基于GIS的地面沉降预测研究
|
摘要
地面沉降是天津市主要的地质灾害,这种复杂的环境地质问题严重影响着城市基础设施建设,制约着天津市的经济发展。目前已普遍证实过量开采地下水造成地下水文地质力学平衡的破坏是导致地面沉降最主要的原因。因此,研究并建立适合该地区的沉降预测方法,为下一步天津市地面沉降的有效控制提供科学依据将具有积极而深远的意义。
首先,本研究选取历史观测数据较为完备的研究区作为研究示范区域,在优化了地面监测点的基础上,利用灰色关联理论对各个含水组与地面沉降系数进行了计算,然后通过肯达尔非参数秩次相关检验法对各个含水组的关联系数进行分析。
其次,以地下各含水组年均水位为输入变量,以优化后监测网络的各监测点年沉降值为输出变量,建立了地面沉降预测BP神经网络模型,并在此基础上,利用规则化调整和初期中止的方法对模型的泛化能力进行改进,此外还建立了径向基神经网络模型。通过三个模型的对比,筛选出了适合该地区的地面沉降预测模型。
最后,详细地阐述了如何利用ArcGIS设计和建立相关数据库和编制数据底图,如何利用空间分析功能对地下水等值线、地面沉降等值线等进行分析。并提出利用COM组件技术将Matlab与ArcGIS进行无缝结合,为ArcGIS与其它软件进行通信提供了一种思路。
Ground subsidence is one of the major geological disasters of Tianjin. This complex environmental geological problem seriously affects the construction of urban infrastructure facilities, so that restricts Tianjin's economic development. It has been widely confirmed that the major course of ground subsidence is the break of geohydrological mechanical equilibrium caused by excessive exploitation of groundwater. Therefore, it is important to establish a set of method to predict the ground subsidence in Tianjin. Thus it can offer scientific basis for effective control of ground subsidence.
Firstly, Tanggu District is selected as a model regional in this research, which has complete historical data. Based on optimized ground monitoring points, related analysis of gray system is employed to calculated each aquiferous group and the coefficient of ground subsidence. Kendall examination method is employed to analyze the coefficient of each aquiferous group.
Secondly, with input variables of average underground water levels and optimized values of ground subsidence monitoring points to be output variables, a BP neural network model for prediction of ground subsidence is established. On this basis, regularization and early stop methods are used to improve the generalization of this model. Besides, a RBF neural network model is established. With compares between these 3 models, a best model for prediction of ground water in this region is selected.
Finally, how to use ArcGIS to design and established the data base and data base map is described in detail, as well as how to use spatial analysis to analyze groundwater contour and ground subsidence. Moreover, a method for seamless integration for Matlab and ArcGIS is developed, which is based on COM technology. It explores a new method for communication between ArcGIS and other software.
首先,本研究选取历史观测数据较为完备的研究区作为研究示范区域,在优化了地面监测点的基础上,利用灰色关联理论对各个含水组与地面沉降系数进行了计算,然后通过肯达尔非参数秩次相关检验法对各个含水组的关联系数进行分析。
其次,以地下各含水组年均水位为输入变量,以优化后监测网络的各监测点年沉降值为输出变量,建立了地面沉降预测BP神经网络模型,并在此基础上,利用规则化调整和初期中止的方法对模型的泛化能力进行改进,此外还建立了径向基神经网络模型。通过三个模型的对比,筛选出了适合该地区的地面沉降预测模型。
最后,详细地阐述了如何利用ArcGIS设计和建立相关数据库和编制数据底图,如何利用空间分析功能对地下水等值线、地面沉降等值线等进行分析。并提出利用COM组件技术将Matlab与ArcGIS进行无缝结合,为ArcGIS与其它软件进行通信提供了一种思路。
Ground subsidence is one of the major geological disasters of Tianjin. This complex environmental geological problem seriously affects the construction of urban infrastructure facilities, so that restricts Tianjin's economic development. It has been widely confirmed that the major course of ground subsidence is the break of geohydrological mechanical equilibrium caused by excessive exploitation of groundwater. Therefore, it is important to establish a set of method to predict the ground subsidence in Tianjin. Thus it can offer scientific basis for effective control of ground subsidence.
