Department of Civil Eng., University of Qom, Qom, Iran.
Sci Total Environ. 2011 Jul 1;409(15):2917-28. doi: 10.1016/j.scitotenv.2010.11.028. Epub 2011 May 4.
In this research, a new wavelet artificial neural network (WANN) model was proposed for daily suspended sediment load (SSL) prediction in rivers. In the developed model, wavelet analysis was linked to an artificial neural network (ANN). For this purpose, daily observed time series of river discharge (Q) and SSL in Yadkin River at Yadkin College, NC station in the USA were decomposed to some sub-time series at different levels by wavelet analysis. Then, these sub-time series were imposed to the ANN technique for SSL time series modeling. To evaluate the model accuracy, the proposed model was compared with ANN, multi linear regression (MLR), and conventional sediment rating curve (SRC) models. The comparison of prediction accuracy of the models illustrated that the WANN was the most accurate model in SSL prediction. Results presented that the WANN model could satisfactorily simulate hysteresis phenomenon, acceptably estimate cumulative SSL, and reasonably predict high SSL values.
在这项研究中，提出了一种新的基于小波分析的人工神经网络（WANN）模型，用于预测河流的日悬浮泥沙负荷（SSL）。在开发的模型中，将小波分析与人工神经网络（ANN）联系起来。为此，通过小波分析将美国北卡罗来纳州雅德金学院 Yadkin 河的日流量（Q）和 SSL 的观测时间序列分解为不同级别下的一些子时间序列。然后，将这些子时间序列应用于 ANN 技术进行 SSL 时间序列建模。为了评估模型的准确性，将所提出的模型与 ANN、多元线性回归（MLR）和传统的泥沙等级曲线（SRC）模型进行了比较。模型预测精度的比较表明，WANN 是 SSL 预测中最准确的模型。结果表明，WANN 模型可以很好地模拟滞后现象，可接受地估计累积 SSL，并合理地预测高 SSL 值。
