共查询到20条相似文献，搜索用时 31 毫秒
1.
Giles M. Foody 《International journal of geographical information science》2013,27(5):527-542
Abstract Remote sensing is an important source of land cover data required by many GIS users. Land cover data are typically derived from remotely–sensed data through the application of a conventional statistical classification. Such classification techniques are not, however, always appropriate, particularly as they may make untenable assumptions about the data and their output is hard, comprising only the code of the most likely class of membership. Whilst some deviation from the assumptions may be tolerated and a fuzzy output may be derived, making more information on class membership properties available, alternative classification procedures are sometimes required. Artificial neural networks are an attractive alternative to the statistical classifiers and here one is used to derive a fuzzy classification output from a remotely–sensed data set that may be post–processed with ancillary data available in a GIS to increase the accuracy with which land cover may be mapped. With the aid ancillary information on soil type and prior knowledge of class occurrence the accuracy of an artificial neural network classification was increased by 29–93 to 77–37 per cent. An artificial neural network can therefore be used generate a fuzzy classification output that may be used with other data sets in a GIS, which may not have been available to the producer of the classification, to increase the accuracy with which land cover may be classified. 相似文献
2.
珠江三角洲都市经济区地域构成的判别与分析 总被引：7，自引：1，他引：6
随着经济全球化和城市化进程的加快, 单个城市的竞争逐渐转变为城市区域的竞争。 都市经济区是在国家战略需求的推动下应势而生的新概念, 已经广泛应用于全国国土规划和 主体功能区划。准确把握都市经济区内部的地域构成有助于进行有效地加强区域管理和空间调控。以往的相关研究主要集中于宏观分析或以区县为单元的空间分析, 从功能空间的角度对都市经济区内部地域构成的研究较少, 更缺少准确科学的划分和判读方法。为了准确把握 区域空间利用中的主要问题和潜在威胁, 规划者和政府官员需要探索判定都市经济区地域构成的新方法。文章在总结当前几种主要的地域类型判读方法优缺点的基础上, 深入探讨了运 用遥感和GIS 手段进行区域地域构成判别的思路, 并成功应用于珠江三角洲内部地域构成的 空间分析。研究发现, 当前珠江三角洲都市经济区正经历着大规模的城镇化, 大都市的发展 无序蔓延, 存在的用地粗放、结构混杂、功能有待优化等问题, 工业区、居住区等用地的空 间分布呈现较明显的向心型分布和交通导向型分布特征, 同种地域类型的集聚性分布明显增强。通过从单要素和整体特征上认识和把握珠江三角洲地域构成与空间组织特征, 可以有的放矢地进行空间管理和调控。还有助于深化区域地域构成的认识和空间结构的监测和分析, 也可作为制定土地利用政策的依据, 为从区域尺度上制定空间政策提供了新的参考依据。 相似文献
3.
基于RS和GIS的人口估计方法研究综述 总被引：13，自引：0，他引：13
随着RS和GIS技术的迅速发展, RS和GIS成为进行人口估计的主要手段。根据人口估计的目标和使用的数据源不同,可以把基于RS和GIS的人口估计方法分成两大类：面插值方法和统计模型方法。面插值方法根据插值过程中是否使用辅助数据可以进一步分成无辅助数据的面插值和有辅助数据的面插值两种。统计模型方法根据模型中自变量的不同可以分成建成区面积估计法、土地利用密度法、居住单元估计法、图像像元特征估计法和自然和社会经济特征综合估计法五种。本文按照上述分类标准综述了基于RS和GIS的各种人口估计方法,分析了各种方法的应用条件、优缺点和研究实例。最后提出了在基于RS和GIS进行人口估计方面需要进一步研究的问题。 相似文献
4.
Hichem Omrani Fahed Abdallah Omar Charif Nicholas T. Longford 《International journal of geographical information science》2013,27(6):1023-1041
During the last two decades, a variety of models have been applied to understand and predict changes in land use. These models assign a single-attribute label to each spatial unit at any particular time of the simulation. This is not realistic because mixed use of land is quite common. A more detailed classification allowing the modelling of mixed land use would be desirable for better understanding and interpreting the evolution of the use of land. A possible solution is the multi-label (ML) concept where each spatial unit can belong to multiple classes simultaneously. For example, a cluster of summer houses at a lake in a forested area should be classified as water, forest and residential (built-up). The ML concept was introduced recently, and it belongs to the machine learning field. In this article, the ML concept is introduced and applied in land-use modelling. As a novelty, we present a land-use change model that allows ML class assignment using the k nearest neighbour (kNN) method that derives a functional relationship between land use and a set of explanatory variables. A case study with a rich data-set from Luxembourg using biophysical data from aerial photography is described. The model achieves promising results based on the well-known ML evaluation criteria. The application described in this article highlights the value of the multi-label k nearest neighbour method (MLkNN) for land-use modelling. 相似文献
5.
6.
深圳市地形对土地利用动态的影响 总被引：5，自引：0，他引：5
基于RS和GIS的技术支持,以深圳市为案例,利用多时段土地利用数据和地形数据,分析土地利用变化的时空分异,研究城市地域地形对土地利用动态的影响。分析表明,土地利用在空间上的变化引起其垂直重心的变化,耕地重心降低,林地和建设用地重心上升。深圳市地形对土地利用动态有明显的制约作用,主要表现为:随着高程和坡度的升高,土地利用动态度大致呈降低趋势。随着城市化的加深,同一高程带和坡度带上土地利用动态度呈加大趋势。土地利用动态度的情景分析指出,在自然景观时期、农业景观成熟期和后城市化时期,土地利用在高程带和坡度带上都比较稳定,动态度低;在这三个时期之间是农业化时期和快速城市化时期,土地利用动态度高。 相似文献
7.
Abstract Limitations of the current land records systems in Belize, Central America, led leaders of the Ministry of Natural Resources to initiate this feasibility study for a computer-aided land information system (LIS). Land records in Belize have been based on the British Torrens land tenure system, which maintains five sets of records along with informative maps. One paper file is maintained for each title application and records are continually circulated between seven locations throughout the country, resulting in up to 3 years to complete the process of title registration. A LIS will permit quick access to land records and eliminate most of the current problems, and will merge with a geographic information system being developed for Belize. 相似文献
8.
Small-area estimation of land cover statistics by post-stratification of a national area frame survey 总被引：1，自引：0，他引：1
The objective of this paper is to examine a method for estimation of land cover statistics for local environments from available area frame surveys of larger, surrounding areas. The method is a simple version of the small-area estimation methodology. The starting point is a national area frame survey of land cover. This survey is post-stratified using a coarse land cover map based on topographic maps and segmentation of satellite images. The approach is to describe the land cover composition of each stratum and subsequently use the results to calculate land cover statistics for a smaller area where the relative distribution of the strata is known. The method was applied to a mountain environment in Gausdal in Eastern Norway and the result was compared to reference data from a complete in situ land cover map of the study area. The overall correlation (Pearson’s rho) between the observed and the estimated land cover figures was r = 0.95. The method does not produce a map of the target area and the estimation error was large for a few of the land cover classes. The overall conclusion is, however, that the method is applicable when the objective is to produce land cover statistics and the interest is the general composition of land cover classes - not the precise estimate of each class. The method will be applied in outfield pasture management in Norway, where it offers a cost-efficient way to screen the management units and identify local areas with a land cover composition suitable for grazing. The limited resources available for in situ land cover mapping can then be allocated efficiently to in-depth studies of the areas with the highest grazing potential. It is also expected that the method can be used to compile land cover statistics for other purposes as well, provided that the motivation is to describe the overall land cover composition and not to provide exact estimates for the individual land cover classes. 相似文献
9.
《The Journal of geography》2012,111(2):95-101
Abstract Models conceptualize structures and relationships. Their design and construction in high schools and junior colleges provide an excellent focus for group activities, and also a mechanism to generate new levels of awareness and understanding of current social issues. The particular method discussed by the authors effects spatial transformations to a demographic base by block accretion. Four illustrations are given ranging from macro- to micro-scale transformation: a continent (Africa), country (Thailand), a U.S. state (Michigan), and a city (Detroit S.M.A.). In each case a chorographic base map is set side-by-side with a demographic base map: one showing territorial or areal reality, the other the quantum reality of population. On these paired maps the distribution of socio-economic and other phenomena can be examined. 相似文献
10.
Abstract This paper examines the use of land and property information systems by local authorities in England and Wales. A number of important lessons for the future are discussed. There is much evidence which suggests that the primary use of land and property information systems is to support administrative tasks. This is an important conclusion when it is borne in mind that, in early days of discussions on the design of land and property information systems, it was envisaged that most of the output from such systems would be for management 相似文献
11.
AKE SIVERTUN LORIN E. REINELT REINHOLD CASTENSSON 《International journal of geographical information science》2013,27(4):365-378
Abstract The use of remote sensing techniques, image processing, computer mapping and overlays to make inventories of land use and to improve land and water management has increasing potential. Advantages of these techniques include greater geometric resolution and potential time and money savings. The increasing capabilities of personal computers and workstations (hardware and software) and the greater availability of databases have simplified the application of these techniques. In this application, a geographical information system (GIS) was used to facilitate the identification of critical non-point source areas of pollution by sediment-related nutrients. This critical source area information might then be used to aid in the development of non-point source control strategies or for monitoring programme design. This study shows the potential of using GIS in selecting critical source areas for sediment-related water quality problems and land resource protection. 相似文献
12.
STEPHEN PRICE 《International journal of geographical information science》2013,27(3):233-243
Abstract This paper considers the use of a modern programming language (Modula-2) to develop a data model for a lot-based land information system. The emphasis is on the importance of maintaining the history of the lots, and a data model is developed which incorporates the history of each lot. 相似文献
13.
基于神经网络的元胞自动机及模拟复杂土地利用系统 总被引：57，自引：9，他引：57
本文提出了基于神经网络的元胞自动机(CellularAutomata),并将其用来模拟复杂的土地利用系统及其演变。国际上已经有许多利用元胞自动机进行城市模拟的研究,但这些模型往往局限于模拟从非城市用地到城市用地的转变。模拟多种土地利用的动态系统比一般模拟城市演化要复杂得多,需要使用许多空间变量和参数,而确定模型的参数值和模型结构有很大困难。本文通过神经网络、元胞自动机和GIS相结合来进行土地利用的动态模拟,并利用多时相的遥感分类图像来训练神经网络,能十分方便地确定模型参数和模型结构,消除常规模拟方法所带来的弊端。 相似文献
14.
Martin A. Andresen Nick Malleson Wouter Steenbeek Michael Townsley Christophe Vandeviver 《International journal of geographical information science》2020,34(7):1306-1322
ABSTRACT The analysis of geographically referenced data, specifically point data, is predicated on the accurate geocoding of those data. Geocoding refers to the process in which geographically referenced data (addresses, for example) are placed on a map. This process may lead to issues with positional accuracy or the inability to geocode an address. In this paper, we conduct an international investigation into the impact of the (in)ability to geocode an address on the resulting spatial pattern. We use a variety of point data sets of crime events (varying numbers of events and types of crime), a variety of areal units of analysis (varying the number and size of areal units), from a variety of countries (varying underlying administrative systems), and a locally-based spatial point pattern test to find the levels of geocoding match rates to maintain the spatial patterns of the original data when addresses are missing at random. We find that the level of geocoding success depends on the number of points and the number of areal units under analysis, but generally show that the necessary levels of geocoding success are lower than found in previous research. This finding is consistent across different national contexts. 相似文献
15.
基于景观生态学和马尔可夫模型的日本北九州土地利用分析 总被引：6，自引：0，他引：6
Based on four phases of TM images acquired in 1990, 1995, 2000 and 2005, this paper took Kitakyushu in Japan as a case study to analyze spatial change of land use landscape and corresponding effects on environmental issues guided by landscape ecology theory in virtue of combining technology of Remote Sensing with GIS. Firstly, land use types were divided into 6 classes （farmland, mountain, forestland, water body, urban land and unused land） according to national classification standard of land use, comprehensible ability of TM image and purpose of this study. Secondly, following the theory of landscape ecology analysis, 11 typical landscape indices were abstracted to evaluate the environmental effects and spatial feature changes of land use. Research results indicated that land use has grown more and more diversified and unbalanced, human activities have disturbed the landscape more seriously. Finally, transfer matrix of Markov was applied to forecast change process of land use in the future different periods, and then potential land use changes were also simulated from 2010 to 2050. Results showed that conversion tendency for all types of land use in Kitakyushu into urban construction land were enhanced. The study was anticipated to help local authorities better understand and address a complex land use system, and develop improved land use management strategies that could better balance urban expansion and ecological conservation. 相似文献
16.
北京城市蔓延的测度与分析 总被引：5，自引：2，他引：3
Concerning about the rapid urban growth in recent China, this study takes Beijing as a case and puts forward that urban sprawl can be measured from spatial configuration, urban growth efficiency and external impacts, and then develops a geo-spatial indices system for measuring sprawl, a total of 13 indicators. In order to calculate these indices, different sources data are selected, including land use maps, former land use planning, land price and floor-area-ratio samples, digitized map of the highways and city centers, population and GDP statistical data, etc. Various GIS spatial analysis methods are used to spatialize these indices into 100m×100m cells. Besides, an integrated urban sprawl index is calculated by weight sum of these 13 indices. The application result indicates that geo-spatial indices system can capture most of the typical features and interior differentia of urban sprawl. Construction land in Beijing has kept fast growing with large amount, low efficiency and disordered spatial configuration, indicating a typical sprawling tendency. The following specific sprawl features are identified by each indicator: (1) typical spatial configuration of sprawling: obvious fragmentation and irregularity of landscape due to unsuccessful enforcement of land use planning, unadvisable pattern of typical discontinuous development, strip development and leapfrog development; (2) low efficiency of sprawl: low development density, low population density and economic output in newly developed area; and (3) negative impacts on agriculture, environment and city life. According to the integrated sprawl index, the sprawling amount in the northern part is larger than that in the southern, but the sprawling extent is in converse case; most sprawling area include the marginal area of the near suburbs and the area between highways, etc. Four sprawling patterns are identified: randomly expansion at urban fringe, strip development along or between highways, scattered development of industrial land, leapfrog development of urban residence and industrial area. 相似文献
17.
《The Journal of geography》2012,111(6):558-569
Abstract This report addresses the question of groundwater quality in a context of economic development and heterogeneous land use. Seven wells, each actively producing for the public water supply, and together providing 37 percent of the total aquifer production of four municipios, were tested in three topographic basins. Major land use categories, including agriculture, urbanization, and industry, were identified throughout the basins. Well samples were drawn three times during a six-month period and analyzed for a set of 15 water quality parameters including biological indicators. The most common pollutants detected were heavy metals, nitrate, arsenic, and semivolatile organic compounds. Wells surrounded by agricultural and commercial activities were contaminated by nitrate, mercury, lead, and phthalates. Wells in mixed residential and industrial settings had concentrations of semivolatile organic compounds and lead. The presence of noxious chemicals in the public water supply, even in relatively small amounts, threatens the viability of the groundwater reservoir. Both operational and policy aspects of water quality should be discussed in the context of urban and economic development. 相似文献
18.
19.
Philip M. Watson Richard A. Wadsworth 《International journal of geographical information science》2013,27(4):425-440
Abstract A primary goal of the NERC/ESRC Land Use Programme (NELUP) was to design and build a decision support system (DSS) to model rural land use and its change due to environmental and agricultural policy. The effects of policies are measured in terms of economic, ecological and hydrological parameters, with land use and land cover being the uniting factors. The DSS incorporates access to a large database and a suite of complex models. The DSS is user-friendly, produces meaningful graphics, and is almost entirely mouse-driven. This paper describes the NELUP view of policy making and DSS, the NELUP database and the DSS models and interface philosophy and design. The results of workshops, conducted with potential users of the DSS, are discussed and summarised. 相似文献
20.
MICHAEL F. GOODCHILD SUN GUOQING YANG SHIREN 《International journal of geographical information science》2013,27(2):87-103
Abstract An error model for spatial databases is defined here as a stochastic process capable of generating a population of distorted versions of the same pattern of geographical variation. The differences between members of the population represent the uncertainties present in raw or interpreted data, or introduced during processing. Defined in this way, an error model can provide estimates of the uncertainty associated with the products of processing in geographical information systems. A new error model is defined in this paper for categorical data. Its application to soil and land cover maps is discussed in two examples: the measurement of area and the measurement of overlay. Specific details of implementation and use are reviewed. The model provides a powerful basis for visualizing error in area class maps, and for measuring the effects of its propagation through processes of geographical information systems. 相似文献