27th Congress of International Council of the Aeronautical Sciences, 19 - 24 September 2010, Nice, France
Paper ICAS2010-P8.2

THE EXPERIMENTAL FORECAST FOR AIRPORT TOTAL CLOUD COVER USING THE LINEAR AND NONLINEAR MODULES

H. F. Wang, B. Huang*, J. W. Liu, Y. B. Hu, J. An, X. T. Wang
Beijing Aviation Meteorological Inst., China; *Beijing Aviation Meteorological Inst. & Physical Inst. Peiking Univ., China

Keywords: total cloud cover, explanation forecast, bp neural network, support vector machines

Airport total cloud cover categorical forecast modules were developed applying the nonlinear methods including the back propagation neural network (BPNN), support vector machines (SVM) etc. and the multivariate linear regression method, respectively. The experimental forecast was applied with the datasets in 2006, and the forecast accuracy of them was compared.

view full paper