A light blue banner on which numerous circles are depicted in which various flowers can be seen. The three flowers that make up the home screen of the Flora Incognita app are placed in the centre of the banner.

Biodiversity, Ecosystems and Society

Dr. Jana Wäldchen

Our mission

Our research aims to harness the potential of artificial intelligence and citizen science to connect and advance the fields of earth sciences and ecology. We focus on improving biodiversity research through the development of methods for automated species identification and the integration of large-scale plant occurrence and trait data. Using these approaches, we seek to better understand ecological and biogeochemical processes, particularly in the context of climate and biodiversity change. In parallel, we engage in public participation initiatives that promote scientific literacy and foster a stronger connection between society and the natural environment.

AI for species identification and morphological & functional trait extraction

Automated species identification has become an essential tool in contemporary biodiversity research and monitoring. A central focus of our group is the continuous development of the Flora Incognita app, which enables the automatic identification of more than 30,000 species of plants, mosses, fungi, and lichens. Our current work aims to further improve the recognition of rare species and taxonomically complex groups, striving to achieve accuracy comparable to that of a human expert. The Flora Incognita app is designed not only as a platform for citizen science, but also as a reliable instrument for scientific plant surveys, both in research and in nature conservation. Beyond plant identification and the ongoing development of the app, we also develop and apply AI methods to other groups of organisms, such as phytoplankton, and to the analysis of morphometric data across diverse taxa. In addition, we work on the automatic extraction of plant traits (e.g. phenological stages) from image data.

Latest key publications:

Hodac et al. (2025) Exploiting algal strains for robust cross‐domain phytoplankton classification via deep learning. Limnology and Oceanography: Methods.
Katal et al. (2025) Expanding phenological insights: automated phenostage annotation with community science plant images. International Journal of Biometeorology: 1-15.
Hodac et al. (2024) Deep learning to capture leaf shape in plant images: Validation by geometric morphometrics. The Plant Journal 120.4: 1343-1357.
Mäder et al. (2021) The flora incognita app–interactive plant species identification. Methods in Ecology and Evolution. 12: 1335– 134

Biodiversity, ecosystems & nature conservation

Understanding how biodiversity influences ