[R-sig-Geo] (Linear) interpolation in three (or more) dimensions

[Pascal Oettli]

Hello Mark,

The DINEOF method is designed for problems as yours.

There is an implementation in R here
(http://menugget.blogspot.de/2012/10/dineof-data-interpolating-empirical.html)
but it doesn't directly work on Raster* object.

Hope this helps,
Pascal

On Tue, Jun 3, 2014 at 3:27 PM, Mark Payne <markpayneatwork at gmail.com> wrote:
> Hi,
>
> I have a dataset that consists of satellite observations on a regular
> lon-lat grid at taken at regularly time pointts. Unfortunately due to cloud
> cover, there are gaps dispersed semi-randomly throughout the 3D data array.
> I would like to fill these gaps.
>
> The "best" solution I guess is space-time kriging, if memory limitations
> permit. But before I go that far, I would like to do a simple 3D linear
> interpolation to fill the gaps i.e interpolating the temperature at the
> missing (lon, lat, time) points.
>
> The akima package does an excellent job of this in 2D, but doesn't support
> higher dimensionality. Does anyone know of a function that supports three
> or more dimensions?
>
> Mark
>
>         [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo



-- 
Pascal Oettli
Project Scientist
JAMSTEC
Yokohama, Japan