Data-driven models for monthly streamflow time series prediction

Authors:
C. L. Wu;K. W. Chau
Affiliations:
Department of Civil and Structural Engineering, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, People's Republic of China;Department of Civil and Structural Engineering, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, People's Republic of China
Venue:
Engineering Applications of Artificial Intelligence
Year:
2010

Citing 4
Cited 3

Extracting qualitative dynamics from experimental data

Physica D
Instance-Based Learning Algorithms

Machine Learning
State space reconstruction in the presence of noise

Physica D
State space reconstruction parameters in the analysis of chaotic time series—the role of the time window length

Physica D

Forecasting daily lake levels using artificial intelligence approaches

Computers & Geosciences
An innovative method for dynamic update of initial water table in XXT model based on neural network technique

Applied Soft Computing
Neo-fuzzy neuron model for seasonal rainfall forecast: A case study of Ceara's eight homogenous regions

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Data-driven techniques such as Auto-Regressive Moving Average (ARMA), K-Nearest-Neighbors (KNN), and Artificial Neural Networks (ANN), are widely applied to hydrologic time series prediction. This paper investigates different data-driven models to determine the optimal approach of predicting monthly streamflow time series. Four sets of data from different locations of People's Republic of China (Xiangjiaba, Cuntan, Manwan, and Danjiangkou) are applied for the investigation process. Correlation integral and False Nearest Neighbors (FNN) are first employed for Phase Space Reconstruction (PSR). Four models, ARMA, ANN, KNN, and Phase Space Reconstruction-based Artificial Neural Networks (ANN-PSR) are then compared by one-month-ahead forecast using Cuntan and Danjiangkou data. The KNN model performs the best among the four models, but only exhibits weak superiority to ARMA. Further analysis demonstrates that a low correlation between model inputs and outputs could be the main reason to restrict the power of ANN. A Moving Average Artificial Neural Networks (MA-ANN), using the moving average of streamflow series as inputs, is also proposed in this study. The results show that the MA-ANN has a significant improvement on the forecast accuracy compared with the original four models. This is mainly due to the improvement of correlation between inputs and outputs depending on the moving average operation. The optimal memory lengths of the moving average were three and six for Cuntan and Danjiangkou, respectively, when the optimal model inputs are recognized as the previous twelve months.