HIGH PERFORMANCE COMPUTING SPONSORED CONTENT
Weathering the storm
Weather and climate simulation can now be accentuated through the use of cloud computing, writes Robert Roe
With heatwaves scorching much of Europe over the past weeks, the importance of accurate weather and climate predictions has been brought sharply into focus. Weather and climate simulation are traditional HPC applications that require vast amounts of computational power, and this makes weather and climate simulation an expensive business as the barrier to entry is a massively powerful supercomputer, in addition to the skills and expertise in software to ensure the users can get the best performance out of their applications. Just last month the US National Oceanic
and Atmospheric Administration (NOAA) inaugurated its newest weather and climate supercomputers with an operational run of the National Blend of Models. The new supercomputers, first announced in February 2020 with a contract award to General Dynamics Information Technology (GDIT), provide a significant upgrade to the computing capacity, storage space and interconnect speed of the nation’s Weather and Climate Operational Supercomputing System. US Secretary of Commerce Gina Raimondo commented: ‘Accurate weather and climate predictions are critical to informing public safety, supporting local economies and addressing the threat of climate change. Through strategic and sustained investments, the US is reclaiming a global top spot in high performance computing to provide more accurate and timely climate forecasts to the public.’ NOAA Administrator Dr Rick Spinrad added: ‘More computing power will enable NOAA to provide the public with more detailed weather forecasts further in advance. Today’s supercomputer implementation is the culmination of years of hard work by incredible teams across
14 Scientific Computing World Summer 2022
NOAA – everyone should be proud of this.’ Enhanced computing and storage
capacity will allow NOAA to deploy higher- resolution models to capture small-scale features like severe thunderstorms, more realistic model physics to capture the formation of clouds and precipitation, and a larger number of individual model simulations to better quantify model certainty. The result is even better forecasts and warnings to support public safety and the national economy. Ken Graham, director of NOAA’s National
Weather Service, stated: ‘Researchers are developing new ensemble-based forecast models at record speed, and now we have the computing power needed to implement many of these substantial advancements to improve weather and climate prediction.’ However, there is now a way to harness
the power of weather and climate simulation without the huge investment in state-of- the-art supercomputers. Cloud providers such as atNorth can deliver large-scale HPC platforms with the latest in processor and GPU technology for any scientists and researchers to use. These resources can be deployed quickly and easily to ensure
“Having a lower price and better performance from a sustainable source is a win-win situation. We love the cost savings as well as the sustainability, and so do our clients”
they get access to the resources they need when they need them and only pay for the resources that are used. This means a cluster can be scaled up for brief periods of high usage and then scaled back when that period of peak usage subsides.
Developing the weather and climate ecosystem It was recently announced that the European Centre for Medium-Range Weather Forecasts (ECMWF) is starting to make some of its Integrated Forecasting System (IFS) available on an open-source basis to facilitate collaboration on the code. This decision aims to bring the weather and climate forecasting community together so they can share their expertise and improve the quality of the models. Some of the code is already available on the internet: a GitHub space has been created to host open-source IFS components. The merits of moving the full IFS forecast model to open source in the future will be reviewed this year, in consultation with ECMWF’s Member States. The main aim of the move is enhanced
collaboration. Removing restrictions on redistribution could make working with ECMWF more attractive to collaborators. Contributing to open-source codes could also be more attractive to academic partners. Another aim is greater efficiency. There
currently is a mix of bespoke licences and open-source material that is time- consuming to handle. Some journals also require open access to the codes used. A third reason is positioning ECMWF and its Member States at the centre of
@scwmagazine |
www.scientific-computing.com
Limbitech/
Shutterstock.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38
