Hydrological Sciences Journal, Volume (66), No (9), Year (2021-7) , Pages (1457-1474)

Title : ( Improving daily stochastic streamflow prediction: comparison of novel hybrid data-mining algorithms )

Authors: Khabat Khosravi , Ali Golkarian , Martijn J. Booij , Rahim Barzegar , Wei Sun , Zaher Mundher Yaseen , Amir Mosavi ,

Access to full-text not allowed by authors

Citation: BibTeX | EndNote

Abstract

In the current paper, the efficiency of three new standalone data mining algorithms [e.g., M5P, Random Forest (RF), M5Rule (M5R)] and six novel hybrid algorithms of Bagging, BA (BA-M5P, BA-RF and BA-M5R) and Attribute Selected Classifier, ASC (ASC-M5P, ASC-RF and ASC-M5R) for streamflow prediction were assessed and compared with autoregressive integrated moving average (ARIMA) model as a benchmark. The models used precipitation (P) and streamflow (Q) data from 1979-2012 for training and validation (70% and 30% of data, respectively). Different input combinations were prepared using both P and Q with different lag times. The best input combination proved to be that in which all the data were used (i.e., R and Q –with lag times). Overall, employing Q with different lag times proved to be more effective than using only P as input for streamflow prediction. Although all models showed very good predictive power, the BA-M5P outperformed the other models.

Keywords

streamflow modelling; M5P; random forest; M5Rule; bagging; Attribute Selected Classifier; data mining; Taleghan catchment
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@article{paperid:1085633,
author = {Khabat Khosravi and Golkarian, Ali and Martijn J. Booij and Rahim Barzegar and Wei Sun and Zaher Mundher Yaseen and Amir Mosavi},
title = {Improving daily stochastic streamflow prediction: comparison of novel hybrid data-mining algorithms},
journal = {Hydrological Sciences Journal},
year = {2021},
volume = {66},
number = {9},
month = {July},
issn = {0262-6667},
pages = {1457--1474},
numpages = {17},
keywords = {streamflow modelling; M5P; random forest; M5Rule; bagging; Attribute Selected Classifier; data mining; Taleghan catchment},
}

[Download]

%0 Journal Article
%T Improving daily stochastic streamflow prediction: comparison of novel hybrid data-mining algorithms
%A Khabat Khosravi
%A Golkarian, Ali
%A Martijn J. Booij
%A Rahim Barzegar
%A Wei Sun
%A Zaher Mundher Yaseen
%A Amir Mosavi
%J Hydrological Sciences Journal
%@ 0262-6667
%D 2021

[Download]