Statistics for Spatial Data.

Preface 1. Spatial concepts and notions 2. Ecological and spatial processes 3. Points, lines and graphs 4. Spatial analysis of complete point location data 5. Contiguous units analysis 6. Spatial analysis of sample data 7. Spatial relationship and multiscale analysis 8. Spatial autocorrelation and inferential tests 9. Spatial partitioning: spatial clusters and boundary detection 10. Spatial diversity analysis 11. Spatio-temporal analysis 12. Closing comments and future directions References Index.

Spatial Analysis A Guide for Ecologists

Remote sensing of soil salinity: potentials and constraints

▪ Abstract Landscape ecology focuses on the reciprocal interactions between spatial pattern and ecological processes, and it is well integrated with ecology. The field has grown rapidly over the past 15 years. The persistent influence of land-use history and natural disturbance on contemporary ecosystems has become apparent. Development of pattern metrics has largely stabilized, and they are widely used to relate landscape pattern to ecological responses. Analyses conducted at multiple scales have demonstrated the importance of landscape pattern for many taxa, and spatially mediated interspecific interactions are receiving increased attention. Disturbance remains prominent in landscape studies, and current research is addressing disturbance interactions. Integration of ecosystem and landscape ecology remains challenging but should enhance understanding of landscape function. Landscape ecology should continue to refine knowledge of when spatial heterogeneity is fundamentally important, rigorously test the ...

/pdf/landscape-ecology-what-is-the-state-of-science-1qj9m9bw8y.pdf

Landscape ecology: what is the state of science?

/pdf/landscape-ecology-what-is-the-state-of-the-science-56vps4fewn.pdf

Landscape ecology: what is the state of the science?

Image destriping is necessary due to sensor-to-sensor variation within instruments. This has most often been done by assuming that each sensor views a statistically similar subimage, and a histogram of each sensor's response is made to match the overall histogram. Histogram matching shows sensitivity to violations of the similarity assumption. An alternative algorithm is suggested which matches the gain and offset of each sensor to typical values, and which is resistant to the effects of outliers. Tests on a sample image show the moment matching algorithm reduces the variance between sensors to a greater degree than histogram matching.

Destriping multisensor imagery with moment matching

Spectral band selection for the characterization of salinity status of soils

Spatial stochastic models play an important role in understanding and predicting the behaviour of complex systems. Such models may be implemented with explicit knowledge of only a limited number of parameters relating to spatial relationships among locations. Consequently, they are often used instead of deterministic-mechanistic models, which may potentially require an unrealistically large number of parameters. Currently, in contrast to spatial stochastic models, the parameterization of the joint spatial distribution of objects in landscape models is more often implicit than explicit. Here, we investigate the similarities and differences between bona fide spatial stochastic models and landscape models by focusing mostly on the relationships between processes, their realizations (patterns), representation and measurement, and their use in exploratory as well as confirmatory data analysis. One of the most important outcomes of recognizing the importance of stochastic processes is the acknowledgement that the spatial pattern observed in a landscape is only one realization of that process. Hence, while ecologists have been using landscape pattern indices (LPIs) to characterize landscape heterogeneity and/or make inferences about processes shaping the landscape, no stochastic modelling framework has been developed for their proper statistical elucidation. Consequently, several (mis)uses of LPIs draw conclusions about landscapes which are suspect. We show that several reports about sensitivities of LPIs to measurements have common roots that can be made explicitly manageable by adopting stochastic models of spatial structure. The key parameters of these stochastic models are composition and configuration, which, in general, cannot be estimated independently from each other. We outline how to develop the stochastic framework to interpret observations and make some recommendations to practitioners about everyday usage. The conceptual linkages between patterns and processes are particularly important in light of recent efforts to bridge the static-structural and the dynamic-analytic traditions of ecology.

On the role of spatial stochastic models in understanding landscape indices in ecology

Spatial patterns of lightning-caused forest fires in Ontario, 1976–1998

Recent developments in remote sensing and geographical information systems make widely available data sets covering large extents with a variety of spatial resolutions, such as digital images and geographic databases, potentially interesting for ecological applications Such regular lattice data consisting of several million observations are now frequently analyzed for mapping, monitoring, and interpreting landscapes from an ecological, pattern-sensitive perspective This requires adaptive data description and interpretation, which usually comes in the form of partitioning the data, for example, by the application of boundary-detection and/or classification and segmentation Such tasks can benefit from utilizing new statistical and image processing tools, including wavelets, because they can characterize global as well as local pattern This paper briefly introduces the wavelet representation and links it with hierarchical spatial data structures (quadtrees) and extensively used statistical techni

Ferenc Csillag

Papers

Destriping multisensor imagery with moment matching

Spectral band selection for the characterization of salinity status of soils

On the role of spatial stochastic models in understanding landscape indices in ecology

Spatial patterns of lightning-caused forest fires in Ontario, 1976–1998

Wavelets, boundaries, and the spatial analysis of landscape pattern