Nonlinear independent component analysis is combined with diffusion-map data analysis techniques to detect good observables in high-dimensional dynamic data. These detections are achieved by integrating local principal component analysis of simulation bursts by using eigenvectors of a Markov matrix describing anisotropic diffusion. The widely applicable procedure, a crucial step in model reduction approaches, is illustrated on stochastic chemical reaction network simulations.
|Number of pages
|Proceedings of the National Academy of Sciences of the United States of America
|Published - Sep 22 2009
All Science Journal Classification (ASJC) codes
- Chemical reactions
- Dimensionality reduction
- Slow manifold