On the Level of Precision of the Wavelet Neural Network in Rainfall Analysis

Authors

  • Christopher Godwin Udomboso Department of Statistics University of Ibadan, Ibadan, Nigeria
  • Godwin Nwazu Amahia Department of Statistics University of Ibadan, Ibadan, Nigeria
  • Isaac Kwame Dontwi Department of Mathematical Science Kwame Nkrumah University of Science and Technology, Kumasi, Ghana

Keywords:

Artificial neural network, rainfall modelling, continuous wavelet transform

Abstract

This research combines the efficiency of the artificial neural network and wavelet transform in modelling rainfall.  The data used were decomposed into continuous wavelet signals on a scale of 48. Each of the decomposed series was subjected to correlation test with the original data.  Instead of using all the series, ten series were selected on the basis of high correlation with the original data. These series included CWT 1, CWT 2, CWT 4, CWT 3, CWT 6, CWT 8, CWT 5, CWT 10, CWT 12, and CWT 7 (according to rank). The analysis showed that except in extremely rare cases, all the series performed optimally compared to the original data.  The result of the study has been able to show that using the continuous wavelet transform in the ANN technique, a better performance of the network is observed.

Downloads

Published

2021-07-10

Issue

Vol. 13 No. 1 (2014): Journal of Science Research

Section

Articles