External Drift Kriging in 2D

[gld78]

Hi,
I'm failing to use kriging with external drift in 2D.
Any ideas why the following code is not working (with the error "Krige: wrong number of ext. drift values") ?

# Grid
gridx = np.arange(0.0, 5.5, 0.5)
gridy = np.arange(0.0, 5.5, 0.5)
# observations
data = np.array(
[
[0.3, 1.2, 0.47],
[1.9, 0.6, 0.56],
[1.1, 3.2, 0.74],
[3.3, 4.4, 1.47],
[4.7, 3.8, 1.74],
]
)
x=data[:, 0]
y=data[:, 1]
cond_val=data[:, 2]
# Drift-Samples
ext_drift_samp = np.array([0.5, 0.56, 0.5, 1.5, 1.8])

# drift at the grid level
grid_drift = np.ones((11,11))*0

# define kriging 
model = Gaussian(dim=2, var=1, len_scale=2)
krig = krige.ExtDrift(model=model, 
                      cond_pos=(x,y), 
                      cond_val=cond_val, 
                      ext_drift=ext_drift_samp)
krig((gridx, gridy), ext_drift=grid_drift)

[LSchueler]

Hi,

in the 2d case, you need two drift sample values per point, e.g.

ext_drift_samp = np.array([0.5, 0.56, 0.5, 1.5, 1.8], [0.5, 0.56, 0.5, 1.5, 1.8])

By the way, instead of using

grid_drift = np.ones((11,11))*0

you can use

grid_drift = np.zeros((11,11))

[gld78]

Thanks for your suggestions.
Just one drift sample value per point seems to be fine.
I simply had to call ".structured"

The following code seems to be ok for me:

import numpy as np
from gstools import Gaussian, krige

# Grid
gridx = np.arange(0.0, 5.5, 0.5)
gridy = np.arange(0.0, 5.5, 0.5)
# observations
data = np.array(
[
[0.3, 1.2, 0.47],
[1.9, 0.6, 0.56],
[1.1, 3.2, 0.74],
[3.3, 4.4, 1.47],
[4.7, 3.8, 1.74],
]
)
x=data[:, 0]
y=data[:, 1]
cond_val=data[:, 2]
# Drift-Samples
ext_drift_samp = np.array([0.5, 0.56, 0.5, 1.5, 1.8])

# drift at the grid level
grid_drift = np.ones((11,11))*0

# define kriging 
model = Gaussian(dim=2, var=1, len_scale=2)
krig = krige.ExtDrift(model=model, 
                      cond_pos=(x,y), 
                      cond_val=cond_val, 
                      ext_drift=ext_drift_samp)
krig.structured((gridx, gridy), ext_drift=grid_drift)
krig.plot()