复杂地学G~4I系统数据集成与云计算关键技术研究
|
摘要
随着信息技术尤其是3S技术的广泛应用,促进了各类地球科学数据的逐步实现了现代化、数字化和网络化。国家在地质采矿、地质地理测绘、土地资源与海洋勘探等领域建设成了全国性的基础地球科学库达上百种,完成各类研究成果报告几十万份,积累了海量的地球科学数据信息。由于各类地球科学数据具有多元化、多尺度、多分辨率、多学科、多类型、多标准等特征,使建立各领域地学空间数据库存在很大难度,并且已建成的各类地学数据库绝大多数处于相对独立的运行状态,数据综合应用、集成和分析程度低,严重制约的各类矿产预测工作的顺利进行。因此,对利用数据集成和数据融合技术对现有的地学空间数据进行科学地操作和管理是地学空间数据领域热点问题,也本文研究内容之一。
现有的各种GIS系统无法有效的集成融合局部地区或全国范围的多元(源)地学数据,同时由于各类地学数据具有分散海量性的特点,现有单机、基于局域网络或互联网络的各种GIS系统以及各种矿产资源预测和评价系统无法提供快速、高效、稳定、可靠的计算资源和管理资源。因此,为了更好完成海量地学数据的数据存储、数据集成融合、数据挖掘和矿产预测与评价,本文将信息技术领域最新的云计算技术融入到现有的地学G4I系统中,构建了基于地学G4I系统的云计算服务系统框架结构体系,认真研究了云计算的分布式数据存储技术、服务器资源虚拟化技术以及并行计算等关键技术。
本文主要研究工作是在吉林大学已经成功研制的具有自主知识产权的“地学G4I系统”基础上,将地学领域具有多源、异构、分散等特性的地学空间数据作为研究对象。探讨与研究数据集成技术和云计算技术在地学G4I系统中的应用。
本文研究内容和成果如下：
1、提出了基于地学G4I系统中地学空间数据的管理方式,以及地学空间数据集成和地学空间数据融合方法。
2、提出了基于地学G4I系统地学空间数据库的互操作技术。
3、针对大规模数据信息和计算资源的特征及其数据处理要求,本文采用云计算技术将网络中各种可用的计算机资源整合为高效的计算集群,采用Hadoop架构和MapReduce编程模型,将地学空间大数据处理任务以分布式的处理方式,分解成众多子任务,在计算集群中的大量计算节点上进行并行处理和计算,提升地学空间大数据的处理能力。云计算平台为地学数据集成与系统集成、地学空间建模(空间统计建模与空间可视化建模)、地学过程模拟仿真及矿产资源预测和评价提供了强大的技术支撑。
复杂地学G4I系统,采用人机交互式操作模式进行地球物理重磁反演解释与人工智能相结合,在云计算环境下执行系统的计算、分析和存储任务。大多数技术可以代表我国目前地学信息化领域的前沿技术,可以满足目前我国地学信息化领域的绝大多数技术需求。
As information technology, especially the wide application of3S technology, promoting progressive types of earth science data to achieve a modern, digital and networking. Countries in geological mining, geology and geography mapping, land resources and the construction of marine exploration and other fields has become the basis for a national database of hundreds of Earth Sciences, completion of various research reports hundreds of thousands of copies, has accumulated vast amounts of earth science data. Since the various earth science data has a diversified, multi-scale, multi-resolution, multi-disciplinary, multi-type, multi-standard and other characteristics that make establishing various fields geospatial database exists great difficulty, and has built the vast types of geoscience databases most are relatively independent of the operating status, data integration applications, integration and analysis of the low level of seriously restricting the types of mineral resources prediction work smoothly. Therefore, the use of data integration and data fusion technology to the existing geospatial data for scientific operations and management is the study of the field of hot issues of spatial data, but also the content of this paper.
