{"id":3055,"date":"2023-06-28T16:33:09","date_gmt":"2023-06-28T16:33:09","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2023\/06\/28\/wholl-stop-the-rain-scientists-call-for-climate-collaboration\/"},"modified":"2023-06-28T16:33:09","modified_gmt":"2023-06-28T16:33:09","slug":"wholl-stop-the-rain-scientists-call-for-climate-collaboration","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2023\/06\/28\/wholl-stop-the-rain-scientists-call-for-climate-collaboration\/","title":{"rendered":"Who\u2019ll Stop the Rain? Scientists Call for Climate Collaboration"},"content":{"rendered":"
\n

A trio of top scientists is helping lead one of the most ambitious efforts in the history of computing \u2014 building a digital twin<\/a> of Earth.<\/p>\n

Peter Bauer, Bjorn Stevens and Francisco \u201cPaco\u201d Doblas-Reyes agree that a digital twin of Earth needs to support resolutions down to a kilometer so a growing set of users can explore the risks of climate change and how to adapt to them. They say the work will require accelerated computing<\/a>, AI and lots of collaboration.<\/p>\n

Their Herculean efforts, some already using NVIDIA technologies, inspired Earth-2<\/a>, NVIDIA\u2019s contribution to the common cause.<\/p>\n

\u201cWe will dedicate ourselves and our significant resources to direct NVIDIA\u2019s scale and expertise in computational sciences, to join with the world\u2019s climate science community,\u201d Jensen Huang, founder and CEO of NVIDIA, had said when he announced the Earth-2 initiative in late 2021.<\/p>\n

Collaborating on an Unprecedented Scale<\/b><\/h2>\n

Huang\u2019s commitment signaled support for efforts like Destination Earth<\/a> (DestinE<\/a>), a pan-European project to create digital twins of the planet.<\/p>\n

\u201cNo single computer may be enough to do it, so it needs a distributed, international effort,\u201d said Bauer, a veteran with more than 20 years at Europe\u2019s top weather forecasting center who now leads the project that aims to make planet-scale models available by 2030.<\/p>\n

Last year, he co-authored a Nature<\/i> article<\/a> that said the work \u201crequires collaboration on an unprecedented scale.\u201d<\/p>\n

<\/p>\n

\"Chart<\/p>\n

<\/a>

Bauer calls for broad international cooperation on a new Earth information system.<\/figcaption><\/figure>\n

In a March GTC talk<\/a>, Bauer envisioned a federation that \u201cmobilizes resources from many countries, including private players, and NVIDIA could be one that would be very interesting.\u201d<\/p>\n

\"Pix<\/a>
Peter Bauer<\/figcaption><\/figure>\n

Such resources would enable the enormous work of developing new numeric and machine-learning models, then running them in massive inference jobs to make predictions that stretch across multiple decades.<\/p>\n

DestinE has its roots in a 2008 climate conference. It\u2019s the fruit of a number of programs, including many Bauer led in his years with the European Centre for Medium-Range Weather Forecasts<\/a> \u2014 based in Reading, England \u2014 which develops some of the most advanced weather forecast models in the world.<\/p>\n

Consuming a Petabyte a Day<\/b><\/h2>\n

The collaboration is broad because the computing requirements are massive.<\/p>\n

\"Pix<\/a>
Francisco Doblas-Reyes<\/figcaption><\/figure>\n

\u201cWe\u2019re talking about producing petabytes of data a day that have to be delivered very quickly,\u201d said Doblas-Reyes, director of the Earth sciences department at the Barcelona Supercomputing Center, a lead author at Intergovernmental Panel on Climate Change<\/a> \u2014 a group that creates some of the most definitive reports on climate change<\/a> \u2014 and a contributor to the DestinE program.<\/p>\n

The digital twin effort will turn the traditional approach to weather and climate forecasting \u201cupside down so users can be the drivers of the process,\u201d he said in a March talk at GTC<\/a>, NVIDIA\u2019s developer conference. The goal is to \u201cput the user at the helm of producing climate information that\u2019s more useful for climate adaptation,\u201d he said.<\/p>\n

His talk described the new models, workflows and systems needed to capture in detail the chaotic nature of climate systems.<\/p>\n

Articulating the Vision<\/b><\/h2>\n

The vision for a digital twin crystalized in a keynote<\/a> at the SC20 supercomputing conference from Stevens, a director at the Max Planck Institute for Meteorology<\/a>, in Hamburg. He leads work on one of the world\u2019s top weather models for climate applications, as well as an effort<\/a> to enable simulations at kilometer-level resolution, an order of magnitude finer than today\u2019s best work.<\/p>\n

\u201cWe need a new type of computing capability \u2026 for planetary information systems that let us work through the consequences of our actions and policies, so we can build a more sustainable future,\u201d he said.<\/p>\n

\"Bjorn<\/a>
Stevens\u2019 landmark talk at SC20 crystallized the vision of a digital twin of Earth.<\/figcaption><\/figure>\n

Stevens described a digital twin that\u2019s accurate and interactive. For example, he imagined people querying it to see how a warming climate could affect flooding in northern Europe or food security in Africa.<\/p>\n

AI Enables Interactive Simulations<\/b><\/h2>\n

AI will play a lead role in giving users that level of interactivity, he said in a talk<\/a> at GTC last year.<\/p>\n

\u201cWe need AI to get to where we need to be,\u201d he said, giving shout-outs to NVIDIA and colleagues, including Bauer and Doblas-Reyes. \u201cReal steps forward come from people bringing their different perspectives together and rethinking how we work.\u201d<\/p>\n

\"Chart<\/a>
Climate simulations pursue ultra-high resolution for greater accuracy.<\/figcaption><\/figure>\n

Doblas-Reyes agreed in his GTC talk this year.<\/p>\n

\u201cIn my opinion, AI is a necessary complement for the digital twin \u2014 it\u2019s the only way to offer true interactivity to users and help provide a good trajectory of what\u2019s to come in our climate,\u201d he said.<\/p>\n

On a Journey Together<\/b><\/h2>\n

All three scientists gave examples of how NVIDIA technologies have been used in a wide variety of projects addressing climate change.<\/p>\n

In his GTC talk, Stevens took a characteristically playful turn. He showed a cartoon version of Huang, like Isaac Newton, struck with a falling apple and an insight for how to engage with the scientific effort.<\/p>\n

\u201cWe need you Jensen, and you need us,\u201d Stevens said.<\/p>\n

\"Slide<\/a>
Stevens playfully portrayed Huang as Isaac Newton in his GTC talk.<\/figcaption><\/figure>\n

The MareNostrum 5 system coming to the Barcelona center provides one example. It\u2019s expected to accelerate some of the DestinE work on NVIDIA H100 Tensor Core GPUs<\/a>.<\/p>\n

Building a digital twin of Earth is \u201can exciting opportunity to re-think the future of HPC with AI on top,\u201d said Mike Pritchard, a veteran climate scientist who directs climate research at NVIDIA.<\/p>\n

NVIDIA Omniverse<\/a> for connecting 3D tools and developing metaverse applications, NVIDIA Modulus<\/a> for physics-informed machine learning and NVIDIA Triton<\/a> for AI inference all have roles to play in the broad effort, he said.<\/p>\n

It\u2019s a long and evolving collaboration, Bauer said in his GTC talk. \u201cI sent my first email to NVIDIA on these issues 14 years ago, and NVIDIA has been with us on this journey ever since.\u201d<\/p>\n

To learn more, read the concept paper<\/a> developed for the Berlin Summit for Earth Virtualization Engines<\/a>, July 3-7, where Huang will deliver a keynote address.<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

https:\/\/blogs.nvidia.com\/blog\/2023\/06\/28\/digital-twins-climate-collaboration\/<\/p>\n","protected":false},"author":0,"featured_media":3056,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/3055"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=3055"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/3055\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/3056"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=3055"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=3055"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=3055"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}