REVIEW 7 cited by
DiffDA: a Diffusion Model for Weather-scale Data Assimilation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The generation of initial conditions via accurate data assimilation is crucial for weather forecasting and climate modeling. We propose DiffDA as a denoising diffusion model capable of assimilating atmospheric variables using predicted states and sparse observations. Acknowledging the similarity between a weather forecast model and a denoising diffusion model dedicated to weather applications, we adapt the pretrained GraphCast neural network as the backbone of the diffusion model. Through experiments based on simulated observations from the ERA5 reanalysis dataset, our method can produce assimilated global atmospheric data consistent with observations at 0.25 deg (~30km) resolution globally. This marks the highest resolution achieved by ML data assimilation models. The experiments also show that the initial conditions assimilated from sparse observations (less than 0.96% of gridded data) and 48-hour forecast can be used for forecast models with a loss of lead time of at most 24 hours compared to initial conditions from state-of-the-art data assimilation in ERA5. This enables the application of the method to real-world applications, such as creating reanalysis datasets with autoregressive data assimilation.
Forward citations
Cited by 7 Pith papers
-
Using Diffusion Models to do Data Assimilation
Diffusion DA systems with climatological, cycled, or forecast-augmented priors target different posterior distributions; only a per-cycle retrained model matches ensemble DA.
-
Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Video Flow-matching
A single latent video flow-matching prior over ERA5, guided by sparse real observations, performs filtering, smoothing, and observation-to-forecast without retraining.
-
PnP-DA: Towards Principled Plug-and-Play Integration of Variational Data Assimilation and Generative Models
PnP-DA combines a lightweight variational observation update with a pretrained conditional flow-matching denoiser to reduce analysis error in chaotic data assimilation, outperforming 3D-Var on Lorenz 63, Lorenz 96, an...
-
ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion
A guided diffusion model pre-trained on climate simulations reconstructs multi-layer global ocean temperature from sparse observations, reporting low MSE on CMIP6 and EN4 data.
-
LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting
A latent diffusion model generates medium-range global weather ensembles at 1.5 degrees that match ECMWF IFS-ENS deterministic skill at lower compute, with weaker probabilistic spread and anecdotal cyclone advantages.
-
Ocean-E2E: Hybrid Physics-Based and Data-Driven Global Forecasting of Extreme Marine Heatwaves with End-to-End Neural Assimilation
Ocean-E2E, a hybrid physics-and-AI model with neural data assimilation, forecasts global marine heatwaves up to 40 days ahead with reported skill above ECMWF's S2S system.
-
Probabilistic Spatial Interpolation of Sparse Data using Diffusion Models
KrigSCD, a kriging-smoothed diffusion inpainting method, reconstructs 2D temperature fields from sparse masks and beats IDW, kriging, and plain diffusion on LPIPS at all tested coverage levels.
Discussion (0). Sign in to comment.