Author(s): Tao Wang; Kailin Yang; Xinlei Guo; Hui Fu; Yongxin Guo
Linked Author(s): Kailin Yang, Tao Wang, Xinlei Guo
Keywords: No Keywords
Abstract: The Inner Mongolia reach of the Yellow River lies at the northern part of the Yellow River basin. In this reach of the river, looking like a reversed "U", is easy for ice disaster to appear, such as flooding in the winter months. The timely and accurate forecast of ice conditions there is essential for protecting the urban and rural areas along the basin from being struck by possible ice-flooding disasters. However, in order to conduct ice condition forecasts, the freeze-up water temperature forecast in winter should be conducted at the first place. With its hybrid learning scheme, adaptive-network-based fuzzy inference system (ANFIS), constructed under the framework of the neural networks and fuzzy models, and the latter possess certain advantages over the former two, is convenient for modelling the nonlinear multivariable process; for instance, in the case of modelling the hydrological information variety. Consequently, ANFIS is applied to the freeze-up water temperature forecast in Inner Mongolia reach of the Yellow River including 4 hydrological stations, i. e the Shizuishan Station, Bayangaole Station, Shanhuhekou Station, and Toudaoguai Station. And the forecast results of water temperature are compared with the measured records in four hydrometric stations. Through such comparisons, it was discovered that the water temperature forecast results approximately agree with those of the field records. The ANFIS model is used for simulating the freeze-up water temperature forecast process in winter, and satisfactory results have been obtained.
Year: 2012