Firstly, Tanggu District is selected as a model regional in this research, which has complete historical data. Based on optimized ground monitoring points, related analysis of gray system is employed to calculated each aquiferous group and the coefficient of ground subsidence. Kendall examination method is employed to analyze the coefficient of each aquiferous group.
Secondly, with input variables of average underground water levels and optimized values of ground subsidence monitoring points to be output variables, a BP neural network model for prediction of ground subsidence is established. On this basis, regularization and early stop methods are used to improve the generalization of this model. Besides, a RBF neural network model is established. With compares between these 3 models, a best model for prediction of ground water in this region is selected.
Finally, how to use ArcGIS to design and established the data base and data base map is described in detail, as well as how to use spatial analysis to analyze groundwater contour and ground subsidence. Moreover, a method for seamless integration for Matlab and ArcGIS is developed, which is based on COM technology. It explores a new method for communication between ArcGIS and other software.
引文
[1]郑铣鑫,沿海地区城市发展及地面沉降的系统控制[J],海洋地质与第四纪地质,1992,12(1):57~65
[2]殷跃平,张作辰,张开军,我国地面沉降现状及防治对策研究[J],中国地质灾害与防治学报,2005,16(2):1~8
[3]李铁锋,潘懋,灾害地质学[M],北京:北京大学出版社,2002
[4]彭汉兴,环境工程水文地质学[M],北京:中国水利水电出版社,1998
[5]刘毅,确定大江大河防洪堤高度应考虑地面沉降因素[J],上海地质,1998,(03):6~12
[6]周健,屠洪权,地下水位与环境岩土工程[M],上海:同济大学出版社,1995
[7]武胜忠,方鹏飞,地面沉降的计算理论和方法[J],太原理工大学学报,2000,31(2):162~166
[8] Bravo R,Rogers J R,New Three Dimensional Finite Difference Model of Ground Water Flow and Land Subsidence in the Houston Area[C],T G Proc 4th International Conference On Land Subsidence,Houston,IAHS Press,1992,78~96
[9] Leake S A,Simulation of Vertical Compaction in Models of Regional Ground-Water Flow[C],Proc 4th International Conference on Land Subsidence,Houston:IAHS Press,1993,565~574
[10]吴林高,缪俊发,抽灌水作用下土层变形及应力—应变本构律的研究[J],地球科学:中国地质大学学报,1995,20(5):581~588
[11]晏同珍,地面沉降规律预测新模式[J],地球科学-中国地质大学学报,1989,14(2):181~188
[12]刘毅,龚士良,上海市地面沉降泊松旋回长期预测[J],中国地质灾害与防治学报,1998,9(2):75~80
[13]阳军生,刘宝琛,抽水地面沉降预计的随机介质模型[J],水文地质工程地质,1999,26(5):11~13
[14]金爱善,采用神经网络模型对天津滨海新区地面沉降预测的研究[J],现代地质,2000,14(4):475~478
[15]刘金韬,武强,等,地面沉降计算中“长期释水系数”的概念及计算方法研究[J],中国矿业大学学报,2001,30(1):103~106
[16] Hu R L,Yue Z Q,Wang L C et al,Review On Current Status and Challenging Issues of Land Subsidence in China[J],Engineering Geology in China,2004,76(1-2):65~77