Various existing GIS system integration can not be effectively integrated multi-local or nationwide (source) for earth science data, and because the various geoscience data has a mass dispersion of the characteristics of the existing stand-alone, based on a local area network or the Internet GIS systems as well as various kinds of mineral resources prediction and evaluation system is unable to provide fast, efficient, stable and reliable computing resources and manage them. Therefore, in order to better accomplish massive geoscience data, data storage, data integration, fusion, data mining and mineral prediction and evaluation, this article will field of information technology the latest cloud computing technologies into existing geoscience G4I system was constructed based on geo G4I systematic framework for cloud computing service system architecture, careful study of cloud computing, distributed data storage, network computing resource integration and scheduling, and parallel computing, and other key technologies.
This paper studies done in Jilin University has successfully developed with independent intellectual property rights of "Earth Science G4I System", based on the multi-source field of earth science, heterogeneous, distributed and other characteristics of geospatial data for the study. Discussion and research data integration technology and cloud computing technology in geoscience G4I System.
In this paper, the content and results are as follows:
1.This paper presents geo spatial data management based on geo G4I, and geospatial data integration and geospatial data fusion methods.
2.This paper presents a geospatial database interoperability technologies based on geo G4I.
3.For large-scale data, information and computing resources characteristics and data processing requirements, this article uses cloud computing technology to network the various available computer resources for the efficient integration of the computing cluster, using the Hadoop framework and MapReduce programming model, geospatial big data processing tasks in a distributed approach, broken down into a number of sub-tasks, a large number in the calculation of the cluster compute nodes for parallel processing and computing to enhance geospatial large data processing capabilities. Cloud computing platform geoscience data integration and system integration, geospatial modeling (spatial statistical modeling and spatial visualization modeling), earth science process simulation and prediction and evaluation of mineral resources provides a powerful technical support.
Complex Geo G4I systems, man-machine interactive operation mode inversion of gravity and magnetic geophysical interpretation and artificial intelligence are combined in a cloud computing environment to perform system calculations, analysis and storage tasks. Most of the techniques can represent our current information in the field of geosciences cutting-edge technology, to meet the current information in the field of geosciences vast majority of technical requirements.
现有的各种GIS系统无法有效的集成融合局部地区或全国范围的多元(源)地学数据,同时由于各类地学数据具有分散海量性的特点,现有单机、基于局域网络或互联网络的各种GIS系统以及各种矿产资源预测和评价系统无法提供快速、高效、稳定、可靠的计算资源和管理资源。因此,为了更好完成海量地学数据的数据存储、数据集成融合、数据挖掘和矿产预测与评价,本文将信息技术领域最新的云计算技术融入到现有的地学G4I系统中,构建了基于地学G4I系统的云计算服务系统框架结构体系,认真研究了云计算的分布式数据存储技术、服务器资源虚拟化技术以及并行计算等关键技术。
本文主要研究工作是在吉林大学已经成功研制的具有自主知识产权的“地学G4I系统”基础上,将地学领域具有多源、异构、分散等特性的地学空间数据作为研究对象。探讨与研究数据集成技术和云计算技术在地学G4I系统中的应用。
本文研究内容和成果如下：
1、提出了基于地学G4I系统中地学空间数据的管理方式,以及地学空间数据集成和地学空间数据融合方法。
2、提出了基于地学G4I系统地学空间数据库的互操作技术。
3、针对大规模数据信息和计算资源的特征及其数据处理要求,本文采用云计算技术将网络中各种可用的计算机资源整合为高效的计算集群,采用Hadoop架构和MapReduce编程模型,将地学空间大数据处理任务以分布式的处理方式,分解成众多子任务,在计算集群中的大量计算节点上进行并行处理和计算,提升地学空间大数据的处理能力。云计算平台为地学数据集成与系统集成、地学空间建模(空间统计建模与空间可视化建模)、地学过程模拟仿真及矿产资源预测和评价提供了强大的技术支撑。
复杂地学G4I系统,采用人机交互式操作模式进行地球物理重磁反演解释与人工智能相结合,在云计算环境下执行系统的计算、分析和存储任务。大多数技术可以代表我国目前地学信息化领域的前沿技术,可以满足目前我国地学信息化领域的绝大多数技术需求。
As information technology, especially the wide application of3S technology, promoting progressive types of earth science data to achieve a modern, digital and networking. Countries in geological mining, geology and geography mapping, land resources and the construction of marine exploration and other fields has become the basis for a national database of hundreds of Earth Sciences, completion of various research reports hundreds of thousands of copies, has accumulated vast amounts of earth science data. Since the various earth science data has a diversified, multi-scale, multi-resolution, multi-disciplinary, multi-type, multi-standard and other characteristics that make establishing various fields geospatial database exists great difficulty, and has built the vast types of geoscience databases most are relatively independent of the operating status, data integration applications, integration and analysis of the low level of seriously restricting the types of mineral resources prediction work smoothly. Therefore, the use of data integration and data fusion technology to the existing geospatial data for scientific operations and management is the study of the field of hot issues of spatial data, but also the content of this paper.
