Latent Diffeomorphic Dynamic Mode Decomposition
By: Willem Diepeveen, Jon Schwenk, Andrea Bertozzi
Potential Business Impact:
Predicts water flow using smart math.
We present Latent Diffeomorphic Dynamic Mode Decomposition (LDDMD), a new data reduction approach for the analysis of non-linear systems that combines the interpretability of Dynamic Mode Decomposition (DMD) with the predictive power of Recurrent Neural Networks (RNNs). Notably, LDDMD maintains simplicity, which enhances interpretability, while effectively modeling and learning complex non-linear systems with memory, enabling accurate predictions. This is exemplified by its successful application in streamflow prediction.
Similar Papers
Localized Dynamic Mode Decomposition with Temporally Adaptive Partitioning
Numerical Analysis
Predicts future better by breaking time into pieces.
Sparse-to-Field Reconstruction via Stochastic Neural Dynamic Mode Decomposition
Machine Learning (CS)
Predicts how things like wind and water move.
Dynamic Modes as Time Representation for Spatiotemporal Forecasting
Machine Learning (CS)
Predicts future weather and traffic better.