# Re: vector eof/pca (e.g. u- and v-component of current data)

From: gibies george <gibies_at_nyahnyahspammersnyahnyah>
Date: Mon Mar 14 2011 - 23:01:20 MDT

Hello Malte,

There is a slight different way, which I am using.

We have

u(time,lat,lon)
v(time,lat,lon)

I combibe them into another variable

data(time,lat,lon,component)

where

data&time = u&time ; is also =v&time
data&lat = u&lat ; is also =v&lat
data&lon = u&lon ; is also =v&lon
data&component = (/"uwnd","vwnd"/)

data(time|:,lat|:,lon|:,component|0) = u(time|:,lat|:,lon|:)
data(time|:,lat|:,lon|:,component|1) = u(time|:,lat|:,lon|:)

Then find the EOF of the variable data.

On 15 March 2011 01:56, Dennis Shea <shea@ucar.edu> wrote:

> Hello,
>
> D. S. Wilks
> Statistical Methods in the Atmospheric Sciences
>
> pp 477-479:
>
> Section 11.2.2: Simultaneous PCA for Multiple Fields
>
> I would suggest you look at results from both the
> correlation and covariance matrices.
>
> Good luck
>
>
>
>
> On 03/14/2011 12:17 PM, Malte Stuecker wrote:
> > Hi everyone,
> >
> > I have done EOF analysis for scalar fields (e.g. SST) with the NCL EOF
> > functions, however I am struggling with the concept of how to do an
> > EOF analysis of vector data (e.g. analyzing the u- and v- component of
> > ocean current data at the same time). I understand that it is possible
> > to represent both quantities as a complex number, however I am not
> > sure about the practical (=programming) approach. Most literature that
> > I found seems to cover only the theory, but there are not many 'HOW TO
> > DO' sources out there.
> > My idea was to just combine the u and v fields in one matrix along one
> > of the spatial axis (e.g. combining a u (20E-40E,20S-20N) and v field
> > (20E-40E,20S-20N) to a (20E-40E,40S-40N) field), calculate the EOF and
> > afterwards split the eigenvector matrix into the u- and v- component
> > and plot the resulting vectors. In this case, is it possible to
> > interpret the eigenvalues + eigenvectors in the same way as you would
> > doing an EOF analysis on a scalar field? It would be great if anyone
> > could point me to some step-by-step introduction to this type of
> > problem or knows maybe some software packages other than NCL that
> > could deal with this type of analysis comfortably.
> > Thank you very much in advance!
> > _______________________________________________
> > ncl-talk mailing list
> > List instructions, subscriber options, unsubscribe:
> > http://mailman.ucar.edu/mailman/listinfo/ncl-talk
> _______________________________________________
> ncl-talk mailing list
> List instructions, subscriber options, unsubscribe:
> http://mailman.ucar.edu/mailman/listinfo/ncl-talk
>

```--
*Gibies George,   CSIR-RF,*
*Seasonal Scale Prediction Group,
Climate and Global Modelling Division,
Indian Institute of Tropical Meteorology,
NCL (P. O.), Pashan,
Pune 411008, India.*