Please wait a minute...
img

官方微信

遥感技术与应用  2009, Vol. 24 Issue (3): 325-330    DOI: 10.11873/j.issn.1004-0323.2009.3.325
技术研究与图像处理     
基于神经网络算法的多极化雷达数据估算鄱阳湖生物量
董磊1,3,廖静娟2,沈国状2
(1.中国科学院遥感应用研究所遥感科学国家重点实验室|北京 100101;2.中国科学院对地观测与数字地球科学中心|北京 100101;3.中国科学院研究生院|北京 100049)
Neural Network-based Biomass Estimation in the Poyang Lake Wetland Using Envisat ASAR Data
DONG Lei1,3,LIAO Jing-juan2,SHEN Guo-zhuang2
(1.State Key Laboratory of Remote Sensing Science,Institute of Remote Sensing Applications,Chinese Academy ofSciences,Beijing 100101,China;2.Center for Earth Observation and Digital Earth,Chinese Academy ofSciences,Beijing 100101,China;3.Graduate University of Chinese Academy of Sciences,Beijing 100049,China)
 全文: PDF(1401 KB)  
摘要:

神经网络的特点是分布并行处理,适用于模拟复杂的非线性模型。在野外调查的基础上,利用多极化雷达数据,通过改进MIMICS模型模拟湿地植被参数(植被高度、含水量、生物量等)和雷达后向散射系数之间的关系,建立神经网络模型。通过模型的训练和仿真,与实测数据进行比较、验证,从而估算鄱阳湖湿地植被的生物量分布情况。研究表明基于改进的MIMICS模型训练数据的神经网络模型有较好的反演湿地植被生物量的能力,并据此反演了鄱阳湖湿地2007年4月、7月、11月的生物量动态变化情况。

关键词: 生物量多极化雷达神经网络MIMICS模型    
Abstract:

Traditional way to monitor biomass changes is to use linear or nonlinear model from TM/ETM data.In this paper we discuss the neural network algorithms(NNA) to retrieve wetland biomass from multi-polarization(HH and VV) backscattering values using ENVISAT ASAR data.Two field measurements were carried out concomitant to the acquisition of ASAR images in this area through the hydrological cycle.Training data of the network are generated by MIMICS model which is often used in the forest.We modify the model to make it available on the wetland system.NNA retrieval results are validated with experimental data.The inversion results show that the NNA is capable of performing the retrieval with good accuracy.Finally,the trained neural network is used to estimate the overall biomass of the Poyang Lake and make the map of biomass distribution in April,July and November.

Key words: Biomass    Multi-polarization    SAR    Neural network    MIMICS
收稿日期: 2011-06-10 出版日期: 2010-01-20
:  TP 79  
基金资助:

863 计划项目(2006AA12Z122)和中国科学院知识创新工程重要方向性项目(KZCX2-YW-313)联合资助。

作者简介: 董磊(1984-)|男|硕士研究生|主要从事微波遥感研究。E-mail:ldong@irsa.ac.cn。
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  
董磊
廖静娟
沈国状

引用本文:

董磊,廖静娟,沈国状. 基于神经网络算法的多极化雷达数据估算鄱阳湖生物量[J]. 遥感技术与应用, 2009, 24(3): 325-330.

DONG Lei,LIAO Jing-juan,SHEN Guo-zhuang. Neural Network-based Biomass Estimation in the Poyang Lake Wetland Using Envisat ASAR Data. Remote Sensing Technology and Application, 2009, 24(3): 325-330.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2009.3.325        http://www.rsta.ac.cn/CN/Y2009/V24/I3/325

[1] Wang Shugong,Li Xia,Zhou Yongzhang.Progress of Method for Wetland Vegetation Biomass[J].Geography and Geo-Information Science,2004,20(5):104-109.[王树功,黎夏,周永章.湿地植被生物量测算方法研究进展[J].地理与地理信息科学,2004,20(5):104-109.]


