AI RESEARCH
From Video-to-PDE: Data-Driven Discovery of Nonlinear Dye Plume Dynamics
arXiv CS.LG
•
ArXi:2605.04535v1 Announce Type: new Inferring continuum models directly from video is hampered by two facts: the recorded field is uncalibrated image intensity rather than a physical state, and direct numerical differentiation of noisy frames is unstable. We develop a video-to-PDE pipeline that converts grayscale recordings of an ink plume into a normalised scalar field $u(x,y,t)$, isolates a bulk drift $\mathbf{}(t)$ from intrinsic spreading via the intensity-weighted centroid, and identifies an effective transport law by weak-form sparse regression.