Please wait a minute...
img

官方微信

遥感技术与应用
模型与反演     
微波散射计反演海面风场的神经网络方法研究
陈坤堂1,2,董晓龙1,徐星欧1,郎姝燕3
(1.中国科学院微波遥感技术重点实验室,中国科学院国家空间科学中心,北京100190;
2.中国科学院大学,北京100049;3.国家卫星海洋应用中心,北京100081)
The Study on Oceanic Vector Wind Field Retrieve Technique based on Neural Networks of Microwave Scatterometer
Chen Kuntang1,2,Dong Xiaolong1,Xu Xing’ou1,Lang Shuyan3
(1.Key Laboratory of Microwave Remote Sensing,National Space Science Center,Beijing 100190,China;
2.University of Chinese Academy of Sciences,Beijing 100049,China;
3.National Satellite Ocean Application Service,Beijing 100081,China)
 全文: PDF(4243 KB)  
摘要:
研究利用神经网络方法处理微波散射计数据,反演海面风场。重点研究海洋二号(HY-2)卫星微波散射计数据反演,特别是中高风速条件下的风场反演。其中风速的反演基于后向传播(Back Propagation,BP)神经网络;多解风向的反演基于混合密度(Mixture Density Network,MDN)神经网络,求解过程中的核函数采用高斯分布;网络训练的目标风场采用欧洲中期天气预报中心(European Centre for Medium\|range Weather Foresting,ECMWF)模式风场。通过与ECMWF风场的比较,利用神经网络方法反演的风场可以满足HY\|2微波散射计风场反演的精度要求。同时通过与国家卫星海洋应用中心发布的HY\|2微波散射计L2B级风场产品相比较,表明该方法反演的风场更接近ECMWF模式风场。
关键词: 微波散射计海面风场反演神经网络中高风速海洋二号卫星(HY-2)    
Abstract: The neural networks are used to retrieve wind fields for microwave scatterometer data,especially for data gained by the scatterometer onboard HY\|2A satellite (HSCAT)under high wind speed conditions.The retrieval of wind speed is based on Back Propagation (BP)neural network,while multiple solutions of wind direction inversion is realized by Mixture Density Network (MDN)neural network.During the process,Gaussian kernel function is employed.The wind field used in network training is from corresponding European Centre for Medium\|range Weather Foresting (ECMWF).It is proved that wind fields retrieved in this paper could get results meeting the accuracy requirement for HSCAT by comparison with ECMWF wind fields.Results are also compared with the L2B wind field products distributed by the National Satellite Oceanic Application Service,it is shown that the method in this paper gave results with closer values than L2B products.
Key words: Microwave scatterometer;Wind field retrieve;Neural networks;High wind speed;HY\    2 satellite
收稿日期: 2016-05-30 出版日期: 2017-09-13
:  TP 75  
基金资助: 中国科学院国家空间科学中心微波遥感技术重点实验室开放课题(MLF2015003)资助.

作者简介: 陈坤堂(1990-),男,山东聊城人,硕士研究生,主要从事微波散射计数据处理研究。Email:chenkuntang@126.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
陈坤堂
董晓龙
徐星欧
郎姝燕

引用本文:

陈坤堂,董晓龙,徐星欧,郎姝燕. 微波散射计反演海面风场的神经网络方法研究[J]. 遥感技术与应用, 10.11873/j.issn.1004-0323.2017.4.0683.

Chen Kuntang,Dong Xiaolong,Xu Xing’ou,Lang Shuyan. The Study on Oceanic Vector Wind Field Retrieve Technique based on Neural Networks of Microwave Scatterometer. Remote Sensing Technology and Application, 10.11873/j.issn.1004-0323.2017.4.0683.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2017.4.0683        http://www.rsta.ac.cn/CN/Y2017/V32/I4/683