Various existing GIS system integration can not be effectively integrated multi-local or nationwide (source) for earth science data, and because the various geoscience data has a mass dispersion of the characteristics of the existing stand-alone, based on a local area network or the Internet GIS systems as well as various kinds of mineral resources prediction and evaluation system is unable to provide fast, efficient, stable and reliable computing resources and manage them. Therefore, in order to better accomplish massive geoscience data, data storage, data integration, fusion, data mining and mineral prediction and evaluation, this article will field of information technology the latest cloud computing technologies into existing geoscience G4I system was constructed based on geo G4I systematic framework for cloud computing service system architecture, careful study of cloud computing, distributed data storage, network computing resource integration and scheduling, and parallel computing, and other key technologies.
This paper studies done in Jilin University has successfully developed with independent intellectual property rights of "Earth Science G4I System", based on the multi-source field of earth science, heterogeneous, distributed and other characteristics of geospatial data for the study. Discussion and research data integration technology and cloud computing technology in geoscience G4I System.
In this paper, the content and results are as follows:
1.This paper presents geo spatial data management based on geo G4I, and geospatial data integration and geospatial data fusion methods.
2.This paper presents a geospatial database interoperability technologies based on geo G4I.
3.For large-scale data, information and computing resources characteristics and data processing requirements, this article uses cloud computing technology to network the various available computer resources for the efficient integration of the computing cluster, using the Hadoop framework and MapReduce programming model, geospatial big data processing tasks in a distributed approach, broken down into a number of sub-tasks, a large number in the calculation of the cluster compute nodes for parallel processing and computing to enhance geospatial large data processing capabilities. Cloud computing platform geoscience data integration and system integration, geospatial modeling (spatial statistical modeling and spatial visualization modeling), earth science process simulation and prediction and evaluation of mineral resources provides a powerful technical support.
Complex Geo G4I systems, man-machine interactive operation mode inversion of gravity and magnetic geophysical interpretation and artificial intelligence are combined in a cloud computing environment to perform system calculations, analysis and storage tasks. Most of the techniques can represent our current information in the field of geosciences cutting-edge technology, to meet the current information in the field of geosciences vast majority of technical requirements.
引文
[1]陈述彭,地学的探索,科学出版社,2003年第1版,302-305,53-55.
[2]王润生等,地质勘查图像分析与综合,地质出版社,1999年第1版.
[3]李德仁,空间信息系统的集成与实现,武汉测绘科技大学出版社,2000年第1版.
[4]杨自安等,化探与一个信息在青海两兰地区找矿预测中的应用,地质与勘探,2003.6.
[5]何国金、李克鲁、胡德永,多卫星遥感数据的信息融合：理论、方法与实践,中国图像图形学报A,1999.9.
[6]Costantiti、M.Farina、A.ZirilliF, The fusion of different resolution SAR images, In:Proceeding softhe IEEE,1997,85(1):139-146.
[7]龚建华、林珲,虚拟地理环境,高等教育出版社,2002,100-101.
[8]蓝国兴、艾国强,信息融合技术,计算机世界,1997.5月,107-108.
[9]DASKALAKIS、KOPANASI、COUDARAM, etal, Data Mining for Derision Support on Customer Insolvency in communications Business [J], European Journal of Operational Research,2003,145(2):239-255.
[10]唐文周,我国遥感地质工作的现状和近期展望,国土资源遥感,1998.2.
