Nvidia to build AI supercomputer to predict climate change
In order to develop the best strategies for mitigation and adaptation of climate change, says the company, climate models are needed that can predict the climate in different regions of the globe over decades.
“To make our future a reality today, simulation is the answer,” says Jensen Huang, CEO of Nvidia.
Unlike predicting the weather, which primarily models atmospheric physics, climate models are multidecade simulations that model the physics, chemistry and biology of the atmosphere, waters, ice, land and human activities. Climate simulations are configured today at 10- to 100-kilometer resolutions.
But, says the company, greater resolution is needed to model changes in the global water cycle – water movement from the ocean, sea ice, land surface and groundwater through the atmosphere and clouds. Changes in this system can lead to intensifying storms and droughts.
Meter-scale resolution is needed to simulate clouds that reflect sunlight back to space, says the company. Scientists estimate that these resolutions will demand millions to billions of times more computing power than what’s currently available. It would take decades to achieve that through the ordinary course of computing advances, which accelerate 10x every five years.
“For the first time,” says Huang, “we have the technology to do ultra-high-resolution climate modeling, to jump to lightspeed and predict changes in regional extreme weather decades out.”
According to the company, million-x speedups can be achieved by combining three technologies:
- GPU-accelerated computing
- Deep learning and breakthroughs in physics-informed neural networks
- AI supercomputers, along with vast quantities of observed and model data to learn from
“And with super-resolution techniques,” says Huang, “we may have within our grasp the billion-x leap needed to do ultra-high-resolution climate modeling. Countries, cities and towns can get early warnings to adapt and make infrastructures more resilient. And with more accurate predictions, people and nations will act with more urgency.”
As a result, says the company, it will dedicate itself and its significant resources to build the world’s most powerful AI supercomputer dedicated to predicting climate change, to join with the world’s climate science community. Named Earth-2, or E-2, the system would create a digital twin of Earth in Omniverse, the company’s extensible, open platform built for virtual collaboration and real-time physically accurate simulation.
The system would be the climate change counterpart to Cambridge-1, the world’s most powerful AI supercomputer for healthcare research. The company unveiled Cambridge-1 earlier this year and says it’s being used by a number of leading healthcare companies.
“All the technologies we’ve invented up to this moment are needed to make Earth-2 possible,” says Huang. “I can’t imagine a greater or more important use.”
Related articles:
Supercomputers, AI to assist in building digital twin of Earth
Nvidia unveils CPU for giant-scale AI and HPC
Microsoft announces new supercomputer, large-scale AI vision
IBM, DOE unveil ‘world’s fastest’ AI supercomputer
Thermal infrared satellites to tackle climate change from space
