一种极端降水预测方法研究

Research on a prediction method of extreme precipitation

为了提高极端降水量的预测精度,将小波分析、支持向量机以及遗传算法相结合,建立了一种极端降水预测模型。首先利用小波变换对极端降水数据进行分解,分离出序列中的低频信息和高频信息;然后对各子序列分别用遗传算法优化的支持向量机进行训练和预测;最后将各子序列的预测结果叠加,得到极端降水量的最终预测结果。实验表明,该组合模型能准确揭示极端降水的变化特性,具有更高的预测精度,从而为极端降水量的预测提供了一种有效方法。

In order to improve the prediction accuracy of extreme precipitation, this paper establishes an extreme precipitation prediction model, combining wavelet analysis, support vector machine and genetic algorithm. Firstly, wavelet transform is used to decompose the extreme precipitation data, separating the low-frequency information and high-frequency information in extreme precipitation sequence. Then, support vector machine optimized by genetic algorithm is used to train and predict each sub-sequence. Finally, the prediction results of each sub-sequence are superimposed to obtain final prediction value. The model is used to analyze daily precipitation sequence at Jiangxi Poyang station, and the experimental results indicate that compared with the traditional support vector machine model, this combined model can reveal the change characteristics of extreme precipitation accurately, and has higher prediction accuracy, thus providing an effective method for prediction of extreme precipitation.