基于RS、GIS和ANN的珠江流域水质分析技术的研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
本论文以珠江水系广州河段为研究对象,提出了联合使用遥感(Remote
     Sensing,简称RS)、地理信息系统(Geographical Information System,简称GIS)和人工神经网络(Artificial Neural Networks,简称ANN)技术对珠江水质进行分析监测的新技术。该新技术能大大减轻传统的监测所耗人力和物力,并能对大范围水域进行快速监测。
     基于RS、GIS和ANN的监测技术主要是利用GIS对RS图像进行地理定位,然后利用RS专用软件提取定位点的RS数据,最后通过建立前馈误差反传人工神经网络(BP网络),确定TM(Thematic Mapper,专题成像仪,简称TM)数据前5个波段在定位点的反射率与水质三个主要参数的映射关系,即建立RS数据与水质的映射模型。本研究对模型建立过程、模型检验进行了探讨,得出了该监测技术完全能满足当前实际需要。
     本研究是建立在当前水色RS技术理论之上的,即RS数据与河水组成是呈复杂函数关系的,但当前水色RS卫星主要是针对海洋设计的,并不适用于内陆江河的水质分析,所以采用了陆地卫星Landsat系列的TM数据。又由于陆地卫星并不是针对水色RS理论建立起来的,所以需重新建立TM数据与水质参数的映射关系,这里采用人工神经网络技术建立两者之间的复杂关系。
     数据采集整理和模型建立是本研究中的两个重点。数据采集主要利用GIS和RS技术,同时采集相同时段的历史监测数据,数据整理主要是针对模型的训练数据,要采取均匀性原则。人工神经网络模型是最常用的含有一个隐层的两层BP(误差反向传播,Error Black Propagation,简称BP)网络,充分利用训练集数据和校验数据,确定了最佳隐节点数目是7个,最佳训练次数是1000次。
     利用这种新技术,可使预测误差小于20%,已经能够满足现实需要。
In this paper, remote sensing (RS) , geographical information system (GIS) and artificial neural networks (ANN) are combined to monitor River Pearl in Guangzhou city. This combination is regarded as a new technology for water quality. Compared to conventional measurement methods, it has advantages in decreasing manpower and material resource. In addition, it makes the rapid monitoring of big river possible.
    In the application of the new measurement technology based on RS, GIS and ANN , firstly, geography location is received by GIS and RS pictures. Secondly, RS data of location is gained by exclusive RS software. Finally, BP network is built up , so the relation between echo rate of five frontal bands of TM data is found.
    The new technology is built on current theory of water color RS, which shows that the relation between RS data and constitutes of river water. But the technology uses TM data of Landsat series because the satellites of water color RS are not designed for rivers inland but only for ocean. In the same way, the relation between TM data and water parameters is built by ANN in the technology, because Landsats are not made on theories of water RS.
    Two important contents in the technology are collection and pretreatment of data, and model's building process. GIS and RS are used during the process of collection of data, at the same time, synchronous history monitoring data is gained. Average principle is adopted during data's pretreatment. The model of ANN is one BP network of two layers including one hidden layer, which has seven nodes in hidden layer and whose perfect train times is 1000.
    The error of forecast by the new technology is less than 20 percentage, and so the new technology can reach practical need.
引文
[1] 张世森.环境监测技术[M].北京:高等教育出版社,1992
    [2] 刘瑞民,王学军.Rs、GIS在内陆湖泊水质研究中的应用[J].环境科学与技术,2001(1):1~4
    [3] 杨建刚.人工神经网络实用教程.杭州:浙江大学出版社,2001
    [4] 从爽.面向MATLAB工具箱的神经网络理论与应用.合肥:中国科技大学出版社,1998
    [5] 宁书年,吕松案等.RS图象处理与应用[M].北京:地震出版社,1995
    [6] Ritchie.J.C., and Cooper.C.M.. An algorithm for estimation surface suspended sediment Concentration with Landsat MSS digital data[J].Wat.Res.Bull., 1991, 27:373~379
    [7] Caims.S.H., Dickson.K.L., and Atkitson.S.F.. An examination of measuring selected water quality trophic indicators with SPOT satellite HRV data[J].Photogramm, EngRemote Sens., 1997, 63:263~265
    [8] Lathrop,R.G.,and Lillesand,T.m..Use of thematic mapper data to assess water quality in Green Bay and central Lake Michigan[J].Photogramm.Eng. Remote Seas.,1996, 52: 671~680
    [9] Lathrop,R.G.,and Lillesand,T.m.,and Yandell,b.s..Testing the utility of simple multidata thematic mapper calibration algorithms for monitoring of turbid inland water[J].Int.J.Remote Sens., 1997,10:2045~2063
    [10] 孙水裕,王孝武.环境信息系统[M].北京:化学工业出版社,2003,11:92~93
    [11] 陈安,罗亚田.人工神网络方法在环境科学领域应用进展.重庆环境科学.2003,25(9):65~70
    [12] 张文艺.基于人工神经网络的地面水环境质量评价模型.环境保护科学.2000,26(8):40~42
    [13] 李莹,邹经湘,张新政,蔡楠.河流水质的预测模型研究.系统仿真学报.2001,13(2):139~142
    [14] 刘罡,李昕,胡非.大气污染物浓度的神经网络预报.中国环境科学.2000,20(5):429~431
    
    
    [15] 郭宗楼,马帆.河流水质预测的因素状态网络模型研究.环境科学研究,2001,14(1):49~52
    [16] 郭劲松,等.间歇曝气活性污泥系统神经网络水质模型.中国给水排水,2000,16(11):15~18
    [17] 田禹,王宝贞,周定.基于BP人工神经网络无神经网络的臭氧生物活性系统建模研究.中国给水排水,1998,14(3):24~27
    [18] 聂亚峰,等.建立土壤硫释放过程的人工神经网络模型.上海环境科学,2001,20(7):349~351
    [19] 白桦,李圭白.混凝投药的神经网络控制方法.给水排水,2001,27(11):83~86
    [20] 王建平,程声通,贾海峰等.用TM影像进行湖泊水色反演研究的人工神经网络模型[J].环境科学,2003,24(2):73~76
    [21] 国际海洋水色协调工作组(IOCCG).海洋水色RS原理与应用[M].李四海译.北京:海洋出版社,2002,5:1~2
    [22] 赵英时等.RS应用分析原理与方法[M].北京:科学出版社,2003,6:413~420
    [23] Thomas M. Lillesand, Ralph W. Kiefer. Remote Sensing and Image Interpretation(Fourth Edition)(RS与图像解译(第四版))[M].彭望碌,余先川,周涛等译.北京:电子工业出版社,2003,8:258~330
    [24] 蒋宗礼.人工神经网络导论[M].北京:高等教育出版社,2001,8
    [25] 韩力群.人工神经网络理论、设计及应用[M].北京:化学工业出版社,2002,1
    [26] 赵保华,朱雪亮.太平洋海温预测的神经网络模型[J].计算机应用,1997,17(4):18~20
    [27] 刘国东,丁晶,张翔.应用人工神经网络求算含水层参数[J].工程勘察,1997.1:25~28
    [28] Carmeron M. Zealand, etc. Short term streamllow forecasting using artificial neural networks[J]. J. Hydro, 1999,214(1):32~48
    [29] Jose M. Paruelo, Fernando Tomasel. Prediction of functional characteristics of ecosystem: a comparison of artificial neural network
    
    and regression models[J]. Ecol. Model., 1997,98:173~186
    [30] Joo-Hwa Tay, Xieyue Zhang. Neural Fuzzy Modelling of Anaerobic Biological Wastewater Treatment Systems[J]. J. Envir. Engrg.,ASCE, 1999,12: 1149~1159
    [31] Cho, BC, etc. Development of a real-time control strategy with artificial neural network for automatic control of continuous-flow sequencing batch reactor[J]. Water Science & Technology, 2001,44(1):95~104
    [32] Catherine Faur-Brasquet, Pierre Le Cloirec. Neural network modeling of organics removal by activated carbon carths[J]. J.Envir. Engrg, 2001, (1):889~894
    [33] Wan, Terng-Jou, etc. An application of artificial neuromolecular system for effluent quality prediction of wastewater treatment plant. J.China. Inst. Environm. Eng.,2000,10(3):155~162
    [34] 王建平,程声通,贾海峰,王志石,邓宇华.用TM影像进行湖泊水色反演研究的人工神经网络模型[J].环境科学,2003,24(2):73~76

© 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