[2] Li Rendong,Liu Jiyuan.An Estimation of Wetland Vegetation Biomass in the Poyang Lake Using Landsat ETM Data[J].Acta Geographica Sinaca,2001,56(5):532-540.[李仁东,刘纪远.应用Landsat ETM数据估算鄱阳湖湿生植被生物量[J].地理学报,2001,56(5):532-540.]


 [3] Wang Shujun,Guan Dongsheng.Remote Sensing Method of Forest Biomass Estimation by Artificial Neural Network Models[J].Ecology and Environment,2007,16(1):108-111.[王淑君,管东生.神经网络模型森林生物量遥感估测方法的研究[J].生态环境,2007,16(1):108-111.]


 [4] Moreau S,Toan T L.Biomass Quantification of Andean Wetland Forages Using ERS Satellite SAR Data for Optimizing Livestock Management[J].International Journal of Remote Sensing,2003,84:477-492.


[5] Dobson M C,Ulaby F T,Toan T L,et al.Dependence of Radar Backscatter on Coniferous Forest Biomass[J].IEEE Transaction Geosciences Remost Sensing,1992,30:412-415.


[6] Kasischke E S,Christensen N L,Bourgeau-Chavez L L.Correlating Radar Backscatter with Components of Biomass in Loblolly Pine Forest[J].IEEE Transaction Geosciences Remost Sensing,1995,32:643-659.


[7] Polatin P F,Sarabandi K,Ulaby F T.An Iterative Inversion Algorithm with Application to the Polarimetric Radar Response of Vegetation Canopies[J].IEEE Transaction Geosciences Remost Sensing,1994,32:62-71.


[8] Ulaby F T,Sarabandi K,McDonald K,et al.Michigan Microwave Canopy Scattering Model[J].International Journal of Remote Sensing,1990,11:1223-1253.


 


[9] Dawson M S,Fung A K,Manry M T.Surface Parameter Retrival Using Fast Learning Neural Networks[J].Remote Sensing Reviews,1993,7:1-18.


[10] Chen Shuiseng,Zhan Zhiming.A Remote Sensing Investigation on Wetlands in the Boyang Lake Area by GIS[J].Tropical Geography,1999,19(1):35-38.[陈水森,詹志明.基于GIS的鄱阳湖湿地遥感调查试验研究[J].热带地理,1999,19(1):35-38]

[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] 廖凯涛,齐述华,王成,王点. 结合GLAS和TM卫星数据的江西省森林高度和生物量制图[J]. 遥感技术与应用, 2018, 33(4): 713-720.
[5] 李德伟,江利明,蒋厚军. GSSR成像雷达应用进展及其对我国深空探测的启示[J]. 遥感技术与应用, 2018, 33(3): 377-386.
[6] 虢韬,沈平,时磊. 机载LiDAR快速定位高压电塔方法研究[J]. 遥感技术与应用, 2018, 33(3): 530-535.
[7] 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.
[8] 李兆明,陈洪滨. 使用金属球定标X波段固态天气雷达[J]. 遥感技术与应用, 2018, 33(2): 259-266.
[9] 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.
[10] 孟庆岩,孙云晓,张佳晖,等. 基于多源遥感的建筑区绿化垂直分布特征与空间配置分析——以匈牙利塞克什白堡市为例[J]. 遥感技术与应用, 2018, 33(2): 370-376.
[11] 万玲,尤红建,程跃兵,卢晓军. 合成孔径雷达图像分割研究进展[J]. 遥感技术与应用, 2018, 33(1): 10-24.
[12] 熊伟,徐永力,姚力波,崔亚奇. 基于SVM的高分辨率SAR图像舰船目标检测算法[J]. 遥感技术与应用, 2018, 33(1): 119-127.
[13] 梁茜茜,张汉德,孙根云,王鹏. 基于机载激光雷达数据的海岸带水域提取方法[J]. 遥感技术与应用, 2018, 33(1): 136-142.
[14] 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.
[15] 张雅,尹小君,王伟强. 基于Landsat 8 OLI遥感影像的天山北坡草地地上生物量估算[J]. 遥感技术与应用, 2017, 32(6): 1012-1021.