Author(s): Jingyi Chen; Dimitri. P. Solomatine; Yi Xu
Linked Author(s):
Keywords: Uncertainty prediction; Residual error; UNEEC; Instance-based learning; K-nearest neighbor; Locally weighted learning; Talagrand diagram
Abstract: A novel version of UNEEC method using instance-based learning is developed. This method is only analogous locally and all calculation is deferred until classification. During the developing process, two thoughts are applied to select the neighbor for uncertainty prediction: one is choosing the optimized k values for neighbors and the other one is choosing the optimized distance weight function using locally weighted learning method. Say specifically, to get more flexible k value for neighbors, the creative ideal combining optimized PICP and limited distance is applied audaciously. What’s more, one smoothing weighted function, which is improved from Gaussian kernel with additional parameter, is determined to computer the weight of each potential neighbor. After building the uncertainty predicted model, the Talagrand diagram will be plotted to compare the performances of several different residual uncertainty prediction methods such as UNEEC and DUMBRAE. Combining the meteorological model and hydrological model then the residual uncertainty prediction results can be applied to get the long-time forecasting runoff in the downstream of the catchment.
Year: 2015