Long‐term streamflow forecasting using artificial neural network based on preprocessing technique

Abstract

Artificial neural network (ANN) combined with signal decomposing methods is effective for long‐term streamflow time series forecasting. ANN is a kind of machine learning method utilized widely for streamflow time series, and which performs well in forecasting nonstationary time series without the need of physical analysis for complex and dynamic hydrological processes. Most studies take multiple factors determining the streamflow as inputs such as rainfall. In this study, a long‐term streamflow forecasting model depending only on the historical streamflow data is proposed. Various preprocessing techniques, including empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD) and discrete wavelet transform (DWT), are first used to decompose the streamflow time series into simple components with different timescale characteristics, and the relation between these components and the original streamflow at the next time step is analyzed by ANN. Hybrid models EMD‐ANN, EEMD‐ANN and DWT‐ANN are developed in this study for long‐term daily streamflow forecasting, and performance measures root mean square error (RMSE), mean absolute percentage error (MAPE) and Nash–Sutcliffe efficiency (NSE) indicate that the proposed EEMD‐ANN method performs better than EMD‐ANN and DWT‐ANN models, especially in high flow forecasting.

An Ensemble Hybrid Forecasting Model for Annual Runoff Based on Sample Entropy, Secondary Decomposition, and Long Short-Term Memory Neural Network

“…Qiu et al (2020 developed a novel hydrological implementation of emotional ANN model for daily rainfall-runoff modeling. Li et al (2019) studied the performance of several preprocessing techniques based on ANN for long-term streamflow forecasting.…”

Enhancing the Prediction Accuracy of Data-Driven Models for Monthly Streamflow in Urmia Lake Basin Based upon the Autoregressive Conditionally Heteroskedastic Time-Series Model

“…The main aim of OPELM [58] is to minimize β that is equivalent to maximization of 2 ||β|| . As discussed in [59], utilizing OPELM algorithms can diminish the time for training models, and i and t also have simpler algorithms.…”

“…So, hydrological modeling can be efficient in order to analyze, understand, and explore solutions for sustainable water management in order to support decision-makers and operational water managers [1]. In recent years, many water-experts have tried to use a range of methods for predicting hydrological components such as streamflow [2]. The prediction of streamflow is essential in many aspects of water resources management, for example, reservoir operation and allocation.…”

Runoff Prediction and Analysis Based on Improved CEEMDAN-OS-QR-ELM

“…However, in the process of EMD decomposition, modal aliasing and end effects often appear [23,24,25] . Ensemble empirical mode decomposition (EEMD) can effectively solve the problem of EMD modal aliasing and is well applied in the field of runoff prediction [26] . This involves the Combination of EEMD and ANN to build an EEMD-ANN model, using the RMSE and mean absolute percentage error (MAPE).…”