Browsing by Author "Hoban, Susan"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Benchmarking parallel implementations of cloud type clustering from satellite data(UMBC) Barajas, Carlos A.; Mukherjee, Lipi; Guo, Pei; Hoban, Susan; Jin, Daeho; Gangopadhyay, Aryya; Wang, JianwuThe study of clouds, i.e., where they occur and what are their characteristics, plays a key role in the understanding of climate change. The aim of this project is to use machine learning in conjunction with parallel computing techniques to classify cloud types. Experiments with k-means clustering are conducted with two parallelism techniques.Item Benchmarking Parallel K-Means Cloud Type Clustering from Satellite Data(Springer, Cham, 2019-10-08) Barajas, Carlos; Guo, Pei; Mukherjee, Lipi; Hoban, Susan; Wang, Jianwu; Jin, Daeho; Gangopadhyay, Aryya; Gobbert, Matthias K.The study of clouds, i.e., where they occur and what are their characteristics, plays a key role in the understanding of climate change. Clustering is a common machine learning technique used in atmospheric science to classify cloud types. Many parallelism techniques e.g., MPI, OpenMP and Spark, could achieve efficient and scalable clustering of large-scale satellite observation data. In order to understand their differences, this paper studies and compares three different approaches on parallel clustering of satellite observation data. Benchmarking experiments with k-means clustering are conducted with three parallelism techniques, namely OpenMP, OpenMP+MPI, and Spark, on a HPC cluster using up to 16 nodes.Item Framework for scientific communication in Earth and space science(IEEE, 2002-08-06) Burrows, G. Howard; Hoban, Susan; Harberts, Robert; Lal, NandWe propose a framework for scientific communication that focuses on the value of the answers provided by science. The implementation would combine the advantages of flexible index/thesaurus, a comprehensive taxonomy/ontology, and an annotation/discussion environment. Using our experience with the NASA Digital Library Technology program we examine the social and economic issues involved in the acceptance of this new information technology by a community of scientists. We then speculate on opportunities provided for existing publishers within this new model of scientific communication.