A statistical interpolation method, also known as Gaussian process regression, most used in geo-statistics. The goal is to map a surface given limited sample data. The process evaluates the variability of supplied data, then uses a weighted average of neighbouring points -- considering both distance and direction -- to interpolate the desired map points.
Questions tagged [kriging]
186 questions
1
vote
1 answer
Turn a 1D array into a sample by OpenTURNS in Python
I'm trying to interpolate responses on a 2D grid by Kriging following this example:
How to interpolate 2D spatial data with kriging in Python?
However, when I'm trying to create a sample from 1D array in OpenTURNS,
import numpy as np
import…
zip
- 21
- 5
1
vote
0 answers
Assertion Error for 3D kriging interpolation using GeoStats package in Julia
I am trying to build a kriging surface interpolation example using GeoStats.jl package.
I have supplied x and y coordinates as inputs and z coordinates as values to train the function. Then I try to predict the z values for other set of inputs.
The…
Mohammad Saad
- 1,935
- 10
- 28
1
vote
1 answer
PyKrige witing a file with 3D kriged data
I am trying to krig soil volumes in 3D using pykrige. I am using ordinary kriging, but once I am done kriging the data, I am not sure how I can write it to an ascii file, Here is my code:
from pykrige.ok3d import OrdinaryKriging3D
from pykrige.uk3d…
Astro
- 11
- 1
1
vote
0 answers
How to perform regression Kriging with R studio using gstat?
I'm struggling with regression kriging in R. I want to interpolate the temperature of a watershed under consideration of elevation, but get always the same error when I want to perform the last step, which is the kriging.
I have two data frames, one…
DAFZ
- 11
- 3
1
vote
1 answer
How to create anisotropic exponential and gaussian correlation function in Python for kernel?
I have a dataset of 1000 observed samples of 6 features that form the X and one target variable that forms the Y.
I am using kriging or Gaussian Process Regressor to train my models. I would like to use anisotropic Gaussian and anisotropic…
Shivam Mishra
- 25
- 5
1
vote
2 answers
Alternative to for-loop for large dataset to improve computational speed
For kriging, I need to compute large mesh arrays of length 20000. The code below works fine, especially for small mesh length (< 100), however, the computational time for such large mesh is very long (approx 45min). The length of data ranges between…
user2554925
- 487
- 2
- 8
1
vote
0 answers
Nugget value is always zero while using scikit-geostat
import numpy as np
import skgstat as skg
coordinates = long_data
values =N_data
V = skg.Variogram(coordinates=coordinates, values=values ,maxlag=np.max(dists)/2.0 , use_nugget =True )
print(V)
V.plot()
enter image description here
from the graph…
Nikhil Dupally
- 753
- 1
- 4
- 12
1
vote
1 answer
is there vignette for the r package randomfields?
i would like to learn more about the R package RandomFields: Simulation and Analysis of Random Fields, and vignettes are usually a good way to go about that.
Lee De Cola
- 31
- 4
1
vote
1 answer
Representing different layers in a ggplot map! R
M intention is to represent 3 different layers of information in a ggplot map:
1. The map itself using a MULTIPOLYGON file
2. Kriging estimations using geom_tile()
3. datapoints using geom_point()
I used the following…
Cebs
- 180
- 13
1
vote
1 answer
Ordinary kriging questions
really newbie here. I would like to do an ordinary kriging on missing rainfall value.Here is my code.
from pykrige.ok import OrdinaryKriging
import numpy as np
import pandas as pd
fname = "C:/Users/Tan/Desktop/sample1.csv"
df =…
SK Tan
- 11
- 1
1
vote
2 answers
Spatial interpolation with kriging or nearest neighbor method?
This is an open question concerning interpolation of data.
My starting point is a couple hundred XYZ points that unevenly spaced, i.e. a point cloud.
I want to use kriging to give the Z values to the points in the area defined by
gridx =…
tincan
- 322
- 2
- 12
1
vote
0 answers
Using kriging in R to extrapolate
I have a very limited time series; Only 4 points are available.
S<-c(81,78,72,65)
x<-c(1,3,5,10)
S represents the survival rate, and t the time in years.
So far, I had used the nlm method to try and predict survival rate at t=20 with the…
Chu
- 17
- 6
1
vote
1 answer
Getting predicted values from autoKrige
I've just performed kriging on my spatial data using the autoKrigefunction from the automap package. However, I am now struggling to get the fitted values.
I can simply execute plot(kriging_results) and see the map, but I want to make some changes…
David
- 371
- 2
- 13
1
vote
0 answers
Why is kriging using parallel processing still using memory and not using my processors?
I have a large dataset of measurement over an area. I want to interpolate my data using kriging over my study area. My final output should be a raster/grid.
My pc has 8Gb RAM and 4 cores. When I try to use predict() with my fitted variogram, my…
A. Lachaud
- 15
- 1
- 5
1
vote
1 answer
Kriging with gstat : "Covariance matrix singular at location" with predict
I am trying to do an estimation by kriging with gstat, but can never achieve it because of an issue with the covariance matrix. I never have estimates on the locations I want, because they are all skipped. I have the following warning message, for…
Dric
- 87
- 13