| 循环神经网络在雷达临近预报中的应用 |
| |
| 引用本文： | 韩丰,龙明盛,李月安,薛峰,王建民. 循环神经网络在雷达临近预报中的应用[J]. 应用气象学报, 2019, 30(1): 61-69. DOI: 10.11898/1001-7313.20190106 |
| |
| 作者姓名： | 韩丰 龙明盛 李月安 薛峰 王建民 |
| |
| 作者单位： | 1.国家气象中心, 北京 100081 |
| |
| 基金项目： | 国家重点研究发展计划重点专项（2016YFB1000700） |
| |
| 摘 要： | 该文将循环神经网络（recurrent neural network，RNN）应用于雷达临近预报。使用预测循环神经网络（predictive RNN）架构，利用雷达历史组合反射率因子建模，给出雷达组合反射率因子未来1 h的预报结果。预测循环神经网络的核心是在长短时记忆单元（long short-term memory，LSTM）中增加时空记忆模块，能够提取雷达回波不同尺度的空间特征，配合循环神经网络架构，可以有效解决反射率因子预测问题。北京大兴雷达和广州雷达长时间序列的独立检验结果和2个强对流天气个例检验结果表明:该方法和传统的基于交叉相关法的1 h雷达外推临近预报相比，在20 dBZ和30 dBZ检验项目内，临界成功指数（CSI）可以提升0.15~0.30，命中率（POD）提高0.15~0.25，虚警率（FAR）降低0.15~0.20，该方法对反射率因子强度变化有一定预报能力。
|
| 关 键 词： | 雷达临近预报 循环神经网络 深度学习 |
| 收稿时间： | 2018-06-06 |
| 修稿时间： | 2018-08-08 |
The Application of Recurrent Neural Network to Nowcasting |
| |
| Han Feng,Long Mingsheng,Li Yuean,Xue Feng and Wang Jianmin. The Application of Recurrent Neural Network to Nowcasting[J]. Journal of Applied Meteorological Science, 2019, 30(1): 61-69. DOI: 10.11898/1001-7313.20190106 |
| |
| Authors: | Han Feng Long Mingsheng Li Yuean Xue Feng Wang Jianmin |
| |
| Affiliation: | 1.National Meteorological Center, Beijing 1000812.School of Software, Tsinghua University, Beijing 100084 |
| |
| Abstract: | Radar extrapolation is an important means in nowcasting. The radar extrapolation methods widely used in China include COTREC and Optical Flow, by which two consecutive echoes are used to diagnose the advection velocity within rain analyses, involving the solution of Lagrangian persistence equation. A new method RNN(recurrent neural network) is applied in nowcasting. Using PredRNN(predictive RNN), by modeling historical radar data, the prediction of radar echo in the next hour is given. PredRNN consists of ST-LSTM unit, which is an improvement of LSTM. One advantage of using PredRNN is the operation of the state accumulation and the hidden layer output is replaced by convolution. Therefore, the neurons not only can get timing relationships, but also extract spatial features like convolutional layers. Another advantage is the addition of new spatial memory, which can enhance the transportation of the spatial feature information in different layers. In order to test the model performance, two radars of Daxing District of Beijing and Guangzhou are analyzed. The radar echo is pre-processed through quality controlling to remove isolated echo, abnormal echo, invalid radial and echo below 15 dBZ and ground echo, and then the combined reflectivity (CR) is made by 0-5 layers of data. To examine the applicability of the PredRNN, a contrast experiment is designed between PredRNN and COTREC, including an independent verification over months of each radar and two severe convective cases analysis. The test is carried out by point by point in three different reflectivity thresholds:20 dBZ, 30 dBZ and 50 dBZ. Indexes of verification are CSI, POD and FAR. The time range of the test is 0-1 h by 6 min. Results show that PredRNN has better forecast performance in all the verification items especially in 20 dBZ and 30 dBZ, when the CSI can be raised by 0.15-0.30, POD can be raised by 0.15-0.25, and FAR can be reduced by 0.15-0.20. This effect of improvement enhances with time. Although forecast performances of both PredRNN and COTREC fall with time, the performance of PredRNN method descends more slowly. The forecast performances of both PredRNN and COTREC fall with the increase of the combined reflectivity factor strength, which shows the insufficient of prediction ability for the region with intensity over 50 dBZ. Two cases show that the PredRNN method has predictive ability for the change of reflectivity factor intensity. In summary, PredRNN is suitable for nowcasting, and its forecast performance is much better than COTREC. |
| |
| Keywords: | nowcasting recurrent neural network deep learning |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《应用气象学报》浏览原始摘要信息 |
|
点击此处可从《应用气象学报》下载免费的PDF全文 |
|
