Mapping uncertain geographical attributes: incorporating robustness into choropleth classification design

Wangshu Mu, Daoqin Tong

Research output: Contribution to journalArticle

Abstract

Choropleth mapping provides a simple but effective visual presentation of geographical data. Traditional choropleth mapping methods assume that data to be displayed are certain. This may not be true for many real-world problems. For example, attributes generated based on surveys may contain sampling and non-sampling error, and results generated using statistical inferences often come with a certain level of uncertainty. In recent years, several studies have incorporated uncertain geographical attributes into choropleth mapping with a primary focus on identifying the most homogeneous classes. However, no studies have yet accounted for the possibility that an areal unit might be placed in a wrong class due to data uncertainty. This paper addresses this issue by proposing a robustness measure and incorporating it into the optimal design of choropleth maps. In particular, this study proposes a discretization method to solve the new optimization problem along with a novel theoretical bound to evaluate solution quality. The new approach is applied to map the American Community Survey data. Test results suggest a tradeoff between within-class homogeneity and robustness. The study provides an important perspective on addressing data uncertainty in choropleth map design and offers a new approach for spatial analysts and decision-makers to incorporate robustness into the mapmaking process.

Original languageEnglish (US)
JournalInternational Journal of Geographical Information Science
DOIs
StateAccepted/In press - Jan 1 2020
Externally publishedYes

    Fingerprint

Keywords

  • Choropleth Mapping
  • optimization
  • robustness
  • uncertainty

ASJC Scopus subject areas

  • Information Systems
  • Geography, Planning and Development
  • Library and Information Sciences

Cite this