[1]Cornford D,Nabney I T,Bishop C M.Neural Network-based Wind Vector Retrieval from Satellite Scatterometer Data[J].Neural Computing & Applications,1999,8(3):206-217.
[2]Thiria S,Mejia C,Badran F,et al.A Neural Network Approach for Modeling Nonlinear Transfer Functions:Application for Wind Retrieval from Spaceborne Scatterometer Data[J].Journal of Geophysical Research:Oceans,1993,98(C12):22827-22841.
[3]Chen K S,Tzeng Y C,Chen P C.Retrieval of Ocean Winds from Satellite Scatterometer by a Neural Network[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(1):247-256.
[4]Kasilingam D,Lin I I,Khoo V,et al.A Neural Network-based Model for Estimating the Wind Vector Using ERS Scatterometer Data[C]// IEEE International Geoscience and Remote Sensing,IGARSS97.Remote Sensing-A Scientific Vision for Sustainable Development,1997,4:1850-1852.
[5]Lin Mingsen,Song Xingai,Peng Hailong,et al.Neural Network Wind Retrieval from Scattormeter Data[J].Remote Sensing for Land & Resources,2006,25(3):8-11.[林明森,宋新改,彭海龙,等.散射计资料的风场神经网络反演算法研究[J].国土资源遥感,2006,18(2):8-11.]
[6]Xie Xuetong,Fang Yu,Chen Kehai,et al.A Neural Network-based Model for Retrieval of the Ocean Surface Wind Vector from Sea Winds Scatterometer Data[J].Chinese High Technology Letters,2008,18(2):184-189.[解学通,方裕,陈克海,等.用SeaWinds散射计数据反演海面风矢量的神经网络模型[J].高技术通讯,2008,18(2):184-189.]
[7]Lin Mingsen,Zou Juhong,Xie Xuetong,et al.HY-2A Microwave Scatterometer Wind Retrieval Algorithm[J].Engineering Sciences,2013,15(7):68-74.[林明森,邹巨洪,解学通,等.HY-2A 微波散射计风场反演算法[J].中国工程科学,2013,15(7):68-74.]
[8]Feng Qian,Peng Hailong,Lin Mingsen.Mixture Density Network based Sea Surface Wind Field Retrieval from NSCAT Scatterometer Data[J].Acta Oceanologica Sinica,2006,28(5):44-48.[冯倩,彭海龙,林明森.基于混合密度网络的 NSCAT 散射计海面风场反演[J].Acta Oceanologica Since,2006,28(5):44-48.]
 
[1] 汪子豪,秦其明,孙元亨. 基于BP神经网络的地表温度空间降尺度方法[J]. 遥感技术与应用, 2018, 33(5): 793-802.
[2] 冯姣姣,王维真,李净,刘雯雯. 基于BP神经网络的华东地区太阳辐射模拟及时空变化分析[J]. 遥感技术与应用, 2018, 33(5): 881-889.
[3] 谢旭,陈芸芝. 基于PSO-RBF神经网络模型反演闽江下游水体悬浮物浓度[J]. 遥感技术与应用, 2018, 33(5): 900-907.
[4] 侯海艳,侯金,黄春林,王昀琛. 基于人工神经网络和AMSR2多频微波亮温的北疆地区雪深反演[J]. 遥感技术与应用, 2018, 33(2): 241-251.
[5] 杨朦朦,汪汇兵,欧阳斯达,范奎奎,戚凯丽. 基于双树复小波分解的BP神经网络遥感影像分类[J]. 遥感技术与应用, 2018, 33(2): 313-320.
[6] 田德宇,张耀南,赵国辉,韩立钦. 基于卷积神经网络的遥感沙漠绿地提取方法[J]. 遥感技术与应用, 2018, 33(1): 151-157.
[7] 王刚,董晓龙,朱迪. 基于星载旋转扫描雷达的高分辨率实现[J]. 遥感技术与应用, 2017, 32(6): 1071-1077.
[8] 何海清,庞燕,陈晓勇. 面向遥感影像场景的深度卷积神经网络递归识别模型[J]. 遥感技术与应用, 2017, 32(6): 1078-1082.
[9] 张焱,李新武,梁雷. 基于微波散射计的格陵兰冰盖冻融探测方法研究[J]. 遥感技术与应用, 2017, 32(1): 113-120.
[10] 林溢园,邹巨洪,林明森,何原荣. 多源星载微波散射计海面风场信息融合研究[J]. 遥感技术与应用, 2017, 32(1): 126-132.
[11] 过杰,何宜军,张彪,Vladimir Yurjevich Karaev,M.A.Panfilova,Yuriy Titchenko. 基于散射计波浪参数反演模型的改进算法实验[J]. 遥感技术与应用, 2016, 31(5): 907-911.
[12] 贾楠,张祥坤,刘和光,蔡永俊. Ku波段成像散射计后向散射系数精度分析[J]. 遥感技术与应用, 2016, 31(3): 497-503.
[13] 高小红,杨扬,张威,贾伟,李金山,田成明,张艳娇,杨灵玉,何林华. 可见光—近红外光谱估算三江源区不同土壤全氮含量[J]. 遥感技术与应用, 2015, 30(5): 849-859.
[14] 熊贤成,杨春平,敖明武,郭晶,曾丹丹. 基于BP神经网络的云相态检测方法研究[J]. 遥感技术与应用, 2015, 30(4): 714-718.
[15] 云婷,董晓龙. 星载微波散射计高分辨率σ0图像重构方法研究[J]. 遥感技术与应用, 2015, 30(3): 495-503.