# Generative Modeling for Atmospheric Convection

arXiv: https://arxiv.org/abs/2007.01444 · HTML: https://mlsanity.com/paper/2007.01444/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Deep Learning Based Cloud Cover Parameterization for ICON](https://mlsanity.com/paper/2112.11317/) (2021)
- [Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs](https://mlsanity.com/paper/2112.01221/) (2021)
- [Toward generative machine learning for boosting ensembles of climate simulations](https://mlsanity.com/paper/2602.06287/) (2026)
- [Tools for Extracting Spatio-Temporal Patterns in Meteorological Image Sequences: From Feature Engineering to Attention-Based Neural Networks](https://mlsanity.com/paper/2210.12310/) (2022)
- [Probabilistic bias adjustment of seasonal forecasts using generative machine learning: A case study of Arctic sea ice predictions](https://mlsanity.com/paper/2605.29172/) (2026)

## Abstract (arXiv)

While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implementing a Variational Autoencoder (VAE) that performs structural replication, dimensionality reduction, and clustering of high-resolution vertical velocity fields. Trained on ~6*10^6 samples spanning the globe, the VAE successfully reconstructs the spatial structure of convection, performs unsupervised clustering of convective organization regimes, and identifies anomalous storm activity, confirming the potential of generative modeling to power stochastic parameterizations of convection in climate models.