Strategy
Draft ENES Infrastructure Strategy 2024-2033 Open for Comment
We have now published a draft, and are seeking feedback from the community via this google form - by August 17 2023.
There are seven headline recommendations:
- The HPC community must continue to provide both CPU and GPU machines; a lot of climate codes will not be sensibly deployed on GPU machines in the near future (even if they can be made to run on them).
- There is a need for a more operational aspect to some aspects of climate science.
- The community should continue to invest in managing and sustaining shared infrastructure.
- Model development takes a long time and is resource intensive. Modellers will have to pay attention to the choices between Performance, Portability, and (scientific) Productivity; in the new world, we can only have two!
- Large expensive modelling projects need to be treated like satellite missions, well publicised and documented.
- The community should continue to invest in the necessary underpinning diagnostic tools and libraries.
- Storage and data systems need to support a variety of use-cases.
However, there are 37 numbered detailed recommendations, seven of which target the HPC community - the other thirty target the climate modelling community. There ought to be no surprises in this document, but nonetheless, community feedback would be valuable, especially if there are significant things missing, or some things need more emphasis.
The infrastructure strategy for ENES 2012-2022: mid-term update 2017
The second phase of IS-ENES, the IS-ENES2 project, started implementing the ENES infrastructure recommendations and updated the 2012 document (see below) with an analysis of drivers and infrastructure components in the context of 2017. This effort confirms previous recommendations with partial reformulations based on a combination of progress and evolving requirements and provides guidance on scientific evaluation of models and emphasizes the need to organizationally tackle the sustainability challenge.
The 2017 recommendations are:
1. On models: Support common development and sharing of software and accelerate the preparation for exascale computing by exploiting next generation hardware and developing appropriate algorithms, software infrastructures, and workflows.
2. On HPC: Exploit a blend of national and European high-performance facilities to support current and next generation science and work toward obtaining sustained access to world-class resources and next generation architectures.
3. On model data: Evolve towards a sustained data infrastructure providing data that are easily available, well-documented and quality assured, and further invest in research into data standards, workflow, high performance data management and analytics.
4. On physical network: Work to maximize the bandwidth between the major European climate data and compute facilities and ensure that documentation and guidance on tools and local network setup are available to users.
5. On people: Grow the numbers of skilled scientists and software engineers in the ENES community, increase opportunities for training at all levels, and strengthen networking between software engineers.
6. On model evaluation (new): Enhance sharing of common open source diagnostics and model evaluation tools, implement governance procedures, and expand data infrastructure to include computational resources needed for more systematic evaluation of model output.
7. On infrastructure sustainability (new): Sustain the cooperation necessary to develop future model and data technology and support international reference experiments programmes, and strengthen collaboration with other European actors providing services to, or using services from, ENES.
The infrastructure strategy for ENES 2012-2022
In 2012, ENES published its infrastructure strategy (IS-ENES project) for the decade to come to support European climate research for seasonal to centennial climate predictions. This research also provides the scientific basis for climate services.