# Toward generative machine learning for boosting ensembles of climate simulations

arXiv: https://arxiv.org/abs/2602.06287 · HTML: https://mlsanity.com/paper/2602.06287/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 19 of 19)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [From Variational to Deterministic Autoencoders](https://mlsanity.com/paper/1903.12436/) (2019)
- [Deep Learning for Post-Processing Ensemble Weather Forecasts](https://mlsanity.com/paper/2005.08748/) (2020)
- [Structured Uncertainty Prediction Networks](https://mlsanity.com/paper/1802.07079/) (2018)
- [Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function](https://mlsanity.com/paper/2501.19374/) (2025)
- [Probabilistic Emulation of a Global Climate Model with Spherical DYffusion](https://mlsanity.com/paper/2406.14798/) (2024)
- [Dynamical-generative downscaling of climate model ensembles](https://mlsanity.com/paper/2410.01776/) (2024)
- [Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation](https://mlsanity.com/paper/2302.11294/) (2023)
- [A non-intrusive machine learning framework for debiasing long-time coarse resolution climate simulations and quantifying rare events statistics](https://mlsanity.com/paper/2402.18484/) (2024)
- [Capturing Climatic Variability: Using Deep Learning for Stochastic Downscaling](https://mlsanity.com/paper/2406.02587/) (2024)
- [Simultaneous emulation and downscaling with physically-consistent deep learning-based regional ocean emulators](https://mlsanity.com/paper/2501.05058/) (2025)
- [Evaluation of Machine Learning Techniques for Forecast Uncertainty Quantification](https://mlsanity.com/paper/2111.14844/) (2021)
- [Generative Modeling for Atmospheric Convection](https://mlsanity.com/paper/2007.01444/) (2020)
- [A probabilistic framework for learning non-intrusive corrections to long-time climate simulations from short-time training data](https://mlsanity.com/paper/2408.02688/) (2024)
- [GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes](https://mlsanity.com/paper/2508.15196/) (2025)
- [Controlling Weather Field Synthesis Using Variational Autoencoders](https://mlsanity.com/paper/2108.00048/) (2021)
- [Probabilistic bias adjustment of seasonal predictions of Arctic Sea Ice Concentration](https://mlsanity.com/paper/2510.09891/) (2025)

## Built on by (most cited first, 1 of 1)

- [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)

Accurately quantifying uncertainty in predictions and projections arising from irreducible internal climate variability is critical for informed decision making. Such uncertainty is typically assessed using ensembles produced with physics based climate models. However, computational constraints impose a trade off between generating the large ensembles required for robust uncertainty estimation and increasing model resolution to better capture fine scale dynamics. Generative machine learning offers a promising pathway to alleviate these constraints. We develop a conditional Variational Autoencoder (cVAE) trained on a limited sample of climate simulations to generate arbitrary large ensembles. The approach is applied to output from monthly CMIP6 historical and future scenario experiments produced with the Canadian Centre for Climate Modelling and Analysis' (CCCma's) Earth system model CanESM5. We show that the cVAE model learns the underlying distribution of the data and generates physically consistent samples that reproduce realistic low and high moment statistics, including extremes. Compared with more sophisticated generative architectures, cVAEs offer a mathematically transparent, interpretable, and computationally efficient framework. Their simplicity lead to some limitations, such as overly smooth outputs, spectral bias, and underdispersion, that we discuss along with strategies to mitigate them. Specifically, we show that incorporating output noise improves the representation of climate relevant multiscale variability, and we propose a simple method to achieve this. Finally, we show that cVAE-enhanced ensembles capture realistic global teleconnection patterns, even under climate conditions absent from the training data.