深度学习模型在2021年汛期武汉市雷达回波临近预报中的应用评估

袁凯, 庞晶, 李武阶, 李明

Application evaluation of deep learning models in radar echo nowcasting in Wuhan in flood season of 2021

YUAN Kai, PANG Jing, LI Wujie, LI Ming

图2 2021年8月23日22：30至24日00：00雷达回波实况和4种深度学习模型及光流法预报回波对比（单位：dBZ） （从上至下依次为实况回波、光流法及CrevNet、MIM、PhyDNet、PredRNN++模式预报回波，黑色三角为武汉雷达站，黑色线包围区域为武汉市。下同）

Fig.2 The comparison of radar echo forecasted by four deep learning models and optical flow method with the observation from 22：30 on 23 August to 00：00 on 24 August， 2021 （Unit： dBZ） （From top to bottom， it is the observed radar echo and radar echo forecasted by optical flow method and deep learning models of CrevNet， MIM， PhyDNet and PredRNN++ in turns， the black triangle is for the Wuhan radar station， the area enclosed by black line is for the Wuhan City. the same as below）