Spatial Sampling for Mapping

You are here


Spatial Sampling for Mapping

To be announced


Sound sampling design is essential for the collection of data to support reliable scientific inference and decision making for management and policy. What counts as a sound design depends on the problem of interest, and the nature of the inference that is required. Many statistical analyses of spatial data, particularly for the prediction of local values as in mapping, are done in a model-based context in which data are treated as realizations of an underlying random process. In this setting it is not necessary to select sampling locations by probability sampling, and there is scope to optimize sampling patterns computationally.
In this course, some of the concepts that underlie the optimization of spatial sampling will be introduced. These include methods to ensure good spatial coverage by a sample, methods to select an optimal grid spacing for geostatistical mapping and complex methods of combinatorial optimization to minimize the expected prediction error variance under certain assumptions about the underlying model. Participants in the course will be provided with scripts for use in R which will allow them to use the methods that are described to solve sampling optimization problems.


Day 1: Regular grid sampling, spatial coverage sampling and model-based sampling (first part)

  • Sampling on regular grids. How to decide on the orientation and spacing?
  • Spatial coverage and spatial infill sampling. How to design a spatial coverage sample? How to account for existing sampling locations?
  • Introduction to kriging. What is a variogram? How to compute optimal weights? How to compute the prediction error variance? What determines this variance? How to exploit covariates in kriging?
  • Optimization of the grid-spacing for ordinary kriging

Day 2: Model-based sampling (continued)

  • Optimization of the grid-spacing for kriging with an external drift
  • Optimization of the sampling locations for ordinary kriging
  • Optimization of the sampling locations for kriging with an external drift
  • Sampling for estimating the variogram: nested sampling, and random sampling of pairs of points

Day 3: Sampling for mapping by non-spatial models; sampling for validation

  • Spatial response surface sampling for mapping by linear regression models
  • Spatial Latin hypercube sampling for mapping by classification and regression trees
  • Sampling for validation of maps; Why is probability sampling the best option, and what sampling designs are recommendable?
  • Wrapping up, discussion of case studies provided by participants
General information
Target Group The course is aimed at PhD candidates and other academics
Group Size Min. 15, max. 25 participants
Course duration 3 days
Language of instruction English
Frequency of recurrence Once every two years
Number of credits 0.9 ECTS
Lecturers Dr. Dick Brus (Alterra - Soil, water and land use, Wageningen UR)
Prior knowledge Basic knowledge of R is assumed
Location Wageningen University Campus
Options for accommodation Accommodation is not included in the fee of the course, but there are several possibilities in Wageningen. For information on B&B's and hotels in Wageningen please visit Another option is Short Stay Wageningen. Furthermore Airbnb offers several rooms in the area. Note that besides the restaurants in Wageningen, there are also options to have dinner at Wageningen Campus.
More information

Claudius van de Vijver (PE&RC)
Phone: +31 (0) 317 485116

Lennart Suselbeek (PE&RC)
Phone: +31 (0) 317 485426

Registration of interest

At this moment, this course is not scheduled yet. However, if you register your interest in this activity below, we will inform you as soon as the course is scheduled and registration of participation is opened.