Quality of crowdsourced data on urban morphology : the Human Influence Experiment (HUMINEX)
- Author
- Benjamin Bechtel, Matthias Demuzere (UGent) , Panagiotis Sismanidis, Daniel Fenner, Oscar Brousse, Christoph Beck, Frieke Vancoillie (UGent) , Olaf Conrad, Iphigenia Keramitsoglou, Ariane Middel, Gerald Mills, Dev Niyogi, Marco Otto, Linda See and Marie-Leen Verdonck
- Organization
- Abstract
- The World Urban Database and Access Portal Tools (WUDAPT) is a community initiative to collect worldwide data on urban form (i.e., morphology, materials) and function (i.e., use and metabolism). This is achieved through crowdsourcing, which we define here as the collection of data by a bounded crowd, composed of students. In this process, training data for the classification of urban structures into Local Climate Zones (LCZ) are obtained, which are, like most volunteered geographic information initiatives, of unknown quality. In this study, we investigated the quality of 94 crowdsourced training datasets for ten cities, generated by 119 students from six universities. The results showed large discrepancies and the resulting LCZ maps were mostly of poor to moderate quality. This was due to general difficulties in the human interpretation of the (urban) landscape and in the understanding of the LCZ scheme. However, the quality of the LCZ maps improved with the number of training data revisions. As evidence for the wisdom of the crowd, improvements of up to 20% in overall accuracy were found when multiple training datasets were used together to create a single LCZ map. This improvement was greatest for small training datasets, saturating at about ten to fifteen sets.
- Keywords
- Local Climate Zones (LCZs), urban climate, crowdsourcing, volunteered geographic information, classification, WUDAPT, LOCAL CLIMATE ZONES, VOLUNTEERED GEOGRAPHIC INFORMATION, CLASSIFICATION, CITIES, MODEL, VARIABILITY, RESILIENCE, ACCURACY, WUDAPT, GROWTH
Downloads
-
Bechtel etal US 2017.pdf
- full text (Published version)
- |
- open access
- |
- |
- 12.82 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8531312
- MLA
- Bechtel, Benjamin, et al. “Quality of Crowdsourced Data on Urban Morphology : The Human Influence Experiment (HUMINEX).” URBAN SCIENCE, vol. 1, no. 2, 2017, doi:10.3390/urbansci1020015.
- APA
- Bechtel, B., Demuzere, M., Sismanidis, P., Fenner, D., Brousse, O., Beck, C., … Verdonck, M.-L. (2017). Quality of crowdsourced data on urban morphology : the Human Influence Experiment (HUMINEX). URBAN SCIENCE, 1(2). https://doi.org/10.3390/urbansci1020015
- Chicago author-date
- Bechtel, Benjamin, Matthias Demuzere, Panagiotis Sismanidis, Daniel Fenner, Oscar Brousse, Christoph Beck, Frieke Vancoillie, et al. 2017. “Quality of Crowdsourced Data on Urban Morphology : The Human Influence Experiment (HUMINEX).” URBAN SCIENCE 1 (2). https://doi.org/10.3390/urbansci1020015.
- Chicago author-date (all authors)
- Bechtel, Benjamin, Matthias Demuzere, Panagiotis Sismanidis, Daniel Fenner, Oscar Brousse, Christoph Beck, Frieke Vancoillie, Olaf Conrad, Iphigenia Keramitsoglou, Ariane Middel, Gerald Mills, Dev Niyogi, Marco Otto, Linda See, and Marie-Leen Verdonck. 2017. “Quality of Crowdsourced Data on Urban Morphology : The Human Influence Experiment (HUMINEX).” URBAN SCIENCE 1 (2). doi:10.3390/urbansci1020015.
- Vancouver
- 1.Bechtel B, Demuzere M, Sismanidis P, Fenner D, Brousse O, Beck C, et al. Quality of crowdsourced data on urban morphology : the Human Influence Experiment (HUMINEX). URBAN SCIENCE. 2017;1(2).
- IEEE
- [1]B. Bechtel et al., “Quality of crowdsourced data on urban morphology : the Human Influence Experiment (HUMINEX),” URBAN SCIENCE, vol. 1, no. 2, 2017.
@article{8531312,
abstract = {{The World Urban Database and Access Portal Tools (WUDAPT) is a community initiative to collect worldwide data on urban form (i.e., morphology, materials) and function (i.e., use and metabolism). This is achieved through crowdsourcing, which we define here as the collection of data by a bounded crowd, composed of students. In this process, training data for the classification of urban structures into Local Climate Zones (LCZ) are obtained, which are, like most volunteered geographic information initiatives, of unknown quality. In this study, we investigated the quality of 94 crowdsourced training datasets for ten cities, generated by 119 students from six universities. The results showed large discrepancies and the resulting LCZ maps were mostly of poor to moderate quality. This was due to general difficulties in the human interpretation of the (urban) landscape and in the understanding of the LCZ scheme. However, the quality of the LCZ maps improved with the number of training data revisions. As evidence for the wisdom of the crowd, improvements of up to 20% in overall accuracy were found when multiple training datasets were used together to create a single LCZ map. This improvement was greatest for small training datasets, saturating at about ten to fifteen sets.}},
articleno = {{15}},
author = {{Bechtel, Benjamin and Demuzere, Matthias and Sismanidis, Panagiotis and Fenner, Daniel and Brousse, Oscar and Beck, Christoph and Vancoillie, Frieke and Conrad, Olaf and Keramitsoglou, Iphigenia and Middel, Ariane and Mills, Gerald and Niyogi, Dev and Otto, Marco and See, Linda and Verdonck, Marie-Leen}},
issn = {{2413-8851}},
journal = {{URBAN SCIENCE}},
keywords = {{Local Climate Zones (LCZs),urban climate,crowdsourcing,volunteered geographic information,classification,WUDAPT,LOCAL CLIMATE ZONES,VOLUNTEERED GEOGRAPHIC INFORMATION,CLASSIFICATION,CITIES,MODEL,VARIABILITY,RESILIENCE,ACCURACY,WUDAPT,GROWTH}},
language = {{eng}},
number = {{2}},
pages = {{21}},
title = {{Quality of crowdsourced data on urban morphology : the Human Influence Experiment (HUMINEX)}},
url = {{http://doi.org/10.3390/urbansci1020015}},
volume = {{1}},
year = {{2017}},
}
- Altmetric
- View in Altmetric