Stochastic Parameterization of Moist Physics Using Probabilistic Diffusion Model

Le-Yi Wang, Yiming Wang, Xiaoyu Hu, Hui Wang, Ruilin ZhouPreprints.org 2024 · DOI

Abstract

Deep-learning-based convection schemes receive wide attention due to its impressive im-provement on precipitation distribution and tropical convections of earth system simulation. But they cannot represent the stochasticity of moist physics, which will degrade the simulation of large-scale circulations, climate mean, and variability. To solve this problem, a stochastic pa-rameterization scheme based on probabilistic diffusion model named DIFF-MP is developed. The cloud-resolving data from GRIST model is coarse-grained into resolved-scale variables and sub-grid contributions due to moist physics to form the training data. DIFF-MP’s performance is compared against generative adversarial network and variational autoencoder. Results show that DIFF-MP is consistently better than the other two models on prediction error, coverage ratio, and spread-skill correlation. The standard deviation, skewness, and kurtosis of subgrid contributions generated by DIFF-MP is also closer to the testing data than the others. Interpretability experiment shows that DIFF-MP’s parameterization of moist physics is physically reasonable.
BibTeX
@misc{wang2024stochastic,
  author = {Le-Yi Wang and Yiming Wang and Xiaoyu Hu and Hui Wang and Ruilin Zhou},
  title = {{Stochastic Parameterization of Moist Physics Using Probabilistic Diffusion Model}},
  year = {2024},
  doi = {10.20944/preprints202409.1262.v1},
  howpublished = {Preprints.org},
}

Loading related content...

Figure