# Poster: Accelerating climate models using an AI surrogate **URL:** \ **Category:** Posters\ **Tags:** python, machine-learning, atmosphere, prediction\ **Created:** [4 September 2023 11:36 UTC](https://forum.access-hive.org.au/t/poster-accelerating-climate-models-using-an-ai-surrogate/1260 "2023-09-04T11:36:53Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![abhnil](https://avatars.discourse-cdn.com/v4/letter/a/67e7ee/32.png) [@abhnil](https://forum.access-hive.org.au/u/abhnil)\ **Post date:** [4 September 2023 11:36 UTC](https://forum.access-hive.org.au/t/poster-accelerating-climate-models-using-an-ai-surrogate/1260/1 "2023-09-04T11:36:53Z")
## 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](https://forum.access-hive.org.au/uploads/short-url/rkqJPiBSFtsIcf60Jc21wlUuduS.pdf) (4.5 MB) ![ACCESS_NRI_Prasad](https://us1.discourse-cdn.com/flex020/uploads/access1/original/2X/d/dc35c91935ad500709ac255c696290cc4c6e2075.jpeg) **Note:** this topic is part of the [2023 ACCESS Community Workshop](https://forum.access-hive.org.au/c/access-workshop-2023/61) Poster session ---
**Author:** ![lachlanswhyborn](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/lachlanswhyborn/32/1837_2.png) [@lachlanswhyborn](https://forum.access-hive.org.au/u/lachlanswhyborn)\ **Post date:** [30 August 2024 05:38 UTC](https://forum.access-hive.org.au/t/poster-accelerating-climate-models-using-an-ai-surrogate/1260/2 "2024-08-30T05:38:53Z")
Closed to release votes for this year’s posters.