C. L. Wu

Predicting monthly streamflow using data‐driven models coupled with data‐preprocessing techniques

[1] In this paper, the accuracy performance of monthly streamflow forecasts is discussed when using data-driven modeling techniques on the streamflow series. A crisp distributed support vectors regression (CDSVR) model was proposed for monthly streamflow prediction in comparison with four other models: autoregressive moving average (ARMA), K-nearest neighbors (KNN), artificial neural networks (ANNs), and crisp distributed artificial neural networks (CDANN). With respect to distributed models of CDSVR and CDANN, the fuzzy C-means (FCM) clustering technique first split the flow data into three subsets (low, medium, and high levels) according to the magnitudes of the data, and then three single SVRs (or ANNs) were fitted to three subsets. This paper gives a detailed analysis on reconstruction of dynamics that was used to identify the configuration of all models except for ARMA. To improve the model performance, the data-preprocessing techniques of singular spectrum analysis (SSA) and/or moving average (MA) were coupled with all five models. Some discussions were presented (1) on the number of neighbors in KNN; (2) on the configuration of ANN; and (3) on the investigation of effects of MA and SSA. Two streamflow series from different locations in China (Xiangjiaba and Danjiangkou) were applied for the analysis of forecasting. Forecasts were conducted at four different horizons (1-, 3-, 6-, and 1 2-month-ahead forecasts). The results showed that models fed by preprocessed data performed better than models fed by original data, and CDSVR outperformed other models except for at a 6-month-ahead horizon for Danjiangkou. For the perspective of streamflow series, the SSA exhibited better effects on Danjingkou data because its raw discharge series was more complex than the discharge of Xiangjiaba. The MA considerably improved the performance of ANN, CDANN, and CDSVR by adjusting the correlation relationship between input components and output of models. It was also found that the performance of CDSVR deteriorated with the increase of the forecast horizon.

Data-driven models for monthly streamflow time series prediction

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 Peoples 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.

Prediction of rainfall time series using modular soft computingmethods

In this paper, several soft computing approaches were employed for rainfall prediction. Two aspects were considered to improve the accuracy of rainfall prediction: (1)carrying out a data-preprocessing procedure and (2)adopting a modular modeling method. The proposed preprocessing techniques included moving average (MA) and singular spectrum analysis (SSA). The modular models were composed of local support vectors regression (SVR) models or/and local artificial neural networks (ANN) models. In the process of rainfall forecasting, the ANN was first used to choose data-preprocessing method from MA and SSA. Modular models involved preprocessing the training data into three crisp subsets (low, medium and high levels) according to the magnitudes of the training data, and finally two SVRs were performed in the medium and high-level subsets whereas ANN or SVR was involved in training and predicting the low-level subset. For daily rainfall record, the low-level subset tended to be modeled by the ANN because it was overwhelming in the training data, which is based on the fact that the ANN is very efficient in training large-size samples due to its parallel information processing configuration. Four rainfall time series consisting of two monthly rainfalls and two daily rainfalls from different regions were utilized to evaluate modular models at 1-day, 2-day, and 3-day lead-time with the persistence method and the global ANN as benchmarks. Results showed that the MA was superior to the SSA when they were coupled with the ANN. Comparison results indicated that modular models (referred to as ANN-SVR for daily rainfall simulations and MSVR for monthly rainfall simulations) outperformed other models. The ANN-MA also displayed considerable accuracy in rainfall forecasts compared with the benchmark.

A flood forecasting neural network model with genetic algorithm

It will be useful to attain a quick and accurate flood forecasting, particularly in a flood-prone region. The accomplishment of this objective can have far reaching significance by extending the lead time for issuing disaster warnings and furnishing ample time for citizens in vulnerable areas to take appropriate action, such as evacuation. In this paper, a novel hybrid model based on recent artificial intelligence technology, namely, a genetic algorithm (GA)-based artificial neural network (ANN), is employed for flood forecasting. As a case study, the model is applied to a prototype channel reach of the Yangtze River in China. Water levels at the downstream station, Han-Kou, are forecasted on the basis of water levels with lead times at the upstream station, Luo-Shan. An empirical linear regression model, a conventional ANN model and a GA model are used as the benchmarks for comparison of performances. The results reveal that the hybrid GA-based ANN algorithm, under cautious treatment to avoid over-fitting, is able to produce better accuracy in performance, although at the expense of additional modelling parameters and possibly slightly longer computation time.

Mathematical model of water quality rehabilitation with rainwater utilisation: a case study at Haigang

This paper presents a mathematical model of water quality rehabilitation by utilising rainwater, which is separated into initial polluted rainwater and later unpolluted rainwater. The planned Haigang city, belonging to Shanghai metropolis in China, is taken as a case example. An analysis is made on how to utilise rainwater and appraise its function in a water quality rehabilitation scheme. It is demonstrated that this method can significantly reduce both project investment and operation costs. Moreover, appropriate drainage plan scheme is presented to address the initial polluted rainwater problem. Thus, the conflict between drainage and rainwater utilisation can be resolved appropriately.

Evaluation of several algorithms in forecasting flood

Precise flood forecasting is desirable so as to have more lead time for taking appropriate prevention measures as well as evacuation actions. Although conceptual prediction models have apparent advantages in assisting physical understandings of the hydrological process, the spatial and temporal variability of characteristics of watershed and the number of variables involved in the modeling of the physical processes render them difficult to be manipulated other than by specialists. In this study, two hybrid models, namely, based on genetic algorithm-based artificial neural network and adaptive-network-based fuzzy inference system algorithms, are employed for flood forecasting in a channel reach of the Yangtze River. The new contributions made by this paper are the application of these two algorithms on flood forecasting problems in real prototype cases and the comparison of their performances with a benchmarking linear regression model in this field. It is found that these hybrid algorithms with a “black-box” approach are worthy tools since they not only explore a new solution approach but also demonstrate good accuracy performance.