Performance of NDVI Index on HPC Resources
Keywords:
GRASS GIS, High Performance Computing, Remote Sensing, NDVIAbstract
Geographic information systems (GIS) [1] are crucial to enable the gathering, analysis, presentation and distribution of spatial and non-spatial data. In some specific GIS applications, such as time-critical simulations or data mining, we need to deal with massive amount of geospatial data storage, retrieval, and processing. The main aim of this article is to analyze and benchmark the performance of Normalized Difference Vegetation Index (NDVI) [2] of satellite images (16 GB [3]) using highperformance computational (HPC) resources, as the developers need to solve the problem of both data and task distribution among serial or parallel environments. The geographical resources analysis support system (GRASS) [4] is used as the main instrument for the study.
References
Geographic information systems as an Integrating Technology: Context, Concepts and Definitions. Kenneth E. Foote and Margaret Lynch.
NDVI index http://gis-lab.info/qa/ndvi.html
Database of Landsat satellite images http://glcfapp.glcf.umd.edu:8080/esdi/
Neteler, M. and Mitasova, H., Open Source GiS: A GRASS GIS Approach. Second Edition, 2003. Kluwer Academic Publishers.
GRASS GIS 7.0.svn Reference Manual http://grass.osgeo.org/grass70/manuals/full_index.html
GRASS GIS official website http://grass.osgeo.org/
The Message Passing Interface (MPI) standard: http://www-unix.mcs.anl.gov/mpi/
Parallel GRASS jobs http://grasswiki.osgeo.org/wiki/Parallel_GRASS_jobs
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
