Training-Free Data Assimilation with GenCast

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Training-Free Data Assimilation with GenCast
Συγγραφείς: Savary, Thomas, Rozet, François, Louppe, Gilles
Συνεισφορές: Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège
Πηγή: Climate Change AI Workshop, San Diego, United States - California [US-CA], 07-12-2025
Έτος έκδοσης: 2025
Θεματικοί όροι: Computer Science - Learning, Engineering, computing & technology, Computer science, Ingénierie, informatique & technologie, Sciences informatiques
Περιγραφή: Data assimilation is widely used in many disciplines such as meteorology, oceanography, and robotics to estimate the state of a dynamical system from noisy observations. In this work, we propose a lightweight and general method to perform data assimilation using diffusion models pre-trained for emulating dynamical systems. Our method builds on particle filters, a class of data assimilation algorithms, and does not require any further training. As a guiding example throughout this work, we illustrate our methodology on GenCast, a diffusion-based model that generates global ensemble weather forecasts.
Τύπος εγγράφου: conference poster not in proceedings
http://purl.org/coar/resource_type/c_18co
conferencePoster
peer reviewed
Γλώσσα: English
Σύνδεσμος πρόσβασης: https://orbi.uliege.be/handle/2268/340521
Rights: open access
http://purl.org/coar/access_right/c_abf2
info:eu-repo/semantics/openAccess
Αριθμός Καταχώρησης: edsorb.340521
Βάση Δεδομένων: ORBi
Περιγραφή
Η περιγραφή δεν είναι διαθέσιμη