Am quite new to wavelet analysis and would like some help. I am performing a spatio-temporal analysis of monthly gridded rainfall data. With PCA, I can reduce the dimension of the rainfall data into a few leading modes, yielding EOFs (which explain spatial variability) and principal components (explaining temporal variability).
I would like to perform a similar analysis with wavelets using the Matlab Wavelet Toolbox. As of now, I am able to decompose a 2D data (spatial decomposition in my case) but unable to take into account the temporal variability in the data.
My first course of action has been to first compress the data with PCA and then perform wavelet decomposition of the leading modes in both the spatial (EOFs) and temporal (PCs) domain.
I am wondering if this is the right way to perform such an analysis and would like suggestions as to how to proceed.
Thanks a lot.