Factors affect the reliability of the experimental variogram

Computing and modelling variograms

  1. Plot the experimental variogram.

  2. Choose several models that appear to have the right shape and fit each in turn by weighted least squares (Cressie, 1985; McBratney and Webster, 1986) in an accredited program.

  3. Plot the fitted models on the graph of the experimental variogram and assess whether the fit looks reasonable.

  4. If all plausible models seem to fit well, choose the one with the smallest residual sum of squares (RSS) or smallest mean square.

  1. One might be able to improve a fit in the above sense by elaborating the model. Any combination of the simple valid models is itself valid. The Akaike information criterion, the AIC (Akaike, 1973), may help to answer. The aim is to minimize it (Webster and McBratney, 1989; Webster and Oliver, 2007).

Factors affect the reliability of the experimental variogram

  • Size of sample

  • Lag interval and bin width

  • Marginal distribution of the data

  • Anisotropy

  • Trend

Variogram modelling

  • How to choose an appropriate model function

  • How to judge fitting quality

  • Sample size influence

Source: https://scikit-gstat.readthedocs.io/en/latest/auto_examples/tutorial_03_variogram_models.html#sphx-glr-auto-examples-tutorial-03-variogram-models-py

How do we find what directions you should calculate the variogram?

  • Explore data

  • Combining knowledge of geologists

  • Azimuth angle in degrees clockwise from north

Paprameter Setting when Calculating Variograms

  • Number of lags

  • Distance between lags

  • Lag tolerance

Visual representation of parameters

See here

Reading

Reading

Python tutorials

Tute 1

Tute 2

Tute 3