Monthly water demand prediction using wavelet transform, first-order differencing and linear detrending techniques based on multilayer perceptron models

Altunkaynak A., Nigussie T. A.

URBAN WATER JOURNAL, vol.15, no.2, pp.177-181, 2018 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 15 Issue: 2
  • Publication Date: 2018
  • Doi Number: 10.1080/1573062x.2018.1424219
  • Journal Name: URBAN WATER JOURNAL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.177-181
  • Istanbul Technical University Affiliated: Yes

Abstract

In this study, combined Discrete Wavelet Transform-Multilayer Perceptron (DWT-MP), combined First-Order Differencing-Multilayer Perceptron (FOD-MP) and combined Linear Detrending-Multilayer Perceptron (LD-MP) were developed and compared with stand-alone Multilayer Perceptron (MP) model for predicting monthly water consumption of Istanbul. The performance of these models were assessed by using coefficient of determination (R-2), root mean square error (RMSE) and the Nash-Sutcliffe coefficient of efficiency (CE) as evaluation criteria. The study showed that DWT-MP could be used for forecasting the monthly water demand of Istanbul for only up to prediction lead-time of 3 months. However, FOD-MP was found to perform very well up to 12months. It can be concluded from the results of the study that First-Order Differencing (FOD) is a reliable pre-processing technique for monthly water demand prediction.