[11]王燕、李睿、李明.数据挖掘技术应用研究[J].甘肃科技,2001,17(1)：49-50
[12]唐泽圣,三维数据场可视化,清华大学出版社,1999.
[13]ANANTHANARAYANA V S、NARASIMHA MURTY M、 SUBRAMAVIAN D K, Tree Structure for Efficient Data Mining Using Rough Sets[J], Pattern Recognition Letters,2003,24(6):851-862.
[14]WoodM.K.Brodlie, ViscANDGIS:Some Fundamental Considera2tions, Visualizationin Geographical Information System, edited by Hi21aryM. Hearnshaw & DavidJ.Urwin,1994,3-8.
[15]KAO S C、CHANG H C、LIN C H, Decision Support for the Academic Library Acquisition Budget Allocation via Circulation Database Mining[J], Information Processing & Management,2003,39(6):133-147.
[16]ZHONG NING、DONG JU-ZHE、SETSUO OHSUGA, Mining Data Mining by Cooperatively Using GDT-RS and RSBR[J], Pattern Recognition Letters, 2003,24(6):887-894.
[17]Visvalingam.M. Visualizationin GIS. Cartography and Vics. Visualiza2tionin Geographical Information System. Edited by HilaryM. Hearnshaw & DavidJ. Urwin,1994,18-25.
[18]江斌、黄波、陆锋.GIS环境下的空间分析和地学视觉化,高等教育出版社,2000年第1版,160.
[19]秦举礼,遥感和多源地学数据图像处理技术及在地质找矿中的应用,四川地质学报,1996.1.
[20]ZHOU ZHI-HUA, Tree Perspectives of Data Mining[J], Artificial Intelligence, 2003,143(1):139-146.
[21]McCormickB. H.DefantiM.D.. BrownM.D. Visualization in Sci2entific Computing. SpecialIssueACMSIGGRAPH Computer Graphics,1987,21(6).
[22]陈述彭、童庆禧、郭华东,遥感信息机理研究,科学出版社,1998,159.
[23]Philbrick.A.K. Towardaunity of carto graphicforms and geographical content, Professional Geographer,1953,5(5):11-15.
[24]查显节、邢立新等,基于空间形态特征的遥感边缘信息提取方法,吉林大学学报(地球科学版),2004.3.
[25]唐泽圣,三维数据场可视化,清华大学出版社,1999.
[26]邢立新、潘军等,Hough变换在线性信息提取中的应用研究,长沙遥感学术会议论文集,2004.
[27]罗森林、王越、周思永,多源信息处理技术——数据融合,系统工程与电子技术,1998.
[28]Ren C luo et al. M ultisenso r Integration and Fusion fo r Intelligent Machines and System s, North Carolina State University, Ables Publishing Corporation, 1995.
[29]刘宴淼、余金生、李纯杰,基于图像处理技术的矿产预测综合分析系统[J],物化探计算技术,1994,16(1)：22-28.
[30]罗可、蔡碧野、胜贤、谢中科,数据挖掘及其发展研究,计算机工程与应用,2002.14.
[31]ChavezPSJr、SidesSC、AndersonJA, Comparison of three differentme thodstomerge multiresolution and multispectral data:TM & SPOT pan[J], Photogrammetric Engineering and RemoteSensing,1991,57(3):295-303.
[32]Corbley K P. Canad applies new processing technology to"old"data in mining exploration project [J], Earth Observation,1994,5:34-36.
[33]Leckie DG.S ynergsim of SAR and visible infrared data for forestty pediscrimination [J], Photogrammetric Engineering and Remote Sensing,1990, 56(9):1237-1246.
[34]江东、王钰、王建华、兰朝利,多源图像信息融合的理论与技术,甘肃科学学报,2002.1.
[35]ZHONG NING、DONG JU-ZHEEN、SETSUO OHSUGA, Mining Data Mining by Cooperatively Using GDT-RS and RSBR[J], Pattern Recognition Letters, 2003,24(6):887-894.
[36]李德仁、程涛,从GIS数据库中发现知识,测绘学报,1995,24(1)：37-43.
