), 47, 2004. ITU-R: The radio refractive index\indexRefractive index: its formula and refractivity data, Recommendation, P.453-9, 2003. Lear, M. W: Computing Atmospheric Scale Height\indexScale Height for Refraction Corrections, NASA Mission Planning and Analysis Division, Lyndon B. Johnson Space Centre, 1980. Musson-Genon, L., Gauthier, S., and Bruth, E.: A Simple Method to Determine Evaporation Duct Height in the Sea Surface boundary layer, Radio Science, 27, 635–644, 1992. Patterson, W. L., Hattan C. P., Lindem, G. E., Paulus, R. A., Hitney, H. V., Anderson, K. D., and Barrios, A. E.: Engineer's Refractive Effects Prediction Systems (EREPS) Version 3.0. NRaD Technical Document 2648, 8–9, May 1994. Paulus, R. A.: Practical Application of an Evaporation Duct Model, Radio Science, 20, 887–896, 1985. Suykens, J. A. K. and Vandewalle, J.: Least squares support vector machine classifiers, Neural Process Lett., 9, 293–300, 1999. Vapnik, V.: The Nature of Statistical Learning Theory, Springer-Verlag, ISBN 0-387-98780-0, 9–14, 1999.