This paper explores data-driven methods for quantifying and incorporating spatio-temporal contextual information in the
mapping of land cover change. In remote sensing, area classes of land cover are typically mapped via statistical
manipulation of feature-space measurement, e.g., reflectance data, and other ancillary data. Contextual information has
been known to have the potential of increasing the accuracy of land cover classification and change detection, on the
ground that land cover often exhibits spatial and temporal correlations and, as such, should be properly accommodated.
In Bayesian methods, a priori probabilities of class occurrences can be considered as contextual information, which are
combined with class-conditional probability densities to arrive at discriminant decisions with minimized
misclassification. These prior probabilities may be made to vary locally to honor variability in the strengths of spatial
dependence in class occurrences. For deriving local prior joint probabilities in land cover co-occurrences over time, a
modified Expectation and Maximization (EM) algorithm was developed, in which a local window size can be adjusted in
the light of spatial dependences inferred from class probability densities computed from spectral data. Empirical studies
were performed using bi-temporal Landsat TM image subsets in Wuhan, which confirmed the comparative benefits of
incorporating localized prior probabilities in land cover change detection.
The term conflation is used as a superset of all kinds of integral approaches to combining heterogeneous geospatial data,
aiming for synergism in geospatial information processes, thus added values in resultant information products. A
coherent strategy for conflation is built upon an evaluation of spatial data models, which include discrete objects that are
geo-referenced by position and associated with some qualitative and/or quantitative attributes, and fields that are
continuous or discrete in terms of the scale of measurement. Regardless of whether positional errors or errors in fields
are concerned, they can be conceived of as being realizations of regionalized random variables. Therefore, multivariate
geostatistics provides a straightforward framework for conflation of spatial data. Scale is an important metric in spatial
data, which can be handled in co-kriging procedures by incorporating block-support variograms derived from point-support
variograms, functioning as either downscaling or upscaling depending on the interaction between the existing
data and the information or analysis required. The methods for scale-dependent manipulation and cross-scale integration
of multi-source data will be described, followed by some discussions.