|Table of Contents|

Precipitation Nowcasting Method with High Spatio-temporal Resolution Based on Deep Learning(PDF)

《地球科学与环境学报》[ISSN:1672-6561/CN:61-1423/P]

Issue:
2023年第03期
Page:
706-718
Research Field:
环境与可持续发展
Publishing date:

Info

Title:
Precipitation Nowcasting Method with High Spatio-temporal Resolution Based on Deep Learning
Author(s):
FANG Wei1; 2; 3;  QI Mei-han1
(1. School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 210044, Jiangsu, China; 2. Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET), Nanjing University of Information Science & Technology, Nanjing 210044, Jiangsu, China; 3. Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou 215006, Jiangsu, China)
Keywords:
precipitation nowcasting;  severe convective weather;  deep learning;  radar echo extrapolation;  SwinAt-UNet model;  spatio-temporal resolution;  weather radar detection
PACS:
P456.1; X43
DOI:
10.19814/j.jese.2023.01010
Abstract:
Precipitation nowcasting plays an important role in severe convective weather monitoring and warning, and is very important for disaster prevention and mitigation. In meteorological services, the radar echo extrapolation method is mainly used to solve the nowcasting problem with high spatio-temporal resolution. In order to solve the problems of insufficient utilization of data information and low forecast accuracy in traditional radar echo extrapolation method, the high spatio-temporal resolution weather radar detection data in Shanghai area over many years were used to extrapolate radar echo based on data-driven deep learning method, and a new precipitation nowcasting model(SwinAt-UNet)was proposed. By fusing the UNet model and Swin Transformer structure to capture the short-term and long-term dynamic variation characteristics of historical weather radar detection data, the SwinAt-UNet model could adaptively learn the potential radar echo evolution laws of generation, dissipation, accumulation and deformation. In addition, in order to improve the generalization ability and forecast accuracy of the model, the depthwise-separable convolution and convolutional block attention module(CBAM)were introduced. The results show that the forecast accuracy of SwinAt-UNet model is higher than that of UNet, SmaAt-UNet, TransUNet and AA-TransUNet models under different base reflectivity thresholds; the critical success index of SwinAt-UNet model is increased by 13% at the base reflectivity threshold of 45 dBZ, and the period validity is improved; the image extrapolated by SwinAt-UNet model has clearer edge and detailed texture, and the predictions of precipitation range, moving direction and intensity change are more accurate.

References:

[1] 谌 芸,曹 勇,孙 健,等.中央气象台精细化网格降水预报技术的发展和思考[J].气象,2021,47(6):655-670.
CHEN Yun,CAO Yong,SUN Jian,et al.Progress of Fine Gridded Quantitative Precipitation Forecast Te-chnology of National Meteorological Centre[J].Me-teorological Monthly,2021,47(6):655-670.
[2] 肖 蕾,杜小玲,武正敏,等.贵州省短时强降水时空分布特征分析[J].暴雨灾害,2021,40(4):383-392.
XIAO Lei,DU Xiao-ling,WU Zheng-min,et al.Temporal and Spatial Distribution Characteristics of Sho-rt-time Heavy Rainfall in Guizhou Province[J].Torrential Rain and Disasters,2021,40(4):383-392.
[3] 程丛兰,陈 敏,陈明轩,等.临近预报的两种高时空分辨率定量降水预报融合算法的对比试验[J].气象学报,2019,77(4):701-714.
CHENG Cong-lan,CHEN Min,CHEN Ming-xuan,et al.Comparative Experiments on Two High Spatiotemporal Resolution Blending Algorithms for Quantitative Precipitation Nowcasting[J].Acta Meteorologica Sinica,2019,77(4):701-714.
[4] LIANG H,CHEN H N,ZHANG W,et al.Convective Precipitation Nowcasting Using U-Net Model [C]∥IEEE.2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS.Brussels:IEEE,2021:7134-7137.
[5] CRANE R K.Automatic Cell Detection and Tracking[J].IEEE Transactions on Geoscience Electronics,1979,17(4):250-262.
[6] AUSTIN G L,BELLON A.The Use of Digital Wea-ther Radar Records for Short-term Precipitation Forecasting[J].Quarterly Journal of the Royal Meteorological Society,1974,100:658-664.
[7] GIBSON J J.The Ecological Approach to Visual Perception:Classic Edition[M].London:Psychology Pre-ss,2014.
[8] 王 芬,李腹广,张 辉.风暴单体识别与跟踪(SCIT)算法评估[J].气象,2010,36(12):128-133.
WANG Fen,LI Fu-guang,ZHANG Hui.Storm Cell Identification and Tracking Algorithm for Assessment of SCIT[J].Meteorological Monthly,2010,36(12):128-133.
[9] 俞小鼎,周小刚,王秀明.雷暴与强对流临近天气预报技术进展[J].气象学报,2012,70(3):311-337.
YU Xiao-ding,ZHOU Xiao-gang,WANG Xiu-ming.The Advances in the Nowcasting Techniques on Thunderstorms and Severe Convection[J].Acta Meteorologica Sinica,2012,70(3):311-337.
[10] 田 刚,陈良华,魏 凡,等.基于光流法雷达外推的2020年长江致洪降水临近预报检验评估[J].暴雨灾害,2021,40(3):316-325.
TIAN Gang,CHEN Liang-hua,WEI Fan,et al.Eva-luation of Flood-producing Rainfall Nowcasting Based on Radar Extrapolation with the Variational Optical Flow Method in the Yangtze River Basin in 2020[J].Torrential Rain and Disasters,2021,40(3):316-325.
[11] 张梦涵,魏 进,卞海丁.基于机器学习的边坡稳定性分析方法:以国内618个边坡为例[J].地球科学与环境学报,2022,44(6):1083-1095.
ZHANG Meng-han,WEI Jin,BIAN Hai-ding.Slope Stability Analysis Method Based on Machine Learning:Taking 618 Slopes in China as Examples[J].Journal of Earth Sciences and Environment,2022,44(6):1083-1095.
[12] 杨 玲,魏 静,许子伏.基于平滑先验法-麻雀搜索算法-支持向量机回归模型的滑坡位移预测:以三峡库区八字门和白水河滑坡为例[J].地球科学与环境学报,2022,44(6):1096-1110.
YANG Ling,WEI Jing,XU Zi-fu.Dispalcement Prediction of Landslide Based on SPA-SSA-SVR Model:Taking Bazimen and Baishuihe Landslides in Three Gorges Reservoir Area,China as Examples[J].Journal of Earth Sciences and Environment,2022,44(6):1096-1110.
[13] 黄兴友,马玉蓉,胡苏蔓.基于深度学习的天气雷达回波序列外推及效果分析[J].气象学报,2021,79(5):817-827.
HUANG Xing-you,MA Yu-rong,HU Su-man.Extrapolation and Effect Analysis of Weather Radar Ec-ho Sequence Based on Deep Learning[J].Acta Meteorologica Sinica,2021,79(5):817-827.
[14] FANG W,PANG L,YI W N,et al.AttEF:Convolutional LSTM Encoder-forecaster with Attention Module for Precipitation Nowcasting[J].Intelligent Automation & Soft Computing,2021,29(3):453-466.
[15] SHI X J,CHEN Z R,WANG H,et al.Convolutional LSTM Network:A Machine Learning Approach for Precipitation Nowcasting[C]∥CORTES C,LEE D D,SUGIYAMA M,et al.Proceedings of the 28th International Conference on Neural Information Processing Systems.Montreal:ACM,2015:802-810.
[16] SHI X J,GAO Z H,LAUSEN L,et al.Deep Learning for Precipitation Nowcasting:A Benchmark and a New Model[C]∥VON LUXBURG U,GUYON I.Proceedings of the 31st International Conference on Neural Information Processing Systems.New York:ACM,2017:5622-5632.
[17] WANG Y B,WU H X,ZHANG J J,et al.PredRNN:A Recurrent Neural Network for Spatiotemporal Predictive Learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,45(2):2208-2225.
[18] WANG Y B,GAO Z F,LONG M S,et al.Pred-RNN++:Towards a Resolution of the Deep-in-time Dilemma in Spatiotemporal Predictive Learning[C]∥PMLR.Proceedings of the 35th International Conference on Machine Learning.Stockholm:PMLR,2018:5123-5132.
[19] WANG Y B,ZHANG J J,ZHU H Y,et al.Memory in Memory:A Predictive Neural Network for Learning Higher-order Non-stationarity from Spatiotemporal Dynamics[C]∥IEEE.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Re-cognition.Long Beach:IEEE,2019:9154-9162.
[20] WU H X,YAO Z Y,WANG J M,et al.MotionRNN:A Flexible Model for Video Prediction with Spacetime-varying Motions[C]∥IEEE.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville:IEEE,2021:15435-15444.
[21] RAVURI S,LENC K,WILLSON M,et al.Skilful Precipitation Nowcasting Using Deep Generative Models of Radar[J].Nature,2021,597:672-677.
[22] LUO C Y,ZHAO X Y,SUN Y X,et al.PredRANN:The Spatiotemporal Attention Convolution Recurrent Neural Network for Precipitation Nowcasting[J].Knowledge-based Systems,2022,239:107900.
[23] EHSANI M R,ZAREI A,GUPTA H V,et al.NowCasting-Nets:Representation Learning to Mitigate Latency Gap of Satellite Precipitation Products Using Convolutional and Recurrent Neural Networks[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:4706021.
[24] 方 巍,庞 林,张飞鸿,等.对抗型长短期记忆网络的雷达回波外推算法[J].中国图象图形学报,2021,26(5):1067-1080.
FANG Wei,PANG Lin,ZHANG Fei-hong,et al.Radar Echo Extrapolation Algorithm Based on Adversarial Long Short-term Memory Network[J].Journal of Image and Graphics,2021,26(5):1067-1080.
[25] RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolutional Networks for Biomedical Image Segmentation[C]∥NAVAB N,HORNEGGER J,WELLS W M,et al.International Conference on Medical Image Computing and Computer-assisted Intervention:MICCAI 2015.Munich:Springer,2015:234-241.
[26] TRNBING K,STANCZYK T,MEHRKANOON S.SmaAt-UNet:Precipitation Nowcasting Using a Small Attention-UNet Architecture[J].Pattern Recognition Letters,2021,145:178-186.
[27] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is All You Need[C]∥VON LUXBURG U,GUYON I.Proceedings of the 31st International Conference on Neural Information Processing Systems.New York:ACM,2017:6000-6010.
[28] DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An Image Is Worth 16×16 Words:Transformers for Image Recognition at Scale[EB/OL].(2020-10-22)[2022-12-20].https:∥arxiv.org/abs/2010.11929.
[29] LIU Z,LIN Y T,CAO Y,et al.Swin Transformer:Hierarchical Vision Transformer Using Shifted Windows[C]∥IEEE.Proceedings of the IEEE/CVF International Conference on Computer Vision.Montreal:IEEE,2021:9992-10002.
[30] NOGUEIRA R,JIANG Z,LIN J.Investigating the Li-mitations of Transformers with Simple Arithmetic Tasks[EB/OL].(2021-02-25)[2022-12-20].https:∥arxiv.org/abs/2102.13019.
[31] CHEN J,LU Y,YU Q,et al.TransUNet:Transfor-mers Make Strong Encoders for Medical Image Segmentation[EB/OL].(2021-02-08)[2022-12-20].https:∥arxiv.org/abs/2102.04306.
[32] YANG Y M,MEHRKANOON S.AA-TransUNet:Attention Augmented TransUNet for Nowcasting Ta-sks[C]∥IEEE.2022 International Joint Conference on Neural Networks(IJCNN).Padua:IEEE,2022:1-8.
[33] CHOLLET F.Xception:Deep Learning with Depthwise Separable Convolutions[C]∥IEEE.2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Honolulu:IEEE,2017:1800-1807.
[34] WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional Block Attention Module[C]∥FERRARI V,HEBERT M,SMINCHISESCU C,et al.Computer Vision-ECCV 2018.Munich:Spriner,2018:3-19.
[35] 张 林,李 峰,吴 蕾,等.CINRAD/SAD双偏振雷达非降水回波识别技术[J].应用气象学报,2022,33(6):724-735.
ZHANG Lin,LI Feng,WU Lei,et al.Non-precipitation Identification Technique for CINRAD/SAD Dual Polarimetric Weather Radar[J].Journal of Applied Meteorological Science,2022,33(6):724-735.

Memo

Memo:
-
Last Update: 2023-05-30