[37]龚建华、林珲,虚拟地理环境,高等教育出版社,2002.
[38][加]Jiawei Han Micheline Kamber著,范明、孟小峰译,数据挖掘概念与技术,机械工业出版社,2005年第1版,301-313.
[39][美] George M. Marakas著,敖富江译,数据仓库、挖掘和可视化——核心概念,清华大学出版社,2004,29、93.
[40]陈中祥、岳超源,空间数据挖掘的研究与发展,计算机工程与应用2003.3.
[41]PohlC、 GenderenJLVan, Multisensor image fusionin remote sensing:concepts, methods and applications [J], International Journalof Remote Sensing,1998, 9(5):823-854.
[42][美]Tom Soukup Ian Davidson著,朱建秋、蔡伟杰译,可视化数据挖掘,电子工业出版社,2004年第1版,3-4.
[43]承继成、林晖、周成虎等,数字地球导论,科学出版社,2000年1月第1版.
[44]郁文贤等,多传感器信息融合技术评述,国防科技大学学报,1994.
[45]ANANTHANARAYANA V S、 NARASIMHA MURTY M、 SUBRAMAVIAN D K, Tree Structure for Efficient Data Mining Using Rough Sets[J], Pattern Recognition Letters,2003,24(6):851-862.
[46]陈建军、余志强等,数据可视化技术及其应用[J],红外与激光工程,2001, 30(5)：239-243.
[47]晓梅等,科学计算可视化导论[M],长沙：国防科技大学出版社,1996,1-18.
[48]谢东升、李旭祥,可视化技术及其在环境科学中的应用,新疆环境保护,2004,26(1)：25-29.
[49]DASKALAKIS、KOPANAS I、 COUDARA M, etal.Data Mining for Derision Support on Customer Insolvency in communications Business [J], European Journal of Operational Research,2003,145(2):239-255.
[50]KAOSC、 CHANG H C、LINCH, Decision Support for the Academic Library Acquisition Budget Allocation via Circulation Database Mining[J], Information Processing & Management,2003,39(6):133-147.
[51]李德仁、龚健雅、朱欣焰、梁宜希,我国地球空间数据框架的设计思想与技术路线,武汉测绘科技学报,1998,Vo1.23,No4,297-303.
[52]宫鹏、史培军、浦瑞良等,对地观测技术与地球系统,科学出版社,1996.8.
[53]GIS环境下的空间分析和地学视觉化,汪斌,黄波,陆锋,高等教育出版社,2002.5,P98-99.
[54]李德仁、关泽群,空间信息系统的集成与实现,武汉：武汉测绘科技大学出版社,2003年3月第1版.
[55]陈常松、何建邦,面向GIS数据共享的概念模型设计研究,遥感学报,1999,3(3)：230-235.
[56]崔伟宏,空间数据结构研究,北京：中国科学技术出版社,1995.
[57]陈军,GIS空间数据模型的基本问题和学术前言,地理学报,1995,50(增刊)：24-32.
[58]地理信息系统与管理决策,科技部国家遥感中心,北京大学出版社,2000.4,P57.
[59]空间数据库,Shashi Shekhar, Sanjay Chawla著,谢昆青,马修军,杨冬青等译,机械工业出版社,2004.1,P28、P32.
[60]杜清运,空间信息的结构、表达及其理解机制,武汉测绘科技大学学报,1998,23(4)：388-392.
[61]地理信息系统,汤国安,赵牡丹,科学出版社,2000.10,P32-39、P90-107.
[62][美]Michael Zeiler著,张晓祥、张峰、姚静等译,为我们的世界建模—ESRI地理数据库设计指南,人民邮电出版社,2004年12月第1版.
[63]空间数据发掘与知识发现,邸凯昌,武汉大学出版社,2000.12,P3-4.
[64]地理信息系统基本原理及应用,朱光,李晓燕,戎兵,测绘出版社,1997.6,P30.
[65]周成虎、骆剑承、杨晓梅等,《遥感影像地学理解与分析》,科学出版社,2001.
[66]王今飞,遥感卫星图像中线性地质特征的自动提取,第四纪研究,2000年,20(3),P252-258.
