mlsanityData to 7 Oct 2026

Monthly Diffusion v0.9: A Latent Diffusion Model for the First AI-MIP

arXiv 2604.13481 ↗First posted 15 Apr 2026cs.LG cs.AI physics.ao-phcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Here, we describe Monthly Diffusion at 1.5-degree grid spacing (MD-1.5 version 0.9), a climate emulator that leverages a spherical Fourier neural operator (SFNO)-inspired Conditional Variational Auto-Encoder (CVAE) architecture to model the evolution of low-frequency internal atmospheric variability using latent diffusion. MDv0.9 was designed to forward-step at monthly mean timesteps in a data-sparse regime, using modest computational requirements. This work describes the motivation behind the architecture design, the MDv0.9 training procedure, and initial results.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 10 of its 16 references that are in the map. First posted on arXiv 15 Apr 2026.

Builds on

10 of 16 references.

References · 10

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2019An Introduction to Variational Autoencoderscited by 997
  6. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 748
  7. 2018Understanding disentangling in β-VAEcited by 332
  8. 2023Neural General Circulation Models for Weather and Climatecited by 232
  9. 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 225
  10. 2024Probabilistic Emulation of a Global Climate Model with Spherical DYffusioncited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models with 3D Diffusion Models
  2. 2023DiffESM: Conditional Emulation of Earth System Models with Diffusion Models
  3. 2024Diffusion-Based Joint Temperature and Precipitation Emulation of Earth System Models
  4. 2026PuYun-LDM: A Latent Diffusion Model for High-Resolution Ensemble Weather Forecasts
  5. 2024Latent Diffusion Model for Generating Ensembles of Climate Simulations
  6. 2025A PDE-Informed Latent Diffusion Model for 2-m Temperature Downscaling
  7. 2025AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions
  8. 2026Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?