Fig. 2: Correlation matrix of spatiotemporal features and principal components (PCs).
From: Visual exploration dynamics are low-dimensional and driven by intrinsic factors
The line plot shows the variance explained by different PCs. The matrix shows the correlation (Pearson’s r) between features, which are ordered according to their loadings in the first three PCs. The colour of Y-axis labels indicates the PC with the highest loading for the corresponding feature, and features written in bold are those with loadings > 0.2.
