Hi,
You'll find 2 krigings algorithm implemented in R.
In the processing toolbox, you can get these scripts with R scripts >
Tools > Get R scripts from on-line scripts :
* Kriging
* Kriging with model selection
Regards,
Le 28/09/2015 11:35, Victor Olaya a écrit :
Kriging is not that hard to find in QGIS, you just have to go to the
Processing search box and type "Kriging" to find all the the kriging
algorithms ;-)
From the point of view of user-friendliness, the Processing
implementation (wrapping the corresponding SAGA modules), might not be
as easy to use as some people would like, but for tools such as
kriging I am strongly against wizard-like UI's and similar elements.
ArcGIS's Statistical Analyst is great and has a wizard with a
fantastic "next" button that allows you to interpolate using all sort
of esoteric methods and will make you believe that you are creating
sound raster layers...when the truth is that, without knowledge, you
are creating rubish. I don't like to give users that wrong sensation.
People want a "Kriging for dummies" functionality, and that's is a bad
idea. Kriging is complex and it's not easy to understand the
underlying principles...but you have to understand them if you want to
use the tool. I think there's no other functionality as misused in GIS
software as this one...everyone want to use kriging because it's cool
and they have heard it's better...but without studying what it really
is.
(I get questions about this topic often, so here's my take on it and
on why the Processing implementation is like that, in case it might
help).
Regards
2015-09-28 9:46 GMT+02:00 Sjur Kolberg <[email protected]>:
I'd prefer Kriging to IDW also for simple jobs.
Kriging is (at least) four operations:
0: Know the assumptions and check your data, transform if necessary and
possible.
1: Estimate your empirical semivariogram (describing how difference increases
with distance).
2: Select a parametric semivariogram model, and adjust parameters to fit the
point cloud from 1)
3: Use the parametric model to calculate a weight matrix between each target
location (grid point) and each observation point.
Loosely speaking, the three first operations define the core of Kriging. The
last operation answers the same question as IDW, both providing the
coefficients (weights) in a linear combination of the input data.
With Gaussian data, spatial stationarity, well-spread data points and a
properly selected/tuned semivariogram model, Kriging can be shown to be 'Best
linear unbiased estimator' (BLUE), and provides mathematically correct
estimates of the variance at each target location. IDW promises no such thing,
hence appears less dependent on assumptions. This does not imply that IDW is
more robust or almost-as-good for simple tasks.
For the numbers that both methods do provide, it is possible to evaluate and
compare the two using leave-one-out cross validation.
With just a reasonable a priori judgment for the range parameter, my guess is
that Kriging will beat IDW in cross-validation for most problems, including
notoriously assumption-breaking daily precipitation data. With some scripting,
it is also possible to optimise Kriging's semivariogram parameters by
minimising the cross-validation RMSE. This does not qualify for being BLUE or
for trusting the variance estimates, though.
All this said, the extra burden of finding Kriging in one of QGIS' plugins, may
serve as a warning that there is more to it than just plug-and play.
Sjur :-)
-----Original Message-----
From: [email protected] [mailto:qgis-developer-
[email protected]] On Behalf Of Barry Rowlingson
Sent: 26. september 2015 19:43
To: Stefan Keller
Cc: [email protected]
Subject: Re: [Qgis-developer] Kriging interpolation functionality in QGIS?
On Fri, Sep 25, 2015 at 6:46 PM, Stefan Keller <[email protected]> wrote:
Hi Barry
Many thanks for your explanations and hints.
So from a pragmatic point-of-view ("80/20 pareto rule"):
Do you think Inverse Distance Weighting (IDW) would do the job as
well, since Kriging has so many parameters to fiddle around and to
understand?
Depends on what "the job" is. To get an impression of the overall trend of a
set
of samples - IDW is probably fine. But to get a
*principled* (ie based on a statistical model) set of estimates over a grid
*with
honest estimates of uncertainty* so you can answer probabilistic questions (like
"what's the chance that the soil over there will contain 1ug gold/tonne?") you
need something like kriging.
Barry
_______________________________________________
Qgis-developer mailing list
[email protected]
http://lists.osgeo.org/mailman/listinfo/qgis-developer
_______________________________________________
Qgis-developer mailing list
[email protected]
http://lists.osgeo.org/mailman/listinfo/qgis-developer
_______________________________________________
Qgis-developer mailing list
[email protected]
http://lists.osgeo.org/mailman/listinfo/qgis-developer
_______________________________________________
Qgis-developer mailing list
[email protected]
http://lists.osgeo.org/mailman/listinfo/qgis-developer
