Poster: Accelerating climate models using an AI surrogate

Title

Accelerating climate models using an AI surrogate

About

We accelerate Community Atmospheric Model (CAM) simulations by replacing the moist physics and radiation with an AI surrogate using a novel python-fortran bridge (TorchClim) in the Community Earth System Model (CESM). We show that a deep neural network surrogate trained on data from CAM itself can produce a stable model that reproduces the climate and variability of the original model, albeit with some biases.

Poster

ACCESS_NRI_Prasad.pdf (4.5 MB)

Note: this topic is part of the 2023 ACCESS Community Workshop Poster session

1 Like

Closed to release votes for this year’s posters.