analiza aiqbench
This research applies latent video flow-matching, a generative AI technique, to solve atmospheric data assimilation by generating continuous trajectories from sparse observations. By treating weather forecasting as a multimodal spatiotemporal problem, the method achieves performance competitive with traditional Bayesian inference models while naturally handling filtering and smoothing tasks. This represents a significant application of machine learning architectures in high-stakes scientific computing domains like fluid dynamics and climate modeling.
Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Flow-matching
arXiv:2608.05103v1 Announce Type: new Abstract: Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data. In this study, we propose a fundamentally different, unified approach to atmospheric data assimilation. We use latent video flow-matching to sample temporally consistent trajectories from a prior trained using ERA5 reanalysis (69 variables over an 8-day window). We also use posterior sampling to assimilate real observation sources, such as those from the NOAA Integrated Global Radiosonde Archive and the Integrated Surface Database. Because the prior generates a continuous trajectory, it naturally propagates information between observed and unobserved frames. Therefore, we can perform various DA tasks, such as filtering and smoothing, simply by changing the observed frames. Moreover, we generate full-state ensemble forecasts directly from sparse observations, achieving performance competitive with state-of-the-art observation-to-forecast models.
Abstract:Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data. In this study, we propose a fundamentally different, unified approach to atmospheric data assimilation. We use latent video flow-matching to sample temporally consistent trajectories from a prior trained using ERA5 reanalysis (69 variables over an 8-day window). We also use posterior sampling to assimilate real observation sources, such as those from the NOAA Integrated Global Radiosonde Archive and the Integrated Surface Database. Because the prior generates a continuous trajectory, it naturally propagates information between observed and unobserved frames. Therefore, we can perform various DA tasks, such as filtering and smoothing, simply by changing the observed frames. Moreover, we generate full-state ensemble forecasts directly from sparse observations, achieving performance competitive with state-of-the-art observation-to-forecast models.
Machine Learning (cs.LG); Mathematical Physics (math-ph); Atmospheric and Oceanic Physics (physics.ao-ph); Fluid Dynamics (physics.flu-dyn)
arXiv:2608.05103 [cs.LG]
(or arXiv:2608.05103v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.05103 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 236 cuvinte
Subiecte conexe
LD-EnFF: Latent-Dynamics Ensemble Flow Filtering for Data Assimilation with Sparse Observations
arXiv · 6 oct. 2026
DAWIS: Data Assimilation with Windowed Inverse Sampling via Multitask Interpolants
arXiv · 5 oct. 2026
Akasha 2: Hamiltonian State Space Duality and Visual-Language Joint Embedding Predictive Architectur
arXiv · 16 iun. 2026
Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows
arXiv · 9 oct. 2026