Abstract
Accurate digital twinning of the global challenges (GC) leads to computationally expensive coupled simulations. These simulations bring together not only different models, but also various sources of massive static and streaming data sets. In this paper, we explore ways to bridge the gap between traditional high performance computing (HPC) and data-centric computation in order to provide efficient technological solutions for accurate policy-making in the domain of GC. GC simulations in HPC environments give rise to a number of technical challenges related to coupling. Being intended to reflect current and upcoming situation for policy-making, GC simulations extensively use recent streaming data coming from external data sources, which requires changing traditional HPC systems operation. Another common challenge stems from the necessity to couple simulations and exchange data across data centers in GC scenarios. By introducing a generalized GC simulation workflow, this paper shows commonality of the technical challenges for various GC and reflects on the approaches to tackle these technical challenges in the HiDALGO project.
Highlights
In recent years, there has been an increasing interest in evidence-based computeraided approaches to address global challenges (GC)
By introducing a generalized GC simulation workflow, this paper demonstrates a commonality of these technical challenges for various GC and reflects on the approaches to overcome them implemented in the HiDALGO project
While not giving direct access to its high performance computing (HPC) systems, which are closed to external access as it is used to produce time-critical twice-daily global weather forecasts, European Centre for Medium-Range Weather Forecasts (ECMWF) provides the migration and Urban Air Pollution (UAP) case studies with the forecast model’s output, as well as climate, atmospheric, and hydrological data via the cloud, which necessitates coupling across data centers
Summary
This research is driven by three representative case studies: human migration from conflict zones, air pollution levels in the cities, and the spread of malicious information in social media (such as Twitter and telecommunications networks) When it comes to coupling of models and data sources for GC simulations in HPC environments, one faces a number of technical challenges, not common for traditional engineering and science applications for HPC. HPC system’s operation must be revised in order to allow highly complex simulation, but at the same time, provide the necessary flexibility to incorporate influx data Another common challenge stems from the necessity to couple simulations and exchange data across data centers in GC simulation scenarios. This demand is introduced by various reasons including endeavor to reuse time-consuming simulation results in multiple use cases, inability to share massive amounts of data, issues related to licensing the data or simulation software available at different data centers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
