Principal component analysis for river network data: Use of spatio-temporal correlation and heterogeneous covariance structure

Abstract

We developed a PCA method to reflect the unique characteristics of river networks. The strengths of our approach are that it can (i) reduce dimensionality for streamflow data while effectively removing correlation among them and (ii) identify the group structure of data.

Contribution

We proposed a new PCA method applicable to river network data. https://doi.org/10.1002/env.2753

Code

Refer to https://github.com/qsoon/pca_on_river.