Staff Publications

Staff Publications

  • external user (warningwarning)
  • Log in as
  • language uk
  • About

    'Staff publications' is the digital repository of Wageningen University & Research

    'Staff publications' contains references to publications authored by Wageningen University staff from 1976 onward.

    Publications authored by the staff of the Research Institutes are available from 1995 onwards.

    Full text documents are added when available. The database is updated daily and currently holds about 240,000 items, of which 72,000 in open access.

    We have a manual that explains all the features 

Record number 509046
Title 'spup' - An R package for uncertainty propagation in spatial environmental modelling
Author(s) Sawicka, K.; Heuvelink, G.B.M.
Source In: Proceedings of Spatial Accuracy 2016. - International Spatial Accuracy Research Association (ISARA) - ISBN 9782910545105 - p. 275 - 282.
Event 12th International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences, Accuracy 2016, Montpellier, 2016-07-05/2016-07-08
Department(s) Soil Geography and Landscape
ISRIC - World Soil Information
Publication type Contribution in proceedings
Publication year 2016
Keyword(s) Monte Carlo - R language - Spatial models - Uncertainty analysis - Uncertainty propagation

Computer models are crucial tools in engineering and environmental sciences for simulating the behaviour of complex systems. While many models are deterministic, the uncertainty in their predictions needs to be estimated before they are used for decision support. Advances in uncertainty analysis have been paralleled by a growing number of software tools, but none has gained recognition for universal applicability, including case studies with spatial models and spatial model inputs. We develop an R package that facilitates uncertainty propagation analysis in spatial environmental modelling. The 'spup' package includes functions for uncertainty model specification, propagation of uncertainty using Monte Carlo (MC) techniques, and uncertainty visualization functions. Uncertain variables are represented as objects which uncertainty is described by probability distributions. Spatial auto-correlation within a variable and crosscorrelation between variables is also accommodated for. The package has implemented the MC approach with efficient sampling algorithms, i.e. stratified random sampling and Latin hypercube sampling. The MC realizations may be used as an input to the environmental models called from R, or externally. Selected static and interactive visualization methods that are understandable by nonstatisticians can be used to visualize uncertainty about the measured input, model parameters and output of the uncertainty propagation.

There are no comments yet. You can post the first one!
Post a comment
Please log in to use this service. Login as Wageningen University & Research user or guest user in upper right hand corner of this page.