Accelerating Carbon Capture and Storage With Fourier Neural Operator and NVIDIA Modulus

Опубликовано 3 июля 2023, 12:53

Carbon storage, which involves injecting CO2 deep into the earth, is a proven method of reducing how much of this greenhouse gas is released into our atmosphere.

To keep the global temperature rise to under 2 degrees Celsius, by 2030, we need to increase CO2 storage to 1,000 megatons per year.

Accelerating simulations by 700,000X using FNO, NVIDIA Modulus and AI help engineers quickly select the best geographical locations, determine the optimal depth and spacing of wells, and select the optimal injection rate and pressure for the CO2. And with NVIDIA Omniverse, they can visualize and optimize the full inspection process.

This helps ensure safe operation and long-term storage, reducing the amount of carbon dioxide released into our atmosphere.

Collaboration between Stanford, Caltech and NVIDIA.

Paper: Real-time high-resolution CO2 geological storage prediction using nested Fourier neural operators, Energy & Environmental Science 16, no. 4 (2023): 1732-1741.
Link:
pubs.rsc.org/en/content/articl...

#The-Berlin-Summit-For-EVE