Abstract
Accessing Parallel Computing Resources from ArcGIS 10.0
Track: Analysis
Authors: Kyle Schutt, Peter Sforza, Nicholas Polys
Analysis of large GIS data sets with complex computations can cause even the most powerful desktop computers to process jobs inefficiently and ineffectively. For instance, calculating Solar Radiation in an ArcGIS environment with large digital elevation models is resource intensive. In order to address this bottleneck, we have employed high-performance computing (HPC) resources utilizing parallel MATLAB to perform parallel calculations and developed an ArcGIS Add-In that manages the communication between the HPC cluster and ArcGIS. The graphical user-interface presents the user with the ability to select an HPC cluster, various computations, and fine-grained tuning options for computation parameters. We found that by employing HPC clusters for large and complex computations, we were able to analyze large data sets for which ArcGIS would fail to complete. Our work shows that we are able to access HPC clusters from an ArcGIS interface that facilitates the transition to parallel computations for GIS technicians.