遥感技术在扎龙湿地资源调查中的应用
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
黑龙江省的扎龙湿地由于近年来的连续干旱,其生态环境遭到破坏。为科学评价扎龙湿地2001年底至2002年初的火灾以及为恢复湿地而进行的补水工程对扎龙湿地的影响,本文采用遥感技术对扎龙湿地资源进行了调查,提出一个改进学习算法的四层神经网络遥感分类模型,分析了扎龙湿地在补水前后的变化,并在提出的光谱相似的图像可以采用相同样本的思想基础上实现了影像自动分类系统。
     本文采用2002年3月14日、5月17日和9月22日的ETM+卫星遥感影像对扎龙湿地现状进行调查。为了达到识别各个土地利用类型的目的,遥感图像经过了一系列的处理,包括预处理、分类、制图、面积统计等步骤。预处理完成后,采用本文提出的改进学习算法的四层神经网络对扎龙湿地影像进行了分类。分类结果表明,该网络能够有效建立扎龙湿地影像的复杂模型。与常规的三层神经网络和传统的最大似然法相比,四层网络能够获得较高的分类精度。而改进的学习算法,即基于鲁棒误差函数的自适应反向传播算法,明显的抑制了过大误差,使误差下降更快,缩短了训练时间。根据分类结果进行的面积统计表明,补水减小了火灾对沼泽的影响,促进了扎龙湿地的恢复。本文还在.NET平台下实现了影像自动分类系统,提出了光谱相似的图像可以采用相同样本的思想,完成了建立图像与样本关联的复杂流程设计。该系统能够对已采集的样本进行充分利用,从而实现影像的自动分类。
Zhalong wetland lies in Heilongjiang province of Northwest China. Its environment is facing degeneration because of continuous drought in recent years. Especially, Zhalong wetland suffered fire from the end of 2001 to the beginning of 2002. Therefore, artificial recharge projects were developed to hasten its recovery. To evaluate the effect of the fire and the recharge on Zhalong wetland scientifically, remote sensing is used to investigate the resource of Zhalong wetland. A four-layer neural network, which adopts improved learning algorithm, is presented to classify remotely sensed images. The changes brought by the recharge have been analyzed. The thought that images with similar spectra can adopt the same samples to do the classification is presented in this paper. And based on this thought, an automatic classification system is performed.
    The ETM+ images taken on March 14, 2002, May 17, 2002 and September 22, 2002 are used to investigate the resources of Zhalong wetland. To recognize different types of land use, the remotely sensed images come through pretreatment, classification, mapping and area measurement. After the pretreatment, the four-layer neural network, which adopts improved learning algorithm, is used to classify images of Zhalong wetland. Results show that the four-layer neural network appears to be feasible to classify the images of Zhalong wetland. Compared with three-layer neural network and maximum likelihood classifier, it has the highest classification accuracy. The improved algorithm, that is, the adaptive back-propagation learning algorithm based on the error robust function, avoids the occurrence of big error, accelerates decreasing rate of error and shortens the learning time. Statistics about the wetland area based on classification results suggest that the recharge reduces the effect of fire on marsh and promotes the
    recovery of the wetland. Additionally, the automatic classification system is realized under .NET platform. The thought that images with similar spectra can adopt the same samples to do the classification is presented, and the complicated flow design for establishing the relation between image and sample is accomplished. The system makes full use of collected samples and realizes the automatic classification of images.
引文
[1] 李禄康.湿地与湿地公约.世界林业研究,2001,14(1):1-7
    [2] 李禄康.保护湿地就是保护人类生存环境.世界林业研究,2001,1(6):22-27
    [3] 贾忠华,罗纨,王文焰,Skaggs,R.W.对湿地定义和湿地水文特征的探讨.水土保持学报,2001,15(6):117-120
    [4] 李云鹏,李青山,刘景哲,郎振华.松嫩平原湖泡湿地水资源质量评价与保护对策研究.东北水利水电,2001,19(10):44-46,56
    [5] 盖赫莉,王淑梅,王欣.对扎龙湿地生态环境的分析.黑龙江环境通报,2002,26(3):94-96
    [6] 谢永刚.扎龙湿地大火灾.中国减灾,2002,(4):53-54
    [7] 谢永刚,张姝慧.扎龙湿地着火了.大自然探索,2002,(12):28-29
    [8] 张显峰,崔伟宏.运用RS、GPS和GIS技术进行大比例尺土地利用动态监测的实验研究.地理科学进展,1999,18(2):137-146
    [9] Maracchi, G., Perarnaud, V., and Kleschenko, A.D. Applications of geographical information systems and remote sensing in agrometeorology. Agricultural and Forest Meteorology, 2000, 103(1-2): 119-136
    [10] Chen, J.H., Kan, C.E., Tan, C.H., and Shih, S.F. Use of spectral information for wetland evapotranspiration assessment. Agricultural Water Management, 2002, 55(3): 239-248
    [11] 沙志刚.数字遥感技术在土地利用动态监测中的应用概述.国土资源遥感,1999,(2):7-11
    [12] 郭中伟,李典谟,甘雅玲.森林生态系统生物多样性的遥感评估.生态学报,2001,21(8):1369-1384
    [13] 罗宏宇,黄方张,养贞.辽河三角洲沼泽湿地时空变化及其生态效应.东北师大学报自然科学版,2003,35(2):100-105
    [14] 周华茂,曾良修,喻歌农,刘鼎昌.卫星遥感和地理信息系统在湿地资源调查中的应用.西南农业学报,2000,13(2):78-72
    [15] 肖飞,蔡述明.洪湖湿地变化研究.华中师范大学学报自然科学版,2003,37(2):266-272
    [16] 蒋卫国,王文杰,谢志仁,高士平.基于RS和GIS的三江平原湿地景观变化研究.地理与地理信息科学,2003,19(2):28-31
    [17] 汪爱华,张树清,何艳芬.RS和GIS支持下的三江平原沼泽湿地动态变化研究.地理科学,2002,22(5):636-640
    [18] 汪爱华,张树清,张柏.遥感和地理信息系统技术在湿地研究中的应用.遥感技术与应用,2001,16(3):200-204
    [19] 许学工,林辉平,付在毅,布仁仓.黄河三角洲湿地区域生态风险评价.北京大学学报自然科学版,2001,37(1):111-120
    [20] 孙玉梅,郝素贞,张义文.利用RS和GIS技术对南大港湿地类型的调查研究.河北师范大学学报自然科学版,2003,27(5):523-526,537
    [21] 杨秀春,朱晓华,黄家柱,谢志仁.江苏省湿地资源现状及其可持续利用研究.经济地理,2004,24(1):81-84
    [22] 朱述龙,张占睦.遥感图象获取与分析.第1版.北京:科学出版社,2000.105-170
    [23] 刘建平,赵英时.高光谱遥感数据解译的最佳波段选择方法研究.中国科学院研究生院学报,
    
    1999,16(2):153-161
    [24] 曾生根,仲海泉,夏德深.从图像工程角度看CBERS-1卫星图像.航天返回与遥感,2001,22(3):40-45
    [25] 甘淑,党承林,欧晓昆.云南山区NPP遥感监测研究中遥感图像预处理.云南大学学报(自然科学版),2002,24(3):229-233
    [26] 刘志丽,陈曦.基于ERDAS IMAGINE软件的TM影像几何精校正方法初探——以塔里木河流域为例.干旱区地理,2001,24(4):353-358
    [27] 党安荣,王晓栋,陈晓峰,张建宝.ERDAS IMAGINE遥感图像处理方法.第1版.北京:清华大学出版社,2003.69-80
    [28] 傅肃性.遥感专题分析与地学图谱.第1版.北京:科学出版社,2002.16-31
    [29] Krasnopolsky, V.M., and Schiller, H. Some neural network applications in environmental sciences. Neural networks, 2003, 16(3-4): 321-334
    [30] Mas, J.F. Mapping land use/cover in a tropical coastal area using satellite sensor data, GIS and artificial neural networks. Estuarine, Coastal and Shelf Science, 2004, 59(2): 219-230
    [31] Niang, A., Gross, L., Thiria, S., Badran, F., and Moulin, C. Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge. Remote Sensing of Environment, 2003, 86(2): 257-271
    [32] Lee, S.K., Chung, P.C., Chang, C.L., Lo, C.S., Lee, T., Hsu, G.C., and Yang C.W. Classification of clustered microcalcifications using a Shape Cognitron neural network. Neural networks, 2003, 16(1): 121-132
    [33] Michelson, D.B., Liljeberg, B.M., and Pilesjo, P. Comparison of algorithms for classifying Swedish landcover using Landsat TM and ERS- 1 SAR data. Remote Sensing of Environment, 2000, 71 (1): 1-15
    [34] Jeng, J.Y., Mau, T.F., and Leu, S.M. Prediction of laser butt joint welding parameters using back propagation and learning vector quantization networks. Journal of Materials Processing Technology, 2000, 99(1-3): 207-218
    [35] Zhu. A back propagation algorithm to estimate the parameters of non-linear dynamic rational models. Applied Mathematical Modelling, 2003, 27(3): 169-187
    [36] Chen, T. A fuzzy back propagation network for output time prediction in a wafer fab. Applied Soft Computing Journal, 2003, 2(3): 211-222
    [37] Krzyzak, A. Nonlinear function learning using optimal radial basis function newtworks. Nonlinear Analysis, 2001, 47(1): 293-302
    [38] Krzyzak, A. Convergence and rates of convergence of radial basis functions networks in function learning. Nonlinear Analysis, 2001, 47(1): 281-292
    [39] Ferreira, A.J.M. A formulation of the multiquadric radial basis function method for the analysis of laminated composite plates. Composite Sturctures, 2003, 59(3): 385-392
    [40] Walczak, B., and Massart D.L. Local modelling with radial basis function networks. Chemometrics and Intelligent Laboratory System, 2000, 50(2): 179-198
    [41] 赵英时等.遥感应用分析原理与方法.第1版.北京:科学出版社,2003.202-208
    [42] Foody, G.M. Status of land cover classification accuracy assessment. Remote Sensing of Environment, 2002, 80(1): 185-201
    
    
    [43] 柏延臣,王劲峰.遥感信息的不确定性研究.第1版.北京:地质出版社,2003.10-16
    [44] 廉茂庆,夏有军,杨秋玲.扎龙自然保护区湿地调水工程的实施.东北水利水电,2001,19(12):46-48
    [45] 潘启成.扎龙湿地应急调水工程的建设与管理.东北水利水电,2002,20(12):46,47,56
    [46] 杨春喜,冯建维.应急补水抢救扎龙湿地.水利天地,2001,(10):4-5
    [47] Lillesand,T.M.,and Kiefer, R.W.著,彭望碌等译.遥感与图像解译.第4版.北京:电子工业出版社,2003.132-142
    [48] 贾永红,张春森,王爱平.基于BP神经网络的多源遥感影像分类.西安科技学院学报,2001,21(1):58-60
    [49] 梁益同,胡江林.NOAA卫星图像神经网络分类方法的探讨.武汉测绘科技大学学报,2000,25(2):148-152
    [50] 毛建旭,王耀南.基于神经网络的遥感图像分类.测控技术,2001,20(5):29,30,32
    [51] 张建宝,陈晓峰,刘建华.用于遥感图象分类的神经网络的构造.中国图象图形学报,1999,4(A)(10):831-834
    [52] 韩敏,程磊.用于航空图片分类的神经网络模型.第二十一届中国控制会议论文集.杭州:浙江大学出版社,2002.452-456
    [53] 周成虎,骆剑承,杨晓梅,杨存建,刘庆生.遥感影像地学理解与分析.第1版.北京:科学出版社,2001.229-239
    [54] 杜惠茜,梅文博,李德生.一种改进的BP神经网络在遥感图像分类中的应用.北京理工大学学报,1998,18(4):485-488
    [55] 王耀南.卫星遥感图像的神经网络自动识别分类.湖南大学学报,1998,25(4):61-66
    [56] 李朝峰,王桂梁.模糊控制BP网络的遥感图象分类方法研究.中国矿业大学学报(自然科学版),2001,30(3):311-314
    [57] 夏国清,边信黔.基于鲁棒误差函数的BP算法.哈尔滨工程大学学报,1998,19(3):33-37
    [58] Han, M., Cheng, L., and Meng, H. Application of four-layer neural network on information extraction. Neural Networks, 2003, 16(5-6): 547-553
    [59] Han, M., Cheng, L. and Meng, H. Classification of Aerial Photograph Using Neural Network. Proc. of IEEE 2002 International Conference Systems, Man and Cybernetics, Tunisia, 2002, 6:93-98
    [60] Bojinski, S., Schaepman, M., Schlapfer, D., and Itten K. SPECCHIO: a spectrum database for remote sensing applications. Computers and Geosciences, 2003, 29(1): 27-38

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700