About my research
The Weather Research and Forecasting (WRF) Model is a next-generation mesocale numerical weather prediction system designed to serve both operational forecasting and atmospheric research needs. It features multiple dynamical cores, a 3-dimensional variational (3DVAR) data assimilation system, and a software architecture allowing for computational parallelism and system extensibility. WRF is suitable for a broad spectrum of applications across scales ranging from meters to thousands of kilometers. For more information on the model visit http://www.wrf-model.org
The current project objective is to find a point during the benchmarking of WRF where the speed up vs. the number of nodes on a GRID will achieve its highest performance. A point that after adding an x amount of nodes the maximum performance is obtained and if one more node is added to the system, the performance starts to decrease or stops improving. WRF is being translated into a parallel environment to keep up with the amount of data that the system will receive in future years, the increase on resolution for weather prediction requires more computing power and the most viable solution at the moment is High Performance Computing through a Grid environment. For more information on the research team please visit http://www.latinamericangrid.org
This is a project conducted by Florida International University, School of Computer Science. This specific research topic is under the supervision of Dr. Masoud Sadjadi
This project is founded by National Science Foundation and IBM.
Current papers, technical reports, posters and publications:
Application performance proļ¬ling and prediction in grid environment. In the 19th Annual Argonne Symposium for Undergraduates in Science, Engineering and Mathematics, Argonne National Lab, IL, November 2008 [.bib]
Shortcut Generator Based on Commonly Used Functions. IP.com Technical Publication Library. IBM publication. To be published by the end of 2008.
A Modeling Approach for Estimating Execution Time of Long-Running Scientific Applications. Fifth High-Performance Grid Computing Workshop (HPGC) in conjunction with International Parallel and Distributed Processing Symposium. (IPDPS) [ http ]. Miami, Florida, USA, April 2008 [.pdf ]
Transparent Grid Enablement of Weather Research and Forecasting. Mardi Gras Conference 2008 – workshop on Grid-Enabling Applications. [ http ] Louisiana State University, USA, January 2008. [.pdf ]
Transparent grid enablement of WRF using a profiling, code inspection, and modeling approach. In the poster presentation session of the 5th Latin American Grid (LA Grid) Summit, The IBM T.J. Watson Research Center, NY, U.S.A., September 2007. [.pdf ]
The Latin American Grid (LA Grid) Weather Research and Forecast (WRF) Portal. In the poster presentation session of the 5th Latin American Grid (LA Grid) Summit, The IBM T.J. Watson Research Center, NY, U.S.A., September 2007.[ .pdf ]
Finding an appropriate profiler for the weather research and forecasting code. Technical Report FIU-SCIS-2007-09-03, School of Computing and Information Sciences, Florida International University, 11200 SW 8th St., Miami, FL 33199, August 2007.[ .pdf ]
Weather research and forecasting model 2.2 documentation: A step-by-step guide of a model run. Technical Report FIU-SCIS-2007-09-02, School of Computing and Information Sciences, Florida International University, 11200 SW 8th St., Miami, FL 33199, August 2007.[ .pdf ]