MIT lab's PEM-UDE recovers interpretable chaos equations from noisy data

burny_tech · x · 2026-09-29

Researchers at MIT's Miller Lab and Christopher Rackauckas et al. present PEM-UDE (arXiv 2507.03631), combining prediction-error methodology with universal differential equations to discover governing equations from limited, noisy chaotic data. Key points:

Original post →

More from Research

Research channel →