Stough, T; Braverman, A; Cressie, N; Kang, E; Michalak, A M.; and Nguyen, H, Visualizing massive spatial datasets using multi-resolution global grids, National Institute for Applied Statistics Research Australia, University of Wollongong, Working Paper 05-14, 2014, 24.
In this chapter, visualization is used to evaluate the performance of global-scale computational algorithms. We generate synthetic global data sets and input them into computational algorithms that have a visualization capability. The global visualization allows us to quickly and easily compare the output of the computational algorithm to the synthetic-data input. Visualization is key here because the algorithms we are evaluating must respect the spatial structure of the input. We modify, augment, and integrate four existing component technologies: statistical conditional simulation, Discrete Global Grids, array set addressing, and Google Earth, where the internal representation of the synthetic data to be visualized is mirrored by the structure of the statistical model used to generate it. Both are spatially nested, so that one can move up and down in resolution in a mutually consistent way. We provide an example of how our simulation-visualization system may be used, by evaluating a computational algorithm called Spatial Statistical Data Fusion that was developed for use on massive, remote sensing data sets.