TY  - CONF
AU  - Erlingsson, Ernir
AU  - Cavallaro, Gabriele
AU  - Neukirchen, Helmut
AU  - Riedel, Morris
TI  - Scalable Workflows for Remote Sensing Data Processing with the Deep-Est Modular Supercomputing Architecture
PB  - IEEE
M1  - FZJ-2019-06503
SP  - 5905-5908
PY  - 2019
AB  - The implementation of efficient remote sensing workflows isessential to improve the access to and analysis of the vastamount of sensed data and to provide decision-makers withclear, timely, and useful information. The Dynamical Exascale Entry Platform (DEEP) is an European pre-exascaleplatform that incorporates heterogeneous High-PerformanceComputing (HPC) systems, i.e., hardware modules which include specialised accelerators. This paper demonstrates thepotential of such diverse modules for the deployment of remote sensing data workflows that include diverse processing tasks. Particular focus is put on pipelines which can usethe Network Attached Memory (NAM), which is a novel supercomputer module that allows near processing and/or fastshared storage of big remote sensing datasets.
T2  - IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium
CY  - 28 Jul 2019 - 2 Aug 2019, Yokohama (Japan)
Y2  - 28 Jul 2019 - 2 Aug 2019
M2  - Yokohama, Japan
LB  - PUB:(DE-HGF)8
UR  - <Go to ISI:>//WOS:000519270605170
DO  - DOI:10.1109/IGARSS.2019.8898487
UR  - https://juser.fz-juelich.de/record/867901
ER  -