[67]赵英时等,遥感应用分析原理与方法,科学出版社,2003,273-276.
[68]王磊,陈刚,陆忠华.基于云计算的高效科学计算应用软件框架[J].华中科技大学学报(自然科学版).2011.39(1)：166-169,183
[69]李刚健.基于虚拟化技术的云计算平台架构研究[J].吉林建筑工程学院学报.2011.28(1)：79-81
[70]陈维崧,陈庆秋.基于云计算的GIS研究[J].测绘与空间地理信息.2011.34(1)：157-161
[71]李嘉虓,陈华根.基于云计算的地学云系统设计[J].计算机工程与科学.2011.33(6)：108-113
[72]滕菲,路来君,孟庆龙.地学G4I系统的开发研究[J].吉林地质.2006.25(4)50-55
[73]史佩昌,王怀民,蒋杰.面向云计算的网络化平台研究与实现[J].计算机工程与科
[74]韩冰,路来君.地学G4I系统中空间元数据的设计技术[J].世界地质.2011.30(2)：307-312.
[75]王鹏,董静宜.一种云计算框架的实现方法研究[J].计算机工程与科学.2009.31(A1)：11-13.
[76]李玲,付园,麻晓珍,张海蓉.云存储系统中数据冗余策略优化问题[J].吉林大学学报(信息科学版).2013.31(1)：1-7.
[77]陈康,郑纬民.云计算：系统实例与研究现状[J].软件学报.2009.20(5)：1337-1348.
[2]王润生等,地质勘查图像分析与综合,地质出版社,1999年第1版.
[3]李德仁,空间信息系统的集成与实现,武汉测绘科技大学出版社,2000年第1版.
[4]杨自安等,化探与一个信息在青海两兰地区找矿预测中的应用,地质与勘探,2003.6.
[5]何国金、李克鲁、胡德永,多卫星遥感数据的信息融合：理论、方法与实践,中国图像图形学报A,1999.9.
[6]Costantiti、M.Farina、A.ZirilliF, The fusion of different resolution SAR images, In:Proceeding softhe IEEE,1997,85(1):139-146.
[7]龚建华、林珲,虚拟地理环境,高等教育出版社,2002,100-101.
[8]蓝国兴、艾国强,信息融合技术,计算机世界,1997.5月,107-108.
[9]DASKALAKIS、KOPANASI、COUDARAM, etal, Data Mining for Derision Support on Customer Insolvency in communications Business [J], European Journal of Operational Research,2003,145(2):239-255.
[10]唐文周,我国遥感地质工作的现状和近期展望,国土资源遥感,1998.2.
[11]王燕、李睿、李明.数据挖掘技术应用研究[J].甘肃科技,2001,17(1)：49-50
[12]唐泽圣,三维数据场可视化,清华大学出版社,1999.
[13]ANANTHANARAYANA V S、NARASIMHA MURTY M、 SUBRAMAVIAN D K, Tree Structure for Efficient Data Mining Using Rough Sets[J], Pattern Recognition Letters,2003,24(6):851-862.
[14]WoodM.K.Brodlie, ViscANDGIS:Some Fundamental Considera2tions, Visualizationin Geographical Information System, edited by Hi21aryM. Hearnshaw & DavidJ.Urwin,1994,3-8.
[15]KAO S C、CHANG H C、LIN C H, Decision Support for the Academic Library Acquisition Budget Allocation via Circulation Database Mining[J], Information Processing & Management,2003,39(6):133-147.
[16]ZHONG NING、DONG JU-ZHE、SETSUO OHSUGA, Mining Data Mining by Cooperatively Using GDT-RS and RSBR[J], Pattern Recognition Letters, 2003,24(6):887-894.
[17]Visvalingam.M. Visualizationin GIS. Cartography and Vics. Visualiza2tionin Geographical Information System. Edited by HilaryM. Hearnshaw & DavidJ. Urwin,1994,18-25.
[18]江斌、黄波、陆锋.GIS环境下的空间分析和地学视觉化,高等教育出版社,2000年第1版,160.
[19]秦举礼,遥感和多源地学数据图像处理技术及在地质找矿中的应用,四川地质学报,1996.1.
[20]ZHOU ZHI-HUA, Tree Perspectives of Data Mining[J], Artificial Intelligence, 2003,143(1):139-146.
[21]McCormickB. H.DefantiM.D.. BrownM.D. Visualization in Sci2entific Computing. SpecialIssueACMSIGGRAPH Computer Graphics,1987,21(6).
[22]陈述彭、童庆禧、郭华东,遥感信息机理研究,科学出版社,1998,159.
[23]Philbrick.A.K. Towardaunity of carto graphicforms and geographical content, Professional Geographer,1953,5(5):11-15.
[24]查显节、邢立新等,基于空间形态特征的遥感边缘信息提取方法,吉林大学学报(地球科学版),2004.3.
[25]唐泽圣,三维数据场可视化,清华大学出版社,1999.
[26]邢立新、潘军等,Hough变换在线性信息提取中的应用研究,长沙遥感学术会议论文集,2004.
[27]罗森林、王越、周思永,多源信息处理技术——数据融合,系统工程与电子技术,1998.
[28]Ren C luo et al. M ultisenso r Integration and Fusion fo r Intelligent Machines and System s, North Carolina State University, Ables Publishing Corporation, 1995.
[29]刘宴淼、余金生、李纯杰,基于图像处理技术的矿产预测综合分析系统[J],物化探计算技术,1994,16(1)：22-28.
[30]罗可、蔡碧野、胜贤、谢中科,数据挖掘及其发展研究,计算机工程与应用,2002.14.
[31]ChavezPSJr、SidesSC、AndersonJA, Comparison of three differentme thodstomerge multiresolution and multispectral data:TM & SPOT pan[J], Photogrammetric Engineering and RemoteSensing,1991,57(3):295-303.
[32]Corbley K P. Canad applies new processing technology to"old"data in mining exploration project [J], Earth Observation,1994,5:34-36.
[33]Leckie DG.S ynergsim of SAR and visible infrared data for forestty pediscrimination [J], Photogrammetric Engineering and Remote Sensing,1990, 56(9):1237-1246.
[34]江东、王钰、王建华、兰朝利,多源图像信息融合的理论与技术,甘肃科学学报,2002.1.
[35]ZHONG NING、DONG JU-ZHEEN、SETSUO OHSUGA, Mining Data Mining by Cooperatively Using GDT-RS and RSBR[J], Pattern Recognition Letters, 2003,24(6):887-894.
[36]李德仁、程涛,从GIS数据库中发现知识,测绘学报,1995,24(1)：37-43.
[37]龚建华、林珲,虚拟地理环境,高等教育出版社,2002.
[38][加]Jiawei Han Micheline Kamber著,范明、孟小峰译,数据挖掘概念与技术,机械工业出版社,2005年第1版,301-313.
[39][美] George M. Marakas著,敖富江译,数据仓库、挖掘和可视化——核心概念,清华大学出版社,2004,29、93.
[40]陈中祥、岳超源,空间数据挖掘的研究与发展,计算机工程与应用2003.3.
[41]PohlC、 GenderenJLVan, Multisensor image fusionin remote sensing:concepts, methods and applications [J], International Journalof Remote Sensing,1998, 9(5):823-854.
[42][美]Tom Soukup Ian Davidson著,朱建秋、蔡伟杰译,可视化数据挖掘,电子工业出版社,2004年第1版,3-4.
[43]承继成、林晖、周成虎等,数字地球导论,科学出版社,2000年1月第1版.
[44]郁文贤等,多传感器信息融合技术评述,国防科技大学学报,1994.
[45]ANANTHANARAYANA V S、 NARASIMHA MURTY M、 SUBRAMAVIAN D K, Tree Structure for Efficient Data Mining Using Rough Sets[J], Pattern Recognition Letters,2003,24(6):851-862.
[46]陈建军、余志强等,数据可视化技术及其应用[J],红外与激光工程,2001, 30(5)：239-243.
[47]晓梅等,科学计算可视化导论[M],长沙：国防科技大学出版社,1996,1-18.
[48]谢东升、李旭祥,可视化技术及其在环境科学中的应用,新疆环境保护,2004,26(1)：25-29.
[49]DASKALAKIS、KOPANAS I、 COUDARA M, etal.Data Mining for Derision Support on Customer Insolvency in communications Business [J], European Journal of Operational Research,2003,145(2):239-255.
[50]KAOSC、 CHANG H C、LINCH, Decision Support for the Academic Library Acquisition Budget Allocation via Circulation Database Mining[J], Information Processing & Management,2003,39(6):133-147.
[51]李德仁、龚健雅、朱欣焰、梁宜希,我国地球空间数据框架的设计思想与技术路线,武汉测绘科技学报,1998,Vo1.23,No4,297-303.
[52]宫鹏、史培军、浦瑞良等,对地观测技术与地球系统,科学出版社,1996.8.
[53]GIS环境下的空间分析和地学视觉化,汪斌,黄波,陆锋,高等教育出版社,2002.5,P98-99.
[54]李德仁、关泽群,空间信息系统的集成与实现,武汉：武汉测绘科技大学出版社,2003年3月第1版.
[55]陈常松、何建邦,面向GIS数据共享的概念模型设计研究,遥感学报,1999,3(3)：230-235.
[56]崔伟宏,空间数据结构研究,北京：中国科学技术出版社,1995.
[57]陈军,GIS空间数据模型的基本问题和学术前言,地理学报,1995,50(增刊)：24-32.
[58]地理信息系统与管理决策,科技部国家遥感中心,北京大学出版社,2000.4,P57.
[59]空间数据库,Shashi Shekhar, Sanjay Chawla著,谢昆青,马修军,杨冬青等译,机械工业出版社,2004.1,P28、P32.
[60]杜清运,空间信息的结构、表达及其理解机制,武汉测绘科技大学学报,1998,23(4)：388-392.
[61]地理信息系统,汤国安,赵牡丹,科学出版社,2000.10,P32-39、P90-107.
[62][美]Michael Zeiler著,张晓祥、张峰、姚静等译,为我们的世界建模—ESRI地理数据库设计指南,人民邮电出版社,2004年12月第1版.
[63]空间数据发掘与知识发现,邸凯昌,武汉大学出版社,2000.12,P3-4.
[64]地理信息系统基本原理及应用,朱光,李晓燕,戎兵,测绘出版社,1997.6,P30.
[65]周成虎、骆剑承、杨晓梅等,《遥感影像地学理解与分析》,科学出版社,2001.
[66]王今飞,遥感卫星图像中线性地质特征的自动提取,第四纪研究,2000年,20(3),P252-258.
[67]赵英时等,遥感应用分析原理与方法,科学出版社,2003,273-276.
[68]王磊,陈刚,陆忠华.基于云计算的高效科学计算应用软件框架[J].华中科技大学学报(自然科学版).2011.39(1)：166-169,183
[69]李刚健.基于虚拟化技术的云计算平台架构研究[J].吉林建筑工程学院学报.2011.28(1)：79-81
[70]陈维崧,陈庆秋.基于云计算的GIS研究[J].测绘与空间地理信息.2011.34(1)：157-161
[71]李嘉虓,陈华根.基于云计算的地学云系统设计[J].计算机工程与科学.2011.33(6)：108-113
[72]滕菲,路来君,孟庆龙.地学G4I系统的开发研究[J].吉林地质.2006.25(4)50-55
[73]史佩昌,王怀民,蒋杰.面向云计算的网络化平台研究与实现[J].计算机工程与科
[74]韩冰,路来君.地学G4I系统中空间元数据的设计技术[J].世界地质.2011.30(2)：307-312.
[75]王鹏,董静宜.一种云计算框架的实现方法研究[J].计算机工程与科学.2009.31(A1)：11-13.
[76]李玲,付园,麻晓珍,张海蓉.云存储系统中数据冗余策略优化问题[J].吉林大学学报(信息科学版).2013.31(1)：1-7.
[77]陈康,郑纬民.云计算：系统实例与研究现状[J].软件学报.2009.20(5)：1337-1348.