Mapping cultural ecosystem services 2.0 – using machine learning annotated photos to learn how humans perceive landscapes and ecosystems

Ecosystems provide many different services to mankind. Services provided depend on how the land is used – land use decisions lead to trade-offs that with respect to the ecosystem service provided by ecosystems and landscapes. This trade-offs vary in many situations in space and time. Therefore, it is essential to quantify and map service provisioning and service demand. The so-called cultural services are hardest to quantify since it involves human perception of the environment.

A research team consisting of members of the Heidelberg GIScience team, the KIT, the Kangwon National University as well as the Universities of Bonn and Bayreuth used publically available photos on Flickr® to quantify and map different dimensions of cultural services for the German Mulde basin. They used deep convolutional neural networks and social network analysis to classify the photos by their content. Mapping the cultural services related photos allowed a better understanding of how the landscapes were perceived and used by people and builds an important base for a forthcoming trade-off analysis with other services and biodiversity indicators. The approach reveals the potential of VGI data for the quantification of human-environment interactions, trade-off analysis and nature conservation planning.

Lee, H., Seo, B., Koellner, T., Lautenbach, S., 2019. Mapping cultural ecosystem services 2.0 – potential and shortcomings from unlabeled crowd sourced images. Ecol. Indic. 96, 505–515.

The article can be accessed free of charge till the 30th of November.



, ,