Autosubmit

Autosubmit is a Python-based workflow manager to create, manage and monitor complex tasks involving different substeps, such as scientific computational experiments.

Institution:

Research Group:

Models and Workflows Team

Researcher/s:

Daniel Beltrán, Bruno de Paula Kinoshita, Luiggi Tenorio Ku, Manuel Giménez de Castro, Erick Doria, Núria Torquet, Suraj Rajesh, Francesca Macchia, Miguel Castrillo, Francisco Javier Doblas Reyes

Description:

Autosubmit gives climate-model developers, national services and digital-twin integrators a “single-button experiment factory”: define, schedule and monitor complex workflows with several interdependent jobs across heterogeneous systems (from HPC to cloud) while preserving full provenance and rapid fault recovery.

Already earmarked to orchestrate workflows for the Destination Earth’s Climate Adaptation Digital Twin (ClimateDT) and the European Digital Twin Ocean, it lets twin builders and operators launch, monitor and recover thousands of coupled-model jobs across multiple supercomputers with full provenance.

Aplication areas:

Digital Twin, Climate, Ocean monitoring

Target market:

Logistics; Energy Companies; Risk Management Service Providers; B2G

Technology Readiness Level (1-9): 9

Protection:

GPL License (Version 3.0)

More information

if you want to know more about this project do not hesitate to contact us