Counting the countless: Machine learning for long-term monitoring of alpine plant diversity in the Hohe Tauern National Park

Thomas Eberl, Roland Kaiser, Christoph Praschl, Gerald Adam Zwettler

Research output: Contribution to conferencePaperpeer-review


The Hohe Tauern National Park has founded an interdisciplinary monitoring and research program for long-term observation of alpine ecosystems (after this referred to as LTM). This initiative provides - among other findings - an ongoing digital image archive in the form of strictly standardised (geo-static, colourfast), high-resolution (1px. ~ 0,1mm) nadir photos (view vertical to the ground) with overwhelmingly high information content and great relevance in terms of documentation. These data, comparable to earth orthophotos, represent the basis for the project at hand. It focuses on developing a software prototype (S/W) to automatically recognise plants from image data using computer vision and machine learning (CV/ML). The goals are threefold. First, the reliable recognition of individual plant species and their individuals, despite overlap with other plants or vegetation structures, is aimed. Secondly, the variation in nature and thus divergent appearance of a specimen is addressed. Thirdly, it should be possible to detect identical plants within a time series. In addition, the S/W should allow the models to be updated when new data are available.
Original languageGerman (Austria)
Publication statusPublished - Sept 2022
EventInternational Symposium for Research in Protected Areas - Wien, Austria
Duration: 7 Sept 20229 Sept 2022
Conference number: 7


ConferenceInternational Symposium for Research in Protected Areas
Internet address

Cite this