1

I'm new in R and ST kriging, I've constructed a STFDF object with the first 4 hours historical data, and want to forecast the fifth hour data. By using krigeST in R, I've constructed vgm model. But after launching:

pred = krigeST(formula=values~1, data=my_stfdf, newdata = my_pred, modelList=my_Vgm)

everything works fine, but the pred object only contains historical data, without prediction data. Any idea? Thank you in advance.

perigee
  • 9,438
  • 11
  • 31
  • 35
  • Or anyone can give some advices on spatio-temporal kriging with Python. Thank you in advance. – perigee Nov 06 '13 at 08:51
  • I've never used that package before, but typically model predictors in R extend the `predict` method; e.g. `lda(params)` makes the model, and `predict.lda(params, data, lda.model)` actually does the prediction. Is this package constructed similarly? – bright-star Nov 06 '13 at 08:53
  • Have no idea, krigeST is in gstat package. – perigee Nov 06 '13 at 09:12
  • I installed it and checked the documentation. Try taking a look at the help file for `predict.gstat {gstat}`, referenced in [this question](http://stackoverflow.com/questions/13920342/how-to-make-ordinary-kriging-by-using-gstat-predict?rq=1) – bright-star Nov 06 '13 at 20:23
  • Thanks a lot Alexander , will give a try. – perigee Nov 07 '13 at 13:03

0 Answers0