LAN Jingke,YANG Ling,SHI Chunxiang,et al.Identification of Severe Convection based on X-band Netted Radar[J].Journal of Chengdu University of Information Technology,2024,39(05):540-545.[doi:10.16836/j.cnki.jcuit.2024.05.004]
基于X波段雷达组网的强对流识别
- Title:
- Identification of Severe Convection based on X-band Netted Radar
- 文章编号:
- 2096-1618(2024)05-0540-06
- 分类号:
- TN959.4
- 文献标志码:
- A
- 摘要:
- 冰雹、暴雨等强对流天气对人类活动的危害巨大,但由于其发展迅速、结构复杂,对其进行自动识别非常困难。基于成都航空港、龙泉,资阳地区3部X波段雷达构成的雷达组网平台,利用雷达组网的高时空分辨率的体扫数据,在传统的U-Net网络基础上进行改进,提出一种基于U-Net语义分割网络的强对流天气识别模型。选取雷达组网中0.5°、2°、3.5°、5°、6.5°、8°和9°共7层仰角基数据中的径向速度和反射率数据,进行配准、归一化等预处理后形成模型训练所需的数据集。经实验验证,训练后得到的模型对强对流识别的结果比较好。
- Abstract:
- Severe convective weather, such as hail and rainstorms, does great harm to human activities, but it is very difficult to identify them automatically because of their rapid development and complex structure. Based on the radar network platform composed of three X-band radars in Chengdu Airport, Longquan, and Ziyang, this study improved the traditional U-Net network by using the bulk sweep data of the netted radar with high spatial and temporal resolution, so as to propose a strong convective weather recognition model based on U-Net semantic segmentation network. In this study, the radial velocity and reflectance data from seven layers of elevation base data of 0.5°,2°,3.5°,5°,6.5°,8°and 9° in the radar network were selected, and the data sets needed for model training were formed after pre-processing such as registration and normalization. The experimental results show that the trained model has a good result for strong convection recognition.
参考文献/References:
[1] 姚蓉,唐佳,兰明才,等.一次混合强对流天气的环境条件及演变特征分析[J].暴雨灾害,2017,36(3):217-226.
[2] Junyent,Francesc,Chandrasekar,et al.The CASA Integrated Project 1 Networked Radar System[J].Journal of Atmospheric and Oceanic Technology,2010,27(1):61-78.
[3] 马舒庆,陈洪滨,王国荣,等.阵列天气雷达设计与初步实现[J].应用气象学报,2019,30(1):1-12.
[4] Best,William H,Jr.Radars over the Hump: Recollections of the First WeatherRadar Network[J].Bulletin of the American Meteorological Society,1973,54(3):205-208.
[5] Wang Yanting,Chandrasekar.Quantitative Precipitation Estimation in the CASA X-band Dual-Polarization Radar Network[J].Journal of Atmospheric and Oceanic Technology,2010,27(10):1665-1676.
[6] Barbary M,Zong P.Optimisation for stealth target detection based on stratospheric balloon-borne netted radar system[J].IET Radar,Sonar & Navigation,2015,9(7):802-816.
[7] Johnson J T,MacKeen P L,Witt A,et al.The storm cell identification and tracking algorithm:An enhanced WSR-88D algorithm[J].Weather and Forecasting,1998,13(2):263-276.
[8] 段艺萍,徐亚娟,支树林.改进的SCIT算法在人工防雹作业中的应用分析[J].气象与减灾研究,2014,37(4):42-49.
[9] 张栋.修正SCIT算法在冰雹识别、跟踪、预警中的应用[J].内蒙古气象,2020(1):40-44.
[10] 王萍,牛智勇.基于多普勒天气雷达数据的中层径向辐合自动识别及其与强对流天气的相关性研究[J].物理学报,2014,63(1):432-444.
[11] 南刚强,陈明轩,秦睿等.基于雷达组合反射率拼图和深度学习的中尺度对流系统识别、追踪与分类方法[J].气象学报,2021,79(6):1002-1021.
[12] Jergensen E G,McGovern A,Lagerquist R,et al.Classifying Convective Storms Using Machine Learning[J].Weather and Forecasting,2020,35(2):537-559.
[13] Zi-Xin Xu,Ling Yang,Bo Lei,et al.An Automatic Framework of Region-of-Interest Detection and Classification for Networked X-Band Weather Radar System[J].Earth and Space Science,2020,7(4):1-11.
[14] Jingjing G,Haihong T.Cramer-Rao lower bounds of target positioning estimate in netted radar system[J].Digital Signal Processing,2021,118.
[15] Mecikalski J R,Williams J K,Jewett C P,et al.Probabilistic 0-1 hour convective initiation nowcasts that combine geostationary satellite observations and numerical weather prediction model data[J].Journal of Applied Meteorology and Climatology,2015,54(5):1039-1059.
[16] 韩丰,龙明盛,李月安等.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.
[17] 郭瀚阳,陈明轩,韩雷等.基于深度学习的强对流高分辨率临近预报试验[J].气象学报,2019,77(4):715-727.
[18] 刘新伟,黄武斌,蒋盈沙等.基于LightGBM算法的强对流天气分类识别研究[J].高原气象,2021,40(4):909-918.
[19] 李兆明,陈洪滨,段树等.网络化多普勒天气雷达反射率因子的衰减订正[J].气象科学,2015,35(5):593-598.
相似文献/References:
[1]杨 梅,罗 建,张晓倩,等.基于改进U-Net的新冠肺炎图像分割方法[J].成都信息工程大学学报,2023,38(01):44.[doi:10.16836/j.cnki.jcuit.2023.01.007]
YANG Mei,LUO Jian,ZHANG Xiaoqian,et al.A Novel Coronary Pneumonia Image Segmentation Method based on Improved U-Net[J].Journal of Chengdu University of Information Technology,2023,38(05):44.[doi:10.16836/j.cnki.jcuit.2023.01.007]
备注/Memo
收稿日期:2022-08-01
基金项目:四川省自然科学基金资助项目(2022NSFSC0216)