NeuralDMD framework reconstructs spatio-temporal dynamics from sparse data

Researchers have introduced NeuralDMD, a novel framework that combines neural implicit representations with Dynamic Mode Decomposition (DMD) to reconstruct continuous spatio-temporal dynamics from sparse and noisy measurements. This interpretable, untrained approach parameterizes DMD modes as continuous neural fields and enforces temporal continuity with a low-rank linear dynamics prior. NeuralDMD has demonstrated superior performance over existing methods in tasks such as weather data assimilation and analyzing interferometric observations of Sagittarius A*, showing stability in forecasting and potential for nonlinear applications. AI

IMPACT Enables more accurate reconstruction and forecasting of complex spatio-temporal systems from limited data.

RANK_REASON The cluster contains a research paper detailing a new computational framework. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Ali SaraerToosi
• dynamic mode decomposition
• NeuralDMD
• Sagittarius A*

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →