动态概率卷积神经网络在雷达回波外推中的应用

雷达回波外推方法已广泛应用于短时强降水临近预报中.针对传统雷达回波外推方法未充分利用海量历史气象数据从而导致预报准确度不高的问题,提出了一个基于动态概率卷积神经网络(dynamic probability convolutional neural network,DPCNN)的雷达回波外推模型.该模型在卷积神经网络的基础上增加动态概率计算层,对不同的雷达回波输入序列计算对应的概率卷积核,并用于后续的外推计算中,使得网络在预测阶段仍然能够根据不同的输入序列作出相应的概率调整,从而增强了外推结果与已知序列的关联.经某局部地区短时强降水外推实验,从外推图像、CSI指数、FAR指数、POD指数四个方面验证了该模型的有效性.

Application of dynamic probability convolutional neural network in radar echo extrapolation

Radar echo extrapolation has been widely used in short-term heavy precipitation nowcasting. Aiming at the problem that traditional radar echo extrapolation methods do not make full use of massive historical meteorological data, which leads to low forecast accuracy, this paper proposed a new radar echo extrapolation method based on DPCNN. With the addition of dynamic probability calculation layer, DPCNN is able to calculate the corresponding probability convolution kernel for different radar echo input sequences and used it in the subsequent extrapolation calculations. Dynamic probability calculation layer enabled the network to make corresponding probability adjustments according to different input sequences in the prediction stage and enhance the connection between extrapolation and input sequences. The extrapolation experiment of short-term heavy precipitation in a certain area verifies the validity of the model from four aspects: extrapolated image, CSI, FAR, and POD.