3 papers
cs.LG2026
Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations
Phillip Si, Yuan Qiu, Omar Sallam +4
AI-driven flood digital twins demand fast hydrodynamic surrogates for ensemble forecasting and observation assimilation. Yet even GPU-accelerated two-dimensional shallow water equa…
stat.ML2026
LD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse Observations
Pengpeng Xiao, Phillip Si, Peng Chen
Data assimilation techniques are crucial for accurately tracking complex dynamical systems by integrating observational data with numerical forecasts. Recently, score-based data as…
cs.LG2026
LEVDA: Latent Ensemble Variational Data Assimilation via Differentiable Dynamics
Phillip Si, Peng Chen
Long-range geophysical forecasts are fundamentally limited by chaotic dynamics and numerical errors. While data assimilation can mitigate these issues, classical variational smooth…