Auditing geospatial datasets for biases: using global building datasets for disaster risk management

Caroline M. Gevaert, Thomas Buunk, Marc J.C. van den Homberg

Research output: Contribution to journalArticleAcademicpeer-review

20 Downloads (Pure)

Abstract

The presence of biases has been demonstrated in a wide range of machine learning applications; however, it is not yet widespread in the case of geospatial datasets. This study illustrates the importance of auditing geospatial datasets for biases, with a particular focus on disaster risk management applications, as a lack of local data may direct humanitarian actors to utilize global building datasets to estimate damage and the distribution of aid efforts. It is important to ensure that there are no biases against the representation of vulnerable populations, and that they are not missed in the distribution of aid. This manuscript audits four global building datasets (Google Open Buildings, Microsoft Bing Maps Building Footprints, Overture Maps Foundation, and OpenStreetMap) for biases regarding the Relative Wealth Index, population density, urban/rural proportions, and building size in Tanzania and the Philippines. The dataset accuracies for these two countries are lower than expected. Google Open Buildings (with a confidence above 0.7) and OpenStreetMap demonstrated the best combinations of False Negative and False Discovery, though Google Open Buildings was more consistent across tiles. The equality of opportunity was lowest for the urban/rural proportions, whereas the OpenStreetMap and Overture Maps Foundation displayed particularly low equality of opportunity for population density and Relative Wealth Index in Tanzania. These results demonstrate that biases exist in these geospatial datasets. The types of biases are not consistent across the datasets and the two study areas, which emphasizes the importance of auditing these datasets for biases in new applications and study areas.

Original languageEnglish
Pages (from-to)12579-12590
Number of pages12
JournalIEEE Journal of selected topics in applied earth observations and remote sensing
Volume17
Early online date3 Jul 2024
DOIs
Publication statusPublished - 2024

Keywords

  • Artificial intelligence
  • bias
  • building detection
  • Buildings
  • Disasters
  • equity
  • ethics
  • Geospatial analysis
  • humanitarian aid
  • Internet
  • machine learning
  • Sociology
  • Statistics
  • ITC-GOLD
  • ITC-ISI-JOURNAL-ARTICLE

Fingerprint

Dive into the research topics of 'Auditing geospatial datasets for biases: using global building datasets for disaster risk management'. Together they form a unique fingerprint.

Cite this