Showing papers on "Spatial analysis published in 1997"

STING: A Statistical Information Grid Approach to Spatial Data Mining

Abstract: Spatial data mining, i.e., discovery of interesting characteristics and patterns that may implicitly exist in spatial databases, is a challenging task due to the huge amounts of spatial data and to the new conceptual nature of the problems which must account for spatial distance. Clustering and region oriented queries are common problems in this domain. Several approaches have been presented in recent years, all of which require at least one scan of all individual objects (points). Consequently, the computational complexity is at least linearly proportional to the number of objects to answer each query. In this paper, we propose a hierarchical statistical information grid based approach for spatial data mining to reduce the cost further. The idea is to capture statistical information associated with spatial cells in such a manner that whole classes of queries and clustering problems can be answered without recourse to the individual objects. In theory, and confirmed by empirical studies, this approach outperforms the best previous method by at least an order of magnitude, especially when the data set is very large.

Scale in remote sensing and GIS

Abstract: Introduction: Scale, Multiscaling, Remote Sensing, and GIS, M.F. Goodchild and D.A. Quattrochi Multiscale Nature of Spatial Data in Scaling Up Environmental Models, L. Bian Scale Dependence of NDVI and its Relationship to Mountainous Terrain, S.J. Walsh, A. Moody, T.R. Allen, and D.G. Brown Understanding the Scale and Resolution Effects in Remote Sensing and GIS, C.-Y. Cao and N. S.-N. Lam Multiresolution Covariation among Landsat and AVHRR Vegetation Indices, L. De Cola Multiscaling Analysis in Distributed Modeling and Remote Sensing: An Application Using Soil Moisture, R. Dubayah, E.F. Wood, and D. Lavallee Examining the Effects of Sensor Resolution and Sub-Pixel Heterogeneity on Spectral Vegetation Indices: Implications for Biophysical Modeling, M.A. Friedl Multiscale Vegetation Data for the Mountains of Southern California: Spatial and Categorical Resolution, J. Franklin and C.E. Woodcock The Use of Remotely Sensed Surface Temperatures from an Aircraft-Based Thermal Infrared Multispectral Scanner (TIMS) to Estimate the Spatial and Temporal Variability of Latent Heat Fluxes and Thermal Response Numbers from a White Pine (Pinus strobus L.) Plantation, J.C. Luvall Scaling Predicted Pine Forest Hydrology and Productivity across the Southern United States, S.G. McNulty, J.M. Vose, and W.T. Swank Modeling Effects of Spatial Pattern, Drought, and Grazing on Rates of Rangeland Degradation: A Combined Markov and Cellular Automaton Approach, H. Li and J.F. Reynolds Scaling Land Cover Heterogeneity for Global Atmosphere-Biosphere Models, R.S. DeFries, J.R. Townshend, and S.O. Los Quadtrees: Hierarchical Multiresolution Data Structures for Analysis of Digital Images, F. Csillag Statistical Models for Multiple Scaled Analysis, D.E. Myers Image Characterization and Modeling System (ICAMS): A Geographic Information System for the Characterization and Modeling of Multiscale Remote Sensing Data, D.A. Quattrochi, N. S.-N. Lam, H.-L. Qiu, and W. Zhao Approaches to Scaling of Geo-Spatial Data, Z.-G. Xia and K.C. Clarke Multifractals and Remotely Sensed Data: Generalized Scale Invariance, Geographical Information Systems and Resolution Dependence, S. Pecknold, S. Lovejoy, D. Schertzer, and C. Hooge Index

Using the Spatial Configuration of the Data to Improve Estimation

Abstract: Using the well-known Harrison and Rubinfeld (1978) hedonic pricing data, this manuscript demonstrates the substantial benefits obtained by modeling the spatial dependence of the errors. Specifically, the estimated errors on the spatial autoregression fell by 44% relative to OLS. The spatial autoregression corrects predicted values by a nonparametric estimate of the error on nearby observations and thus mimics the behavior of appraisers. The spatial autoregression, by formally incorporating the areal configuration of the data to increase predictive accuracy and estimation efficiency, has great potential in real estate empirical work.

Continental scale variability in ecosystem processes: models, data, and the role of disturbance

Abstract: Management of ecosystems at large regional or continental scales and de- termination of the vulnerability of ecosystems to large-scale changes in climate or atmo- spheric chemistry require understanding how ecosystem processes are governed at large spatial scales. A collaborative project, the Vegetation and Ecosystem Modeling and Analysis Project (VEMAP), addressed modeling of multiple resource limitation at the scale of the conterminous United States, and the responses of ecosystems to environmental change. In this paper, we evaluate the model-generated patterns of spatial variability within and be- tween ecosystems using Century, TEM, and Biome-BGC, and the relationships between modeled water balance, nutrients, and carbon dynamics. We present evaluations of models against mapped and site-specific data. In this analysis, we compare model-generated patterns of variability in net primary productivity (NPP) and soil organic carbon (SOC) to, respec- tively, a satellite proxy and mapped SOC from the VEMAP soils database (derived from USDA-NRCS (Natural Resources Conservation Service) information) and also compare modeled results to site-specific data from forests and grasslands. The VEMAP models simulated spatial variability in ecosystem processes in substantially different ways, reflect- ing the models' differing implementations of multiple resource limitation of NPP. The models had substantially higher correlations across vegetation types compared to within vegetation types. All three models showed correlation among water use, nitrogen avail- ability, and primary production, indicating that water and nutrient limitations of NPP were equilibrated with each other at steady state. This model result may explain a number of seemingly contradictory observations and provides a series of testable predictions. The VEMAP ecosystem models were implicitly or explicitly sensitive to disturbance in their simulation of NPP and carbon storage. Knowledge of the effects of disturbance (human and natural) and spatial data describing disturbance regimes are needed for spatial modeling of ecosystems. Improved consideration of disturbance is a key ''next step'' for spatial ecosystem models.

GeoMiner: a system prototype for spatial data mining

Abstract: Spatial data mining is to mine high-level spatial information and knowledge from large spatial databases. A spatial data mining system prototype, GeoMiner, has been designed and developed based on our years of experience in the research and development of relational data mining system, DBMiner, and our research into spatial data mining. The data mining power of GeoMiner includes mining three kinds of rules: characteristic rules, comparison rules, and association rules, in geo-spatial databases, with a planned extension to include mining classification rules and clustering rules. The SAND (Spatial And Nonspatial Data) architecture is applied in the modeling of spatial databases, whereas GeoMiner includes the spatial data cube construction module, spatial on-line analytical processing (OLAP) module, and spatial data mining modules. A spatial data mining language, GMQL (Geo-Mining Query Language), is designed and implemented as an extension to Spatial SQL [3], for spatial data mining. Moreover, an interactive, user-friendly data mining interface is constructed and tools are implemented for visualization of discovered spatial knowledge.

Map dynamics: integrating cellular automata and GIS through Geo-Algebra

Abstract: In this paper the modelling formalism of cellular automata (CA) is generalized and extended within Geo-Algebra, a mathematical generalization of map algebra capable of expressing a variety of dynamic spatial models and spatial data manipulations within a common framework. Map dynamics, that is, the integration of the spatial dynamics reflected in CA and the spatial data handling capabilities of map algebra, constitutes a critical element within a wider project which sets out to formulate a general framework for simultaneously supporting spatial database manipulations and static and dynamic modelling within GIS. Map dynamics can also allow the modelling of additional dynamic behaviours and phenomena such as adaptation, design, learning and gaming not currently expressible as GIS models.

Spatial relations, minimum bounding rectangles, and spatial data structures

Abstract: Spatial relations are important in numerous domains, such as Spatial Query Languages, Image and Multimedia Databases, Reasoning and Geographic Applications. This paper is concerned with the retrieval of topological and direction relations using spatial data structures based on Minimum Bounding Rectangles. We describe topological and direction relations between region objects and we study the spatial information that Minimum Bounding Rectangles convey about the actual objects they enclose. Then we apply the results in R-trees and their variations, R-trees and R*-trees, in order to minimize the number of disk accesses for queries involving topological and direction relations. We also investigate queries that express complex conditions in the form of disjunctions and conjunctions, and discuss possible extensions.

A Generalized Linear Model Approach to Spatial Data Analysis and Prediction

Abstract: The theory of generalized linear models and quasi-likelihood provides a flexible framework for analyzing non-normal data. In this article, we demonstrate how this theory can be extended to include the analysis of discrete and categorical spatial data. This theory can be used to estimate parameters and test treatment effects in a designed experiment involving discrete or categorical spatial responses. It also provides a flexible method for spatial prediction using non-normal data and includes universal kriging and indicator kriging as special cases. Examples are given, including one where the focus is on comparing treatments in a designed experiment in which spatial correlation is present, and two others where spatial prediction or mapping is the desired goal. The methods presented here provide an additional set of tools for the analysis of spatial data that will be useful to researchers in a variety of disciplines, including hydrology, soil science, entomology, agronomy, and ecology.

Quantifying Spatial Heterogeneity in Streams

Abstract: Although theoretical and empirical studies show that spatial heterogeneity has important effects on the dynamics of populations and the structure of communities, there has been little rigorous quantification of terms like ''patchiness'' or ''spatial heterogeneity'' in studies of lotic systems. In order to compare the spatial heterogeneity of different systems and understand the causes and consequences of that heterogeneity, we must first be able to quantitatively measure it. Spatial heterogeneity has many aspects that change with the scale of our observations, so we need a battery of descriptive measures that explicitly consider the scale-dependence of ecological pattern Response variables exhibiting similar frequency distributions (i.e., similar overall variability) can have very different spatial distributions; consequently, descriptions of spatial heterogeneity require spatial data, i.e., data related to geographic locations (maps). We review statistical techniques for quantitatively describing aspects of heterogeneity in spatial data, emphasizing the decomposition of heterogeneity into different scales of variation (trends, overall variability and spatial dependence or autocorrelation). Gradients in spatial data can be evaluated using trend analyses (e.g., regressions), whereas the spatial structure of variation around trends can be evaluated using geostatistical methods. The central concept of geostatistics is spatial dependence, which is the degree to which values of a response variable differ as a function of the distance (lag) between sampling locations. Semivariograms plot variation among samples separated by a common lag Versus lag, and can be objectively decomposed by piece-wise regression techniques to estimate the strength and scales of spatial dependence. A variety of other methods can be used to quantify spatial heterogeneity from categorical and numerical maps depending on the question of interest and the underlying structure of the spatial data (e.g., methods derived from fractal geometry and information theory, nearest neighbor analysis, spectral analysis, Mantel's test). Spatial heterogeneity in stream organisms is driven by local variation in environmental conditions, by interactions between individuals of the same or different species, and by the effects of organisms on their abiotic environment. By applying geostatistical methods to spatial data collected from field experiments, stream ecologists can evaluate the effects of biotic and abiotic factors on the spatial arrangement of organisms in streams. We present examples of data obtained from experiments examining how consumers affect, and respond to, spatial heterogeneity in their resources. The results indicate that consumer-resource feedbacks should be considered when modeling the causes and consequences of spatial heterogeneity in streams.

Exploring spatial analysis in geographic information systems

Abstract: Introduction to spatial analysis spatial data quantification of spatial analysis single layer operations multiple layer operations point pattern analysis network analysis spatial modelling surface analysis grid analysis decision making in spatial analysis.

Size separation spatial join

Abstract: We introduce a new algorithm to compute the spatial join of two or more spatial data sets, when indexes are not available on them. Size Separation Spatial Join (S3J) imposes a hierarchical decomposition of the data space and, in contrast with previous approaches, requires no replication of entities from the input data sets. Thus its execution time depends only on the sizes of the joined data sets.We describe S3J and present an analytical evaluation of its I/O and processor requirements comparing them with those of previously proposed algorithms for the same problem. We show that S3J has relatively simple cost estimation formulas that can be exploited by a query optimizer. S3J can be efficiently implemented using software already present in many relational systems. In addition, we introduce Dynamic Spatial Bitmaps (DSB), a new technique that enables S3J to dynamically or statically exploit bitmap query processing techniques.Finally, we present experimental results for a prototype implementation of S3J involving real and synthetic data sets for a variety of data distributions. Our experimental results are consistent with our analytical observations and demonstrate the performance benefits of S3J over alternative approaches that have been proposed recently.

Towards a holistic exploration strategy: Using Geographic Information Systems as a tool to enhance exploration

Abstract: The exploration and mining process, from grass‐roots exploration to mine‐site development is a multidisciplinary task and involves the collection, integration and analysis of datasets from many different sources. Geographic Information Systems (GIS) have been used to coordinate and manage the large amounts of spatial and related non‐spatial data associated with modern exploration programs. Once suitably captured in a GIS, these spatial data can be queried, analysed, and by the application of various techniques, maps that depict mineralisation potential or prospectivity, can be defined. Methodologies for the construction of prospectivity maps can be split into two complementary types: empirical and conceptual. Empirical methodologies analyse for spatial relationships between known deposits and surrounding features. Identified spatial relationships are quantified and ultimately integrated into a single map which highlights areas similar to those known to contain significant mineralisation. Conceptual method...

Regression Analysis of Spatial Data

Abstract: Practitioners of regional science often are engaged in statistical analysis of regional data samples collected with reference to points in space. Examples are cross-sectional observations on county-level income, employment or payroll, cross-sectional observations from a group of neighboring states in a region, and firm-level employment or payroll where we know the firm address or an approximate location based on a postal code. Ignoring the spatial configuration of sample observations in regression analysis has been found to produce residuals that vary systematically over space, a phenomenon known as spatial autocorrelation. This paper illustrates how to incorporate spatial information in regression relationships that exhibit spatial auto-correlation. I argue that a simple contiguity matrix provides a unified approach that works with cross-sectional continuous linear relationships, as well as with binary and censored dependent variable problems and autoregressive time series relationships.

Surveillance systems for monitoring the development of spatial patterns

Abstract: Statistical methods concerned with the identification of temporal patterns may be classified into those that examine retrospectively a set of observations, and those that constitute surveillance systems that monitor changes as new observations become available. A similar distinction applies to the identification of geographical patterns in spatial data. There has been a notable lack of attention given to the surveillance of spatial pattern. This paper concerns development of a cumulative sum statistic and procedure for the monitoring of spatial pattern, and its application to both simulated data and to data on Burkitt's lymphoma in Uganda.

Spatial Cognition: Geographic Environments

Abstract: 1: Geography and Cognitive Science. 1.1. Introduction. 1.2. Cognitive Processing. 1.3. Conclusions. 2: A Connectionist Approach to Spatial Cognition. 2.1. Introduction. 2.2. Memory Hardware. 2.3. Map Reading. 2.4. Analyzers. 2.5. Types of Memory. 2.6. Episodic Analyzer. 2.7. Action System. 2.8. Interacting Systems. 2.9. Fuzzy Cognitive Maps. 2.10. Interactive Activation Competition Models. 2.11. Interaction Activation Competition Model as Cognitive Map. 2.12. Conclusions. 3: Cognitive Maps. 3.1. Introduction. 3.2. Encoding Processes. 3.3. Conclusions. 4: Storing Spatial Information in Memory. 4.1. Introduction. 4.2. Object Files. 4.3. Mental Models. 4.4. Conclusions. 5: Spatial Search Processes. 5.1. Introduction. 5.2. Cognitive Theories of Search. 5.3. Geographic Applications. 5.4. Conclusions. 6: Learning Geographic Information. 6.1. Introduction. 6.2. Learning Categories. 6.3. Climate Categories. 6.4. Learning Higher-Order Categories. 6.5. The Organization of Geographic Information. 6.6. Conclusions. 7: Spatial Prototypes. 7.1. Introduction. 7.2. Category Prototypes. 7.3. Using Prototypes. 7.4. When is What Where? 7.5. Conclusions. 8: Similarity. 8.1. Introduction. 8.2. Comparing Maps. 8.3. Theoretical Similarity of Maps. 8.4. Conclusions. 9: Neural Network Applications. 9.1. Introduction. 9.2. Types of Problems. 9.3. The Gravity Model. 9.4. Residential Integration. 9.5. Acquiring Spatial Information. 9.6. Pattern Recognition. 9.7. Conclusions. 10: Conclusions. 10.1. Introduction. 10.2. Summary of Ideas. References. Index.

Gene dispersal and spatial genetic structure.

Abstract: Spatial autocorrelation statistics have been studied in theoretical population genetic models and widely used in experimental studies of spatial structure in many plant and animal populations. However, the statistical properties of spatial autocorrelation statistics have remained uncharacterized. Little is known about how values of spatial autocorrelation statistics in population samples depend on the level of dispersal and scheme of sampling. In this paper, we characterize the statistical properties of join-count spatial autocorrelation statistics for population genetic surveys under various conditions of dispersal and sampling. The results indicate generally high statistical power. These results can provide a method to estimate gene dispersal based on standing spatial patterns of genetic variation observed within populations.

A contiguity-enhanced k-means clustering algorithm for unsupervised multispectral image segmentation

Abstract: The recent and continuing construction of multi- and hyper-spectral imagers will provide detailed data cubes with information in both the spatial and spectral domain. This data shows great promise for remote sensing applications ranging from environmental and agricultural to national security interest. The reduction of this voluminous data to useful intermediate forms is necessary both for downlinking all those bits and for interpreting them. Smart on-board hardware is required, as well as sophisticated earth-bound processing. A segmented image is one kind of intermediate form which provides some measure of data compression. Traditional image segmentation algorithms treat pixels independently and cluster the pixels according only to their spectral information. This neglects the implicit spatial information that is available in the image. We will suggest a simple approach - a variant of the standard k-means algorithm - which uses both spatial and spectral properties of the image. The segmented image has the property that pixels which are spatially continuous are more likely to be in the same class than are random pairs of pixels. This property naturally comes at some cost in terms o of the compactness of the clusters in the spectral domain,but we have found that the spatial contiguity and spectral compactness properties are nearly 'orthogonal', which means that we can make considerable improvements in the one with minimal loss in the other.© (1997) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

A Taxonomy of Spatial Data Integrity Constraints

Abstract: Spatial data quality has become an issue of increasing concern to researchers and practitioners in the field of Spatial Information Systems (SIS). Clearly the results of any spatial analysis are only as good as the data on which it is based. There are a number of significant areas for data quality research in SIS. These include topological consistency; consistency between spatial and attribute data; and consistency between spatial objects’ representation and their true representation on the ground. The last category may be subdivided into spatial accuracy and attribute accuracy. One approach to improving data quality is the imposition of constraints upon data entered into the database. This paper presents a taxonomy of integrity constraints as they apply to spatial database systems. Taking a cross disciplinary approach it aims to clarify some of the terms used in the database and SIS fields for data integrity management. An overview of spatial data quality concerns is given and each type of constraint is assessed regarding its approach to addressing these concerns. Some indication of an implementation method is also given for each.

Using Hierarchical Spatial Data Structures for Hierarchical Spatial Reasoning

Abstract: This paper gives a definition of Hierarchical Spatial Reasoning; which computes increasingly better results in a hierarchical fashion and stops the computation when a result is achieved which is ‘good enough’. This is different from standard hierarchical algorithms, which use hierarchical data structures to improve efficiency in computing the correct result. An algorithm on hierarchical spatial data structure explores all details where such exist. An hierarchical reasoning algorithm stops processing if additional detail does not effectively contribute to the result and is thus more efficient.

Spatial information theory : a theoretical basis for GIS : International Conference COSIT '97, Laurel Highlands, Pennsylvania, USA, October 15-18, 1997 : proceedings

Abstract: Continuous change in spatial regions- Qualitative representation of change- Image-schemata-based spatial inferences: The container-surface algebra- A city metaphor to support navigation in complex information spaces- Using hierarchical spatial data structures for hierarchical spatial reasoning- Structuring space with image schemata: Wayfinding in airports as a case study- Fiat and bona fide Boundaries: Towards an ontology of spatially extended objects- A representation-oriented taxonomy of gradation- Classification as an impediment to the reliable and valid use of spatial information: A disaggregate approach- What maps mean to people: Denotation, connotation, and geographic visualization in land-use debates- The algebraic structure of sets of regions- Complex regions in topological queries- A cognitive assessment of topological spatial relations: Results from an empirical investigation- Voronoi diagrams on line segments: Measurements for contextual generalization purposes- A qualitative coordinate language of location of figures within the ground- Identification of fuzzy objects from field observation data- Long-term spatial representations from pictorial and textual input- Feature accumulation and route structuring in distance estimations - An interdisciplinary approach- The perception and cognition of environmental distance: Direct sources of information- Improving multi-purpose GIS design: Participative design- Self-organization, cities, cognitive maps and information systems- Cognitive requirements on making and interpreting maps- From knowledge to words to wayfinding: Issues in the production and comprehension of route directions- Spatial representation for pragmatic navigation- Partition and conquer- Supporting emergence in spatial reasoning with shape algebras and formal logic- Linear constraints: Geometric objects represented by inequalitiesl- An event-based approach to spatial information- Geocognostics - A new framework for spatial information theory- Graphical modelling for geographic explanation- Experiments using context and significance to enhance the reporting capabilities of gis- Automatic summarization of radiographic imagery- An automated system for name placement which complies with cartographic quality criteria: The hydrographic network- Agent-based simulations of a city dynamics in a gis environment- A logical approach to incorporating qualitative spatial reasoning into GIS (Extended Abstract)- User interaction in a sketch-based GIS user interface- Metrical refinement of topological relations- Approximation of topological relations between fuzzy regions satisfying a linguistically described query

Algorithmic Foundations of Geographic Information Systems

Abstract: to geometric computing: From algorithms to software.- Voronoi methods in GIS.- Digital elevation models and TIN algorithms.- Visualization of TINs.- Generalization of spatial data: Principles and selected algorithms.- Spatial data structures: Concepts and design choices.- Space filling curves versus random walks.- External-memory algorithms with applications in GIS.- Precision and robustness in geometric computations.

Geographic information systems, spatial network analysis, and contraceptive choice

Abstract: How does family planning accessibility affect contraceptive choice? In this paper we use techniques of spatial analysis to develop measures of family planning accessibility, and evaluate the effects of these geographically derived measures in a multilevel statistical model of temporary method choice in Nang Rong, Thailand. In our analyses we combine spatial data obtained from maps and Global Positioning System (GPS) readings with sociodemographic data from surveys and administrative records. The new measures reveal (1) important travel time effects even when family planning outlets are close by; (2) independent effects of road composition; (3) the relevance of alternative sources of family planning supply; and (4) the importance of the local history of program placement.

Representing Space in Language and Perception

Abstract: Space can be understood through perception and language, but are the processes that represent spatial information the same in both cases? This paper reviews psychological evidence for the functional equivalence of spatial representations based on perceptual and linguistic inputs. It is proposed that spatial information is processed by a specialised spatial representation system (SRS) that creates geometric representations of space. The SRS receives inputs from perceptual and linguistic systems and uses these basic inputs to construct mental spatial models of the observed or described environment. A mental spatial model is created by determining the coordinate locations of objects in the egocentric or allocentric frame of reference. The goal of the SRS is not to represent strictly what is perceived, but to model an environment that has an inherent three-dimensional spatial structure.