Geostatistics for Reliable Mapping with Isatis

Gain a sound understanding of the geostatistics essential methods for environmental applications


The course objective is to present the basic concepts and methods of geostatistics for interpolating between data in environmental applications. The subject matter ranges from variograms to kriging and multivariate geostatistics. The potential pitfalls and hints in the geostatistical analysis of data are highlighted for each of these concepts. Particular attention is paid to the specific issues related to air pollution.

Key Features

The ability of geostatistics to handle data that are characterised by spatial heterogeneity.

Who should attend

The course is designed for geologists, engineers and other geoscientists requiring a practical introduction to geostatistical methods applied to data analysis, interpolation and simulation.

Course content

  • Introduction: what is geostatistics? The advantages of using geostatistics over existing methods.
  • The foundation stone of geostatistics: quantifying the spatial behaviour via the variogram. Calculating, modelling and interpreting the directional variograms.
  • Interpolating between the data: the theory and practice of kriging. The estimated values reflect the spatial continuity observed in the data.
  • Multivariate geostatistics and cokriging. Integrating multidisciplinary correlated data (remote sensing data, DTM’s or other co-factors) to improve the final estimate.
  • Using non-stationary geostatistics to respect the trend present in the data.

Half of the course is dedicated to practical computer exercises, using Isatis in order to reinforce the previously presented theoretical notions.

For the attendees interested in applying the notions presented during the training on the their own data set, 2 additional days can be scheduled with the assistance of a senior geostatistician. Call us for more information.


No prior knowledge of geostatistics is required. However a basic understanding of statistics is recommended.