SC20 Proceedings

The International Conference for High Performance Computing, Networking, Storage, and Analysis

Orchestration of a Forecasting Chain for Forest Fire Prevention Using the LEXIS Cloud/HPC Platform


Authors: Mohamad Hayek (Leibniz Supercomputing Centre); Laurent Ganne (Atos); Antonio Parodi, Andrea Parodi, and Mirko D’Andrea (CIMA Research Foundation, Italy); Rubén J. García-Hernández and Stephan Hachinger (Leibniz Supercomputing Centre); Martin Golasowski and Kateřina Slaninová (IT4Innovations, Czech Republic); Frédéric Donnat (Outpost24); Emanuele Danovaro (European Centre for Medium-Range Weather Forecasts); Johannes Munke (Leibniz Supercomputing Centre); Alberto Scionti, Giacomo Vitali, and Olivier Terzo (Advanced Computing and Applications LINKS Foundation); and Jan Martinovič (IT4Innovations, Czech Republic)

Abstract: We describe a first successful application of the LEXIS platform for advanced orchestration of complex simulation and data-analysis workflows in mixed cloud/HPC environments. A workflow for forest fire risk assessment based on the models WRF and RISICO was executed, using IaaS cloud resources at LRZ (DE) and national HPC resources at IT4I (CZ). Besides concept and results of the workflow, our contribution focuses on core systems of LEXIS: a distributed data infrastructure using iRODS and EUDAT, and an orchestration system with the novel ability to address HPC schedulers besides IaaS clouds. The approach and open platform, currently federating IT4I, LRZ and ECMWF (UK), are aimed at broad application within the current project (“Large-scale EXecution for Industry and Society”, H2020 GA 825532) and beyond.

Best Poster Finalist (BP): no

Poster: PDF
Poster summary: PDF


Back to Poster Archive Listing