R package for visualizing uncertainty in spatial data
Branch: master
Clone or download
Latest commit a2afe9c Nov 7, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
R Package name change Nov 8, 2018
data Initial commit Aug 16, 2017
man Package name change Nov 8, 2018
vignettes Package name change Nov 8, 2018
.Rbuildignore Update README files Aug 20, 2017
.gitattributes Initial commit Aug 16, 2017
.gitignore Vignette Aug 17, 2017
DESCRIPTION Package name change Nov 8, 2018
LICENSE Package name change Nov 8, 2018
NAMESPACE Initial commit Aug 16, 2017
README.Rmd Package name change Nov 8, 2018
README.md Package name change Nov 8, 2018
Vizumap.Rproj Package name change Nov 8, 2018


Vizumap: An R package for visualising uncertainty in spatial data.

Installation ------------

You can install a development version of the Vizumap package from GitHub

# install.packages("devtools")
devtools::install_github(repo = "pkuhnert/Vizumap", build_vignettes = TRUE, force = TRUE)


Petra Kuhnert, CSIRO Data61, Email: Petra.Kuhnert@data61.csiro.au

Lydia Lucchesi, University of Washington, Email: lydialuc@uw.edu

About the Package

Approaches for visualizing uncertainty in spatial data are presented in this package. These include the three approaches developed in Lucchesi and Wikle (2017) and a fourth approach presented in Kuhnert et al. (2018) that uses exceedance probabilities to convey uncertainty on a map (or stream network) from a spatio-temporal model.

Bivariate Maps

This approach is an extension of previous implementations of choropleth mapping that includes new features to make the maps more useful for interpretation. Bivariate choropleth maps explore the “blending” of two colour schemes, one representing the estimate and a second representing the margin of error, which can be conveyed on a map through a single blended colour. Bivariate colour maps can be created for both areal and point level data. Using a bivariate colour grid, estimates from a spatial model (e.g. mean) and the uncertainty surrounding these values (e.g. standard deviation) are mapped simulataneously. Vizumap allows the user to create a bivariate colour scheme by mathematically blending two single hue colour palettes and organising them on a 3 x 3 grid. Users can develop their own bivariate colour palette as well as select from some pre-prepared palettes.

Map Pixelation

This approach uses map pixelation to convey uncertainty. This is a novel approach that pixelates areas within each region of the map according to the size of the margin of error. Regions that appear visually as a solid piece of colour reflect smaller margins of error, while more pixelated regions indicate larger margins of error. These maps can be animated using visuanimation techniques to provide a novel “user experience” to visualizing uncertainty on a map.

Glyph Rotation

Glyph rotation uses a glyph to represent uncertainty. When rotated in different ways, the rotation of the glyph corresponds to the margin of error.

Exceedance Probability Maps

The final map based exploration of uncertainty is through exceedance probabilities, that can be showcased on a map to highlight regions that exhibit varying levels of departure from a threshold of concern or target.


A vignette for the Vizumap package is available and contains examples relating to each of the visualisation methods.


How to Reference

Vizumap : An R package for visualizing uncertainty in spatial data, DOI: 10.5281/zenodo.1013930, https://zenodo.org/record/1013930#.W-Nw7fkzbcs


The package Vizumap version 1.1.0 is licensed under GPL-3 (see LICENSE file)


Kuhnert, P.M., Pagendam, D.E., Bartley, R., Gladish, D.W., Lewis, S.E. and Bainbridge, Z.T. (2018) Making management decisions in face of uncertainty: a case study using the Burdekin catchment in the Great Barrier Reef, Marine and Freshwater Research, 69, 1187-1200, https://doi.org/10.1071/MF17237.

Lucchesi, L.R. and Wikle C.K. (2017) Visualizing uncertainty in areal data with bivariate choropleth maps, map pixelation and glyph rotation, Stat, https://doi.org/10.1002/sta4.150.