Spatial data analytics on heterogeneous multi- and many-core parallel architectures using python

By:  and 

Links

Abstract

Parallel vector spatial analysis concerns the application of parallel computational methods to facilitate vector-based spatial analysis. The history of parallel computation in spatial analysis is reviewed, and this work is placed into the broader context of high-performance computing (HPC) and parallelization research. The rise of cyber infrastructure and its manifestation in spatial analysis as CyberGIScience is seen as a main driver of renewed interest in parallel computation in the spatial sciences. Key problems in spatial analysis that have been the focus of parallel computing are covered. Chief among these are spatial optimization problems, computational geometric problems including polygonization and spatial contiguity detection, the use of Monte Carlo Markov chain simulation in spatial statistics, and parallel implementations of spatial econometric methods. Future directions for research on parallelization in computational spatial analysis are outlined.

Additional publication details

Publication type Book chapter
Publication Subtype Book Chapter
Title Spatial data analytics on heterogeneous multi- and many-core parallel architectures using python
DOI 10.1007/978-3-319-17885-1_1569
Year Published 2017
Language English
Publisher Springer
Contributing office(s) Astrogeology Science Center
Larger Work Type Book
Larger Work Title Encyclopedia of GIS