[17] Zhang Y,Xue Y Q,Wu J C,et al,Characteristics of Aquifer System Deformation in the Southern Yangtse Delta, China[J],Engineering Geology,2007,90(3-4):160~173
[18] Larson K J,Basagaoglu H,Mari M A,Prediction of Optimal Safe Ground Water Yield and Land Subsidence in the Los Banos-Kettleman City Area, California, Using a Calibrated Numerical Simulation Model[J],Journal of Hydrology,2001,242(1-2):79~102
[19]阎世骏,刘长礼,城市地面沉降研究现状与展望[J],地学前缘,1996,3(1):93~98
[20]胡俊杰,蒙爱军,天津地区的相对海平面上升与地面沉降[J],海洋信息,2005,(2):17~19
[21] Seber G A,Multivariate Observations[M],New York:Wiley,1984
[22] Spath H,Cluster Dissection and Analysis: Theory, Fortran Programs, Examples, Translated by J. Goldschmidt[M],New York:Halsted Press,1985
[23]张建军,地面沉降预测及经济影响评价研究[D],硕士,天津大学,2006
[24]王仁超,谭学奇,王秀杰等,区域性地面沉降量预测的灰色与时间序列方法[J],水利水电技术,2005,36(2):32~35
[25]林跃忠,地面沉降量的灰色预测方法[J],山东科技大学学报(自然科学版),2000,19(3):108~110
[26]王学萌,张继忠,王荣,灰色系统分析及实用计算程序[M],武汉:华中科技大学出版社,2001
[27]邓聚龙,灰色理论基础[M],武汉:华中科技大学出版社,2002
[28]潘国营,钟福平,姜衍祥等,应用灰色关联分析法识别导致地面沉降的抽水层位[J],河南理工大学学报(自然科学版),2006,25(1):18~21
[29]张迎春,基于模糊神经网络的股票价格预测研究[D],硕士,南京气象学院,2003
[30]张学真,城市化对供水河流水文序列的影响分析[J],水利经济,2005,23(1):39~41
[31]伊利军,唐玲,用肯达尔检验法对淄博市河流水质趋势进行分析[J],水文水资源,2001,22(3):20~20
[32] Yue S,Pilon P,Cavadias G,Corrigendum to "power of the Mann-Kendall and Spearman's Rho Tests for Detecting Monotonic Trends in Hydrological Series" [J],Journal of Hydrology,2002,264(1-4):262~263
[33]武建强,余勤,神经网络技术在地面沉降区划中的应用研究[J],江苏地质,2003,27(3):171~174
[34]王巧平,李明良,卢胜勇,河北省京津以南平原区地面沉降预测研究[J],南水北调与水利科技,2002,23(2):27~30
[35] Coppola J E,Szidarovszky F,Poulton M,et al,Artificial Neural Network Approach for Predicting Transient Water Levels in a Multilayered Groundwater System Under Variable State, Pumping, and Climate Conditions[J],Journal of Hydrologic Engineering,2003,8:348~360
[36] Jiangong C , A Neural Network Method to Evaluate Consolidation Coefficient[J],Journal of Chongqing University,2003,(01):1~4
[37]兰云,短时交通流量预测研究[D],硕士,西北工业大学,2002
[38]闻新,周露,李翔,Matlab神经网络仿真与应用[M],北京:科学出版社,2003
[39]刘俊萍,畅明琦,RBF神经网络模型在山西省需水预测中的应用[J],人民黄河,2007,(04)
[40] Jean J S,Wang J,Weight Smoothing to Improve Network Generalization[J],Neural Networks, IEEE Transactions on,1994,5(5):752~763
[41]唐巍,张学义,神经网络权值的混沌优化方法研究[J],哈尔滨工程大学学报,2000,21(3):12~14
[42]王忠忠,钱为民,径向基神经网络在地面沉降预测中的应用[J],地下水,2006,28(2):84~87
[43]张兴兰,RBF神经网络理论及其在脱硫智能控制系统中的应用[D],硕士,重庆大学,2002
[44] Liji T,Ning W,Splicing System Based Genetic Algorithms for Developing RBF Net-Works Models[J],Chinese Journal of Chemical Engineering,2007,(02):240~246
[45] Wang L,Shao C,Wang H,et al,Radial Basis Function Neural Networks-Based Modeling of the Membrane Separation Process: Hydrogen Recovery From Refinery Gases[J],Journal of Natural Gas Chemistry,2006,15(3):230~234
[46]李红艳,城市给水系统优化调度模型研究[D],硕士,太原理工大学,2003
[47]朱树先,张仁杰,BP和RBF神经网络在人脸识别中的比较[J],仪器仪表学报,2007,(02):375~379
[48] Chu Z X,Sun X G,Zhai S K,et al,Changing Pattern of Accretion/Erosion of the Modern Yellow River (Huanghe) Subaerial Delta, China: Based On Remote Sensing Images[J],Marine Geology,2006,227(1-2):13~30
[49]汤国安,杨昕,ARCGIS地理信息系统空间分析试验教程[M],北京:科学出版社,2006
[50]周卫,利用Arcview实现地面沉降数据的处理和可视化[J],南京建筑工程学院学报(自然科学版),2001,(4):59~64
[2]殷跃平,张作辰,张开军,我国地面沉降现状及防治对策研究[J],中国地质灾害与防治学报,2005,16(2):1~8
[3]李铁锋,潘懋,灾害地质学[M],北京:北京大学出版社,2002
[4]彭汉兴,环境工程水文地质学[M],北京:中国水利水电出版社,1998
[5]刘毅,确定大江大河防洪堤高度应考虑地面沉降因素[J],上海地质,1998,(03):6~12
[6]周健,屠洪权,地下水位与环境岩土工程[M],上海:同济大学出版社,1995
[7]武胜忠,方鹏飞,地面沉降的计算理论和方法[J],太原理工大学学报,2000,31(2):162~166
[8] Bravo R,Rogers J R,New Three Dimensional Finite Difference Model of Ground Water Flow and Land Subsidence in the Houston Area[C],T G Proc 4th International Conference On Land Subsidence,Houston,IAHS Press,1992,78~96
[9] Leake S A,Simulation of Vertical Compaction in Models of Regional Ground-Water Flow[C],Proc 4th International Conference on Land Subsidence,Houston:IAHS Press,1993,565~574
[10]吴林高,缪俊发,抽灌水作用下土层变形及应力—应变本构律的研究[J],地球科学:中国地质大学学报,1995,20(5):581~588
[11]晏同珍,地面沉降规律预测新模式[J],地球科学-中国地质大学学报,1989,14(2):181~188
[12]刘毅,龚士良,上海市地面沉降泊松旋回长期预测[J],中国地质灾害与防治学报,1998,9(2):75~80
[13]阳军生,刘宝琛,抽水地面沉降预计的随机介质模型[J],水文地质工程地质,1999,26(5):11~13
[14]金爱善,采用神经网络模型对天津滨海新区地面沉降预测的研究[J],现代地质,2000,14(4):475~478
[15]刘金韬,武强,等,地面沉降计算中“长期释水系数”的概念及计算方法研究[J],中国矿业大学学报,2001,30(1):103~106
[16] Hu R L,Yue Z Q,Wang L C et al,Review On Current Status and Challenging Issues of Land Subsidence in China[J],Engineering Geology in China,2004,76(1-2):65~77
[17] Zhang Y,Xue Y Q,Wu J C,et al,Characteristics of Aquifer System Deformation in the Southern Yangtse Delta, China[J],Engineering Geology,2007,90(3-4):160~173
[18] Larson K J,Basagaoglu H,Mari M A,Prediction of Optimal Safe Ground Water Yield and Land Subsidence in the Los Banos-Kettleman City Area, California, Using a Calibrated Numerical Simulation Model[J],Journal of Hydrology,2001,242(1-2):79~102
[19]阎世骏,刘长礼,城市地面沉降研究现状与展望[J],地学前缘,1996,3(1):93~98
[20]胡俊杰,蒙爱军,天津地区的相对海平面上升与地面沉降[J],海洋信息,2005,(2):17~19
[21] Seber G A,Multivariate Observations[M],New York:Wiley,1984
[22] Spath H,Cluster Dissection and Analysis: Theory, Fortran Programs, Examples, Translated by J. Goldschmidt[M],New York:Halsted Press,1985
[23]张建军,地面沉降预测及经济影响评价研究[D],硕士,天津大学,2006
[24]王仁超,谭学奇,王秀杰等,区域性地面沉降量预测的灰色与时间序列方法[J],水利水电技术,2005,36(2):32~35
[25]林跃忠,地面沉降量的灰色预测方法[J],山东科技大学学报(自然科学版),2000,19(3):108~110
[26]王学萌,张继忠,王荣,灰色系统分析及实用计算程序[M],武汉:华中科技大学出版社,2001
[27]邓聚龙,灰色理论基础[M],武汉:华中科技大学出版社,2002
[28]潘国营,钟福平,姜衍祥等,应用灰色关联分析法识别导致地面沉降的抽水层位[J],河南理工大学学报(自然科学版),2006,25(1):18~21
[29]张迎春,基于模糊神经网络的股票价格预测研究[D],硕士,南京气象学院,2003
[30]张学真,城市化对供水河流水文序列的影响分析[J],水利经济,2005,23(1):39~41
[31]伊利军,唐玲,用肯达尔检验法对淄博市河流水质趋势进行分析[J],水文水资源,2001,22(3):20~20
[32] Yue S,Pilon P,Cavadias G,Corrigendum to "power of the Mann-Kendall and Spearman's Rho Tests for Detecting Monotonic Trends in Hydrological Series" [J],Journal of Hydrology,2002,264(1-4):262~263
[33]武建强,余勤,神经网络技术在地面沉降区划中的应用研究[J],江苏地质,2003,27(3):171~174
[34]王巧平,李明良,卢胜勇,河北省京津以南平原区地面沉降预测研究[J],南水北调与水利科技,2002,23(2):27~30
[35] Coppola J E,Szidarovszky F,Poulton M,et al,Artificial Neural Network Approach for Predicting Transient Water Levels in a Multilayered Groundwater System Under Variable State, Pumping, and Climate Conditions[J],Journal of Hydrologic Engineering,2003,8:348~360
[36] Jiangong C , A Neural Network Method to Evaluate Consolidation Coefficient[J],Journal of Chongqing University,2003,(01):1~4
[37]兰云,短时交通流量预测研究[D],硕士,西北工业大学,2002
[38]闻新,周露,李翔,Matlab神经网络仿真与应用[M],北京:科学出版社,2003
[39]刘俊萍,畅明琦,RBF神经网络模型在山西省需水预测中的应用[J],人民黄河,2007,(04)
[40] Jean J S,Wang J,Weight Smoothing to Improve Network Generalization[J],Neural Networks, IEEE Transactions on,1994,5(5):752~763
[41]唐巍,张学义,神经网络权值的混沌优化方法研究[J],哈尔滨工程大学学报,2000,21(3):12~14
[42]王忠忠,钱为民,径向基神经网络在地面沉降预测中的应用[J],地下水,2006,28(2):84~87
[43]张兴兰,RBF神经网络理论及其在脱硫智能控制系统中的应用[D],硕士,重庆大学,2002
[44] Liji T,Ning W,Splicing System Based Genetic Algorithms for Developing RBF Net-Works Models[J],Chinese Journal of Chemical Engineering,2007,(02):240~246
[45] Wang L,Shao C,Wang H,et al,Radial Basis Function Neural Networks-Based Modeling of the Membrane Separation Process: Hydrogen Recovery From Refinery Gases[J],Journal of Natural Gas Chemistry,2006,15(3):230~234
[46]李红艳,城市给水系统优化调度模型研究[D],硕士,太原理工大学,2003
[47]朱树先,张仁杰,BP和RBF神经网络在人脸识别中的比较[J],仪器仪表学报,2007,(02):375~379
[48] Chu Z X,Sun X G,Zhai S K,et al,Changing Pattern of Accretion/Erosion of the Modern Yellow River (Huanghe) Subaerial Delta, China: Based On Remote Sensing Images[J],Marine Geology,2006,227(1-2):13~30
[49]汤国安,杨昕,ARCGIS地理信息系统空间分析试验教程[M],北京:科学出版社,2006
[50]周卫,利用Arcview实现地面沉降数据的处理和可视化[J],南京建筑工程学院学报(自然科学版),2001,(4):59~64