spatial distance in sum metric spatiotemporal variogram

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

spatial distance in sum metric spatiotemporal variogram

sara osama

Dear All,
I have fitted the attached sum-metric variogram using the following command:
varpm10 <- variogramST(lnpm10only~1,data=lnpm10_stfdf,assumeRegular=F,na.omit=T)

and the distance in the figure are in decimals. I want to know how this distances are calculated and what is the unit of measurement used. this is the coordinates of the first 5 observations my data

> coords
     longitude latitude
1     30.92500 29.95300
61    31.36000 30.26000
121   31.33300 29.84720
181   31.29800 29.90500
241   31.20416 30.04278
301   31.32000 30.06000
361   31.23900 30.09470
 
by the way the data consists of only 26 stations where the max distance is about 200 km.

Any help will be highly appreciated 

Best regards
Sara

--
Best Regards

Faculty of Economics & Political Science
Cairo University

Tel:(202)35728055-(202)35728116-(202)35736608-(202)35736605
Fax:(202)35711020
Follow us on twitter:https://twitter.com/fepsnews

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

sum metric variogram.docx (59K) Download Attachment
Reply | Threaded
Open this post in threaded view
|

Re: spatial distance in sum metric spatiotemporal variogram

Dr. Benedikt Gräler
Dear Sara,

if you provide information about the coordinate reference system in your
object lnpm10_stfdf@sp@proj4string (e.g. if your data is recorded as
WGS84 geographic coordinates: lnpm10_stfdf@sp@proj4string <-
CRS("+init=epsg:4326") ), distances are calculated as great-circle
distances in "km" for geographic CRS, as straight line distances in m
for projected CRS and if no CRS is defined, the distances will be the
simple euclidean distance of the coordinates.

In your example, there does not seem to be any information about the CRS
and the values are then euclidean distances between latitudes and
longitudes (quite miss-leading in most parts of the world, i.e. 1° N-S
might strongly deviate from 1° E-W).

Furthermore - just to clarify - what you present is the empirical
spatiotemporal variogram. No assumptions about a model (metric,
sum-metric, ...) nor any fit of model parameters have been made.

HTH,

  Ben


On 18/10/2017 09:33, sara osama wrote:

>
> Dear All,
> I have fitted the attached sum-metric variogram using the following command:
> varpm10 <-
> variogramST(lnpm10only~1,data=lnpm10_stfdf,assumeRegular=F,na.omit=T)
>
> and the distance in the figure are in decimals. I want to know how this
> distances are calculated and what is the unit of measurement used. this
> is the coordinates of the first 5 observations my data
>
>  > coords
>       longitude latitude
> 1     30.92500 29.95300
> 61    31.36000 30.26000
> 121   31.33300 29.84720
> 181   31.29800 29.90500
> 241   31.20416 30.04278
> 301   31.32000 30.06000
> 361   31.23900 30.09470
> by the way the data consists of only 26 stations where the max distance
> is about 200 km.
>
> Any help will be highly appreciated
>
> Best regards
> Sara
>
> --
> Best Regards
>
> Faculty of Economics & Political Science
> Cairo University
>
>
> Tel:(202)35728055-(202)35728116-(202)35736608-(202)35736605
> Fax:(202)35711020
> Follow us on twitter:https://twitter.com/fepsnews
>
>
> _______________________________________________
> R-sig-Geo mailing list
> [hidden email]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>
--
Dr. Benedikt Gräler
52°North Initiative for Geospatial Open Source Software GmbH
Martin-Luther-King-Weg 24
48155 Muenster, Germany

E-Mail: [hidden email]
Fon: +49-(0)-251/396371-39
Fax: +49-(0)-251/396371-11

http://52north.org/
Twitter: @FiveTwoN

General Managers: Dr. Albert Remke, Dr. Andreas Wytzisk
Local Court Muenster HRB 10849

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

b_graeler.vcf (458 bytes) Download Attachment