Titlebar

Export bibliographic data
Literature by the same author
plus on the publication server
plus at Google Scholar

 

Mapping cultural ecosystem services 2.0 - Potential and shortcomings from unlabeled crowd sourced images

Title data

Lee, Heera ; Seo, Bumsuk ; Koellner, Thomas ; Lautenbach, Sven:
Mapping cultural ecosystem services 2.0 - Potential and shortcomings from unlabeled crowd sourced images.
In: Ecological Indicators. Vol. 96 (2019) Issue 1 . - pp. 505-515.
ISSN 1470-160x
DOI: https://doi.org/10.1016/j.ecolind.2018.08.035

Abstract in another language

The volume of accessible geotagged crowdsourced photos has increased. Such data include spatial, temporal,and thematic information on recreation and outdoor activities, thus can be used to quantify the demand forcultural ecosystem services (CES). So far photo content has been analyzed based on user-labeled tags or themanual labeling of photos. Both approaches are challenged with respect to consistency and cost-efficiency,especially for large-scale studies with an enormous volume of photos. In this study, we aim at developing a newmethod to analyze the content of large volumes of photos and to derive indicators of socio-cultural usage oflandscapes. The method uses machine-learning and network analysis to identify clusters of photo content thatcan be used as an indicator of cultural services provided by landscapes. The approach was applied in the Mulderiver basin in Saxony, Germany. All public Flickr photos (n=12,635) belonging to the basin were tagged bydeep convolutional neural networks through a cloud computing platform, Clarifai. The machine-predicted tagswere analyzed by a network analysis that leads to nine hierarchical clusters. Those clusters were used to distinguishbetween photos related to CES (65%) and not related to CES (35%). Among the nine clusters, twoclusters were related to CES: ‘landscape aesthetics’ and ‘existence’. This step allowed mapping of different aspectsof CES and separation of non-relevant photos from further analysis. We further analyzed the impact ofprotected areas on the spatial pattern of CES and not-related CES photos. The presence of protected areas had asignificant positive impact on the areas with both ‘landscape aesthetics’ and ‘existence’ photos: the total numberof days in each mapping unit where at least one photo was taken by a user (‘photo-user-day’) increased with theshare of protected areas around the location. The presented approach has shown its potential for reliablemapping of socio-cultural uses of landscapes. It is expected to scale well with large numbers of photos and to beeasily transferable to different regions.

Further data

Item Type: Article in a journal
Refereed: Yes
Additional notes: BAYCEER149167
Keywords: Social media photo services; Cloud computing; Tagging; Keywords network analysis; Mapping ecosystem services; Big data analysis
Institutions of the University: Faculties > Faculty of Biology, Chemistry and Earth Sciences > Department of Earth Sciences > Professorship Ecological Services
Faculties > Faculty of Biology, Chemistry and Earth Sciences > Department of Earth Sciences > Professorship Ecological Services > Professorship Ecological Services - Univ.-Prof. Dr. Thomas Köllner
Research Institutions
Research Institutions > Research Centres
Research Institutions > Research Centres > Bayreuth Center of Ecology and Environmental Research- BayCEER
Result of work at the UBT: Yes
DDC Subjects: 500 Science
Date Deposited: 25 Mar 2019 10:18
Last Modified: 25 Mar 2019 10:18
URI: https://eref.uni-bayreuth.de/id/eprint/48083