Leveraging the Omniverse to Help Understand Climate Change
Cambrian-AI analyst Alberto Romero contributed to this article.
One of the greatest challenges facing humanity today is climate change. Although climate change occurs naturally, over the past 200 years human activities have directly influenced otherwise normal climate cycles in a very specific way: we are heating the planet. Scientists cannot give policy makers enough warning of the disaster we will face in the decades to come unless we act effectively and with extreme urgency.
NVIDIA CEO Jensen Huang hinted at this issue in his Keynote 2022 GTC. He mentioned that scientists believe we will need X billion computing power to “effectively simulate regional climate change.” NVIDIA has developed three core technologies – GPU-accelerated computations, physics-informed AI models, and AI supercomputers – which together can grant a million times acceleration. Today, the company has embarked on a journey to tackle a crucial goal for climate science: closing the gap with that billion-X we need to adopt strategies for climate change and climate change. effective adaptation and save our planet from its impending future.
NVIDIA’s full-stack approach is key: physics-informed, GPU-accelerated AI models at data center scale are our best chance of fulfilling the EU mandate to achieve climate neutral by 2050. How do they plan to do this? With a digital twin of our planet. They will build the most powerful AI supercomputer designed for climate science: Earth-2. It will be a physically accurate, high-fidelity, ultra-high resolution replica of the Earth working continuously to predict climate and weather events on a regional and global scale.
In a Q&A with analysts, Jensen Huang said Earth-2 will “constantly recalibrate itself to Earth…constantly refining its models…constantly making future predictions.” And that’s exactly what makes Earth’s digital twin uniquely suited to meet the challenge. Unlike traditional simulations, a digital twin is constantly synchronized with its real-world counterpart through detailed measurements. It’s also extremely fast. As David Matthew Hall, Senior Data Scientist at NVIDIA, puts it, Earth-2 can deliver “actionable insights in actionable time.”
“Economists, biologists, scientists, companies from countries around the world will be able to… simulate whether the dams they are building in Venice will make a difference. Simulate… what will happen to the Mekong River in Southeast Asia. Simulate… what will change the weather conditions in California,” Huang said. “Earth-2 will literally be Earth-two.”
There are two essential technological pillars to build Earth-2: Modulus and Omniverse, NVIDIA’s simulation engine. The virtual worlds people build in the Omniverse obey the laws of physics, can operate at scale, and are shareable, allowing simultaneous collaboration for scientists around the world. Omniverse enables visualization and interactive exploration, but scientists also need an AI model to simulate and predict Earth’s climate and weather.
That’s what the module is for. It is a framework for developing physical-ML neural network models trained with terabytes of data. Such a model can then become the substitute for digital twins. Modulus uses the Neural Fourier Operator framework to provide AI models with the ability to understand physics, laying the foundation for predicting climate variations and atmospheric events quickly and accurately.
The simulation and visualization power of the Omniverse, combined with the precision of physics-based AI models developed by Modulus, as well as data center-scale GPU-accelerated computing, makes NVIDIA exceptionally well placed to solve the problem of forecasting normal and extreme weather conditions. and climate events at ultra-high resolution – both regionally and globally.
In a first step towards Earth-2, NVIDIA unveiled a digital weather forecasting twin: FourCastNet. It is a GPU-accelerated Physics-ML model trained on 10TB of Earth-truth data to predict problematic atmospheric events such as hurricanes and atmospheric rivers. It is the first deep learning model that outperforms state-of-the-art numerical models (specifically, the ECMWF Integrated Prediction System) in accuracy and speed, up to 5 orders of magnitude faster . In Huang’s words, “what takes a year for a typical numerical simulation now takes minutes.”
This is just the beginning for Earth-2. NVIDIA is committed to helping the scientific community – and, by extension, all of humanity – solve one of the most important and potentially existential challenges of our time. And just so that you put into perspective why so much effort is needed to solve climate change – and why we shouldn’t treat it like any other problem – I’ll end by repeating the words Jensen Huang wrote in 2021 about Earth-2: “All the technologies we have invented so far are needed to make Earth-2 possible. I can’t imagine a bigger or bigger use.
Disclosures: This article expresses the opinions of the author and should not be considered advice on buying or investing in the companies mentioned. Our company, Cambrian AI Research, is fortunate to have many, if not most, semiconductor companies as customers, including Blaize, Cerebras, Esperanto, Graphcore, IBM, Intel, NVIDIA, Qualcomm Technologies, Synopsys, and Tenstorrent. We have no investment position in any of the companies mentioned in this article and do not plan to initiate any in the near future. For more information, please visit our website at https://cambrian-AI.com.