Project description

The Pilot Lab Exascale Earth System Modelling (PL-ExaESM) is a “Helmholtz-Inkubator Information & Data Science” project and explores specific concepts to enable exascale readiness of Earth System models and associated work flows in Earth System science. PL-ExaESM provides a new platform for scientists of the Helmholtz Association to develop scientific and technological concepts for future generation Earth System models and data analysis systems. Even though extreme events can lead to disruptive changes in society and the environment, current generation models have limited skills particularly with respect to the simulation of these events. Reliable quantification of extreme events requires models with unprecedentedly high resolution and timely analysis of huge volumes of observational and simulation data, which drastically increase the demand on computing power as well as data storage and analysis capacities. At the same time, the unprecedented complexity and heterogeneity of exascale systems, will require new software paradigms for next generation Earth System models as well as fundamentally new concepts for the integration of models and data. Specifically, novel solutions for the parallelisation and scheduling of model components, the handling and staging of huge data volumes and a seamless integration of information management strategies throughout the entire process-value chain from global Earth System simulations to local scale impact models will be developed in PL-ExaESM. The potential of machine learning to optimize these tasks will be investigated. At the end of the project, several program libraries and workflows will be available, which provide the basis for the development of next generation Earth System models.

Main objectives

  • to develop new software paradigms to overcome the limited scalability (i.e. limitation in using a large number of compute cores) of existing ESM software on HPC platforms
  • to increase the flexibility and portability of ESM software and workflows without compromising computational efficiency
  • to explore novel concepts for improving the transport of huge amounts of information on hierarchical and federated storage systems
  • to better understand the computational and data demands of future ESM codes for optimizing the design of exascale HPC architectures
  • to explore the use of machine learning to optimize or replace numerically expensive parameterisations in Earth System model components

Project structure

The PL-ExaESM focuses on five specific topics, which address strategic, structural, methodological, as well as technical aspects to be solved.

Sustained effort - Joint Lab ExaESM

The Joint Lab ExaESM consolidates and continues the developments of the Pilot Lab ExaESM. The next-generation earth system models will run at resolutions of 1-3 km, which means that around 200 numerical equations must be solved in each of about 100 billion model grid boxes at each model time step (i.e. every minute). With such simulations local scale phenomena can be accurately reproduced and extreme events will be simulated much more accurately than at present. Furthermore, the way we run Earth system models will change: the actual simulations will be combined with online analyses of observations, visualisation tools, and novel deep learning concepts to generate new knowledge for society and to provide data for further analysis in user-friendly open web services. Due to the monitoring of the runtime behaviour of Earth system models, important information will be gained how future supercomputer systems can be further optimized to further increase computational speed while saving on energy consumption.

The work of the Joint Lab ExaESM focusses on the application of the tools, which are developed in the Pilot Lab ExaESM, on complete earth system models. The first exascale applications come into existence.