Hydrometeor Classification Method in Dual-polarization Weather Radar Based on Fuzzy Neural Network-fuzzy C-means
-
摘要:
对于地杂波存在情况下的降水粒子分类问题，传统方法在不同的天气及环境条件下会产生较大分类误差。该文提出一种基于模糊神经网络(FNN)-模糊C均值聚类(FCM)算法的双偏振气象雷达降水粒子分类方法。该方法首先利用双偏振气象雷达在晴空模式下接收的地杂波数据训练FNN，自适应地计算地杂波各偏振参量隶属函数的参数，然后利用训练得到的地杂波隶属函数对降水模式下的地杂波进行抑制，最后采用模糊C均值聚类算法对地杂波抑制后的回波进行降水粒子分类。对实测数据的处理结果表明，该方法能够有效地抑制地杂波并获得较为精细的降水粒子分类结果。
Abstract:For the problem of hydrometeor classification in the presence of ground clutter, traditional methods produce large classification errors under different weather and environmental conditions. A new method for the classification of Hydrometeor based on Fuzzy Neural Network-Fuzzy C-Means (FNN-FCM) is proposed. Firstly, the FNN is trained by the clutter data received by the Dual-polarization weather radar in the clear sky mode. The parameters of the membership function of each polarization parameter of the clutter are calculated adaptively. Then the ground clutter in the rainfall mode is suppressed by the ground clutter membership function obtained by the training. Finally, FCM clustering algorithm is used to classify the Hydrometeor after clutter suppression. The processing results of the measured data show that the proposed method can effectively suppress ground clutter and obtain finer hydrometeor classification results.
-
表 1 降水粒子及地杂波
${{{Z}}_{\rm{H}}}$ 隶属函数参数值粒子类型 毛毛雨 雨 冰晶 干雪 湿雪 高密度霰 冰雹 大雨滴 地杂波 a 29.00 15.50 22.00 17.00 22.00 9.00 12.00 9.00 25.10 b 10.00 10.00 20.00 15.00 10.00 6.00 10.00 10.00 20.00 m 2.00 41.50 –3.00 17.00 21.00 49.00 58.00 57.00 –1.10 
下载: 导出CSV
表 2 各类别粒子数量及占比(2017.08.17/06)
类别 FNN-FCM方法 模糊逻辑方法 数据个数 百分比(%) 数据个数 百分比(%) 毛毛雨 113387 39.82 217450 57.59 雨 21663 7.61 14789 3.92 冰晶 3654 1.28 31729 8.40 干雪 53532 18.80 33032 8.75 湿雪 26563 9.33 10058 2.66 高密度霰 19796 6.95 12921 3.42 冰雹 10174 3.57 4874 1.29 大雨滴 35985 12.64 52727 13.97 数据整体 286724 100 377580 100
下载: 导出CSV
-
李金辉, 樊鹏. 冰雹云提前识别及预警的研究[J]. 南京气象学院学报, 2007, 30(1): 114–119 doi: 10.3969/j.issn.1674-7097.2007.01.016LI Jinhui and FAN Peng. Investigation on early identification and warning of hail clouds[J]. Journal of Nanjing Institute of Meteorology, 2007, 30(1): 114–119 doi: 10.3969/j.issn.1674-7097.2007.01.016 孟旭航, 刘玉玲, 白洁. 航线天气预报中航迹规划仿真研究[J]. 系统仿真学报, 2006, 18(2): 832–836 doi: 10.3969/j.issn.1004-731X.2006.z2.235MENG Xuhang, LIU Yuling, and BAI Jie. Researches of computer simulation on path planning in airway weather forecast[J]. Journal of System Simulation, 2006, 18(2): 832–836 doi: 10.3969/j.issn.1004-731X.2006.z2.235 楼小凤, 师宇, 李集明. 云降水和人工影响天气催化数值模式的发展及应用[J]. 气象科技进展, 2016, 6(3): 75–82 doi: 10.3969/j.issn.2095-1973.2016.03.010LOU Xiaofeng, SHI Yu, and LI Jiming. Development and application of the cloud and seeding models in weather modification[J]. Advances in Meteorological Science and Technology, 2016, 6(3): 75–82 doi: 10.3969/j.issn.2095-1973.2016.03.010 杨通晓, 袁招洪. 多波段双偏振天气雷达识别降水类型的模拟研究[J]. 高原气象, 2017, 36(1): 241–255 doi: 10.7522/j.issn.1000-0534.2016.00016YANG Tongxiao and YUAN Zhaohong. Simulation research on hydrometeor classification by multi-wavelength dual linear polarization Doppler radar[J]. Plateau Meteorology, 2017, 36(1): 241–255 doi: 10.7522/j.issn.1000-0534.2016.00016 唐顺仙, 吕达仁, 何建新, 等. 天气雷达技术研究进展及其在我国天气探测中的应用[J]. 遥感技术与应用, 2017, 32(1): 1–13 doi: 10.11873/j.issn.1004-0323.2017.1.0001TANG Shunxian, LÜ Daren, HE Jianxin, et al. Research of weather radar technology and application on Chinese weather observation[J]. Remote Sensing Technology and Application, 2017, 32(1): 1–13 doi: 10.11873/j.issn.1004-0323.2017.1.0001 宗蓉, 陈超, 潘国盛. 基于模糊逻辑的双偏振多普勒雷达地物杂波抑制方法的初步应用[J]. 广东气象, 2017, 39(6): 56–59 doi: 10.3969/j.issn.1007-6190.2017.06.015ZONG Rong, CHEN Chao, and PAN Guosheng. Preliminary application of dual-polarization Doppler radar clutter suppression based on fuzzy logic[J]. Guangdong Meteorology, 2017, 39(6): 56–59 doi: 10.3969/j.issn.1007-6190.2017.06.015 GIANGRANDE S E and RYZHKOV A V. Estimation of rainfall based on the results of polarimetric echo classification[J]. Applied Meteorology Climatological, 2008, 47(4): 2445–2462 doi: 10.1175/2008JAMC1753.1 HUBBERT J and BRINGI V N. An iterative filtering technique for the analysis of copolar differential phase and dual-frequency radar measurements[J]. Journal Atmospheric Oceanic Technology, 1995, 12(3): 643–648 doi: 10.1175/1520-0426(1995)012<0643:AIFTFT>2.0.CO;2 汪月霞, 林伙海, 何建新, 等. 双偏振天气雷达降水粒子相态识别研究[C]. 第30届中国气象学会年会, 南京, 中国, 2014: 1–6.WANG Yuexia, LIN Huohai, HE Jianxin, et al. Study on hydrometeors identification based on polarimetric radar[C]. 30th Annual Meeting of the Chinese Meteorological Society, Nanjing, China, 2014: 1–6. HOLLER H, BRINGI V N, HUBBERT J, et al. Life cycle and precipitation formation in a hybrid-type hailstorm revealed by polarimetric and Doppler radar measurements[J]. Atmosphere Science, 1994, 51(12): 2500–2522 doi: 10.1175/1520-0469(1994)051<2500:LCAPFI>2.0.CO;2 冉元波, 孙敏, 高梦清, 等. 双偏振天气雷达水凝物识别研究[J]. 成都信息工程大学学报, 2017, 32(6): 590–596 doi: 10.16836/j.cnki.jcuit.2017.06.003RAN Yuanbo, SUN Min, GAO Mengqing, et al. Study on hydrometeor identification based on deep learning[J]. Journal of Chengdu University of Information Technology, 2017, 32(6): 590–596 doi: 10.16836/j.cnki.jcuit.2017.06.003 许哲万, 李晶皎, 王爱侠, 等. 一种基于改进T-S模糊推理的模糊神经网络学习算法[J]. 计算机科学, 2011, 38(11): 196–219 doi: 10.3969/j.issn.1002-137X.2011.11.044XU Zhewan, LI Jingjiao, WANG Aixia, et al. Training algorithm of fuzzy neural network based on improved T-S fuzzy reasoning[J]. Computer Science, 2011, 38(11): 196–219 doi: 10.3969/j.issn.1002-137X.2011.11.044 BANDYOPADHYAY S and MAULIK U. An evolutionary technique based on K-means algorithm for optimal clustering in ${\mathbb{R}}_N$ [J]. Information Sciences, 2002, 146(1/4): 221–237 doi: 10.1016/S0020-0255(02)00208-6 -
计量
- 文章访问数: 1992
- HTML全文浏览量: 869
- PDF下载量: 74
- 被引次数: 0
下载:
