Monthly River Discharge Prediction by Wavelet Fuzzy Time Series Method


Başakın E. E., Özger M.

International Journal of Uncertainty, Fuzziness and Knowlege-Based Systems, cilt.29, sa.1, ss.17-35, 2021 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 29 Sayı: 1
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1142/s0218488521500021
  • Dergi Adı: International Journal of Uncertainty, Fuzziness and Knowlege-Based Systems
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Computer & Applied Sciences, zbMATH
  • Sayfa Sayıları: ss.17-35
  • Anahtar Kelimeler: Fuzzy time series, wavelet analysis, hydrology, machine learning, WATER-LEVEL FLUCTUATIONS, NEURO-FUZZY, FORECASTING ENROLLMENTS, INFERENCE SYSTEMS, HYBRID WAVELET, MODEL, RAINFALL, FLOW, NETWORK, OPTIMIZATION
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

© 2021 World Scientific Publishing Company.Prediction of river discharge is important for water resources management. Engineers have developed many physical and mathematical models for prediction of river discharge. The fact that physical hydrological models are site specific and include many parameters, has led researchers to work on mathematical black-box models. In this study, the fuzzy time series (FTS) method was used in the prediction of river discharge. The proposed method, which is employed for the first time in hydrology, allows to fast decision-making mechanism. The proposed algorithm, FTS, is used along with continuous wavelet transform (CWT) method to improve prediction performance. CWT, can be used as pre-Treatment technique, is able decompose concerned time series into several bands at different scales which allows to predict much more homogeneous series rather than complex flow discharge series. By considering various statistical success criteria, the wavelet transformed time series (WFTS) method performed quite high accurate predictions compared to the classical fuzzy time series method. Combining FTS with wavelet transform opens a new window in the fuzzy time series method applications that has ability to improve the prediction performance.