Title :
Sensitivity analysis on neural networks for meteorological variable forecasting
Author :
Castellanos, J. ; Pazos, A. ; Ríos, J. ; Zafra, J.L.
Author_Institution :
Fac. de Inf., Univ. Politecnica de Madrid, Spain
Abstract :
The problem that arises in a neural network with many inputs is being able to eliminate the irrelevant ones. In the particular case of short-term weather forecasting, there are variables that may have little or no impact on the forecasts. A technique of sensitivity analysis of outputs over inputs has been applied to the trained network. Thus the most relevant inputs have been determined, as have less important inputs that can be eliminated. By employing this technique, a smaller sized neural network is obtained which also has a greater capacity for generalization
Keywords :
generalisation (artificial intelligence); geophysics computing; neural nets; sensitivity analysis; weather forecasting; generalization; meteorological variable forecasting; neural networks; sensitivity analysis; short-term weather forecasting; Equations; Land surface temperature; Meteorology; Neural networks; Neurons; Predictive models; Satellite ground stations; Sensitivity analysis; Testing; Weather forecasting;
Conference_Titel :
Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop
Conference_Location :
Ermioni
Print_ISBN :
0-7803-2026-3
DOI :
10.1109/NNSP.1994.366007