Generating Initial Conditions for Ensemble Data Assimilation of Large-Eddy Simulations with Latent Diffusion Models

by   Alex Rybchuk, et al.

In order to accurately reconstruct the time history of the atmospheric state, ensemble-based data assimilation algorithms need to be initialized appropriately. At present, there is no standard approach to initializing large-eddy simulation codes for microscale data assimilation. Here, given synthetic observations, we generate ensembles of plausible initial conditions using a latent diffusion model. We modify the original, two-dimensional latent diffusion model code to work on three-dimensional turbulent fields. The algorithm produces realistic and diverse samples that successfully run when inserted into a large-eddy simulation code. The samples have physically plausible turbulent structures on large and moderate spatial scales in the context of our simulations. The generated ensembles show a lower spread in the vicinity of observations while having higher variability further from the observations, matching expected behavior. Ensembles demonstrate near-zero bias relative to ground truth in the vicinity of observations, but rank histogram analysis suggests that ensembles have too little member-to-member variability when compared to an ideal ensemble. Given the success of the latent diffusion model, the generated ensembles will be tested in their ability to recreate a time history of the atmosphere when coupled to an ensemble-based data assimilation algorithm in upcoming work. We find that diffusion models show promise and potential for other applications within the geosciences.


page 7

page 11

page 12

page 13

page 23

page 24

page 25

page 26


Generating observation guided ensembles for data assimilation with denoising diffusion probabilistic model

This paper presents an ensemble data assimilation method using the pseud...

Training Data Attribution for Diffusion Models

Diffusion models have become increasingly popular for synthesizing high-...

Towards replacing precipitation ensemble predictions systems using machine learning

Precipitation forecasts are less accurate compared to other meteorologic...

Reducing the irreducible uncertainty in return periods of 21st-century precipitation extremes

Internal climate variability, captured through multiple initial conditio...

KNN Ensembles for Tweedie Regression: The Power of Multiscale Neighborhoods

Very few K-nearest-neighbor (KNN) ensembles exist, despite the efficacy ...

Hybrid iterative ensemble smoother for history matching of hierarchical models

The choice of the prior model can have a large impact on the ability to ...

RINGER: Rapid Conformer Generation for Macrocycles with Sequence-Conditioned Internal Coordinate Diffusion

Macrocyclic peptides are an emerging therapeutic modality, yet computati...

Please sign up or login with your details

Forgot password? Click here to reset