5 papers
Predictor-Driven Diffusion for Spatiotemporal Generation
Yuki Yasuda, Tobias Bischoff
Multiscale spatial structure complicates temporal prediction because small-scale spatial fluctuations influence large-scale evolution, yet resolving all scales is often intractable…
Statistical Parameter Calibration via the Generalized Fluctuation Dissipation Theorem and Generative Modeling
Ludovico T. Giorgini, Tobias Bischoff, Andre N. Souza
We introduce a response-theoretic framework that recasts parameter calibration of ergodic stochastic differential equations as a fluctuation-dissipation problem. Our central result…
Reduced-Order Modeling of Cyclo-Stationary Time Series Using Score-Based Generative Methods
Ludovico Theo Giorgini, Tobias Bischoff, Andre Noguiera Souza
Many natural systems exhibit cyclo-stationary behavior characterized by periodic forcing such as annual and diurnal cycles. We present a data-driven method leveraging recent advanc…
Surface to Seafloor: A Generative AI Framework for Decoding the Ocean Interior State
Andre N. Souza, Simone Silvestri, Katherine Deck +3
Understanding subsurface ocean dynamics is essential for quantifying oceanic heat and mass transport, but direct observations at depth remain sparse due to logistical and technolog…
KGMM: A K-means Clustering Approach to Gaussian Mixture Modeling for Score Function Estimation
Ludovico T. Giorgini, Tobias Bischoff, Andre N. Souza
We propose a hybrid method for accurately estimating the score function, i.e., the gradient of the log steady-state density, using a Gaussian Mixture Model (GMM) in conjunction wit…