Ashesh Chattopadhyay (@ashesh6810) header
Ashesh Chattopadhyay (@ashesh6810) profile picture

Asst. Prof @am_ucsc Ex @PARCinc, PhD @RiceMech, deep learning for dynamical systems and weather/climate, theoretical deep learning, scientific computing

Houston, TX
Joined March 2017
Photo by Ashesh Chattopadhyay (@ashesh6810)Photo by Ashesh Chattopadhyay (@ashesh6810)
Ashesh Chattopadhyay retweeted
Thrilled to share that Ashesh Chattopadhyay (@ashesh6810), assistant professor of applied mathematics at #BaskinEngineering, was awarded the 2026 @TheSIAMNews Activity Group on Mathematics of Planet Earth Early Career Prize! Learn more: bit.ly/4wlKxNk
3
6
581
🧵 1/10 We introduce a new theoretical framework for continuous score-based diffusion models, showing that standard DDPMs contain a built-in spectral failure mode when applied to any multiscale, power-law physical system. arxiv.org/abs/2512.09572
1
1
121
9/10 📌 Key Theoretical Insights ⚡ Spectral collapse is SDE-driven ⚡ Linear schedules are incompatible with power-law systems ⚡ β(τ) must be designed as a spectral operator ⚡ One-step generators emerge naturally from score geometry
1
64
10/10 🚀 Closing Our framework links spectral physics + SDE theory to define when diffusion models succeed—or fail—on multi-scale systems. This theory provides a blueprint for stable, high-fidelity generative modeling of physical dynamics.
64
🚀 Why it’s exciting: ✅ Physically grounded ✅ 10x–1000x faster than ROMS ✅ Enables regional “digital twins” ✅ Sets up for coupled ocean–atmosphere emulation ✅ Works across different reanalysis sources AI meets ocean science.
1
71
🚨 New preprint alert! “Generative Lagrangian Data Assimilation for Ocean Dynamics Under Extreme Sparsity” is live! 📄 arxiv.org/abs/2507.06479🌊 Reconstructs high-res ocean states from just 0.1% data using #GenAI. No forward model needed. (1/5)
1
101
Our method is: ⚡️ One-shot 🌀 Physically-consistent 🌐 Scalable It captures high-wavenumber, fine-scale structures other ML baselines miss. Spectral diagnostics & vorticity metrics confirm this. (4/5)
1
60
Led by @ucsc PhD students Niloofar & Lenny with Tianning Wu & Roy He from @NCState (5/5)
56