论文部分内容阅读
为解决降水资源预测复杂的问题,建立了具有物理意义的新预测模型,即利用集合经验模态分解(EEMD)方法,分解降水资源并识别其演变模式,获得各本征模函数(IMF),然后结合最近邻抽样回归模型(NNBR)对数据进行预测分析,汇总相应的计算结果,从而构成了EEMD-NNBR降水预测模型。以无锡市惠山区的降水序列资料为例,采用EEMD-NNBR模型预测降水资源,并与单一的NNBR模型预测值进行对比分析。结果表明,所建模型稳定性较好,能合理预测水资源演变趋势,提高降水资源预测精度,具有一定的应用价值。
In order to solve the problem of complex prediction of precipitation resources, a new prediction model with physical meaning is established, that is, the EEMD method is used to decompose precipitation resources and identify their evolution patterns, and obtain the IMFs, Then, the data are predicted and analyzed by using the nearest neighbor sampling regression model (NNBR), and the corresponding calculation results are summarized to form the EEMD-NNBR precipitation forecasting model. Taking the precipitation sequence data of Huishan District in Wuxi City as an example, the rainfall resources were predicted by EEMD-NNBR model and compared with the predicted value of a single NNBR model. The results show that the stability of the model is good, which can reasonably predict the evolution trend of water resources and improve the prediction accuracy of precipitation resources, which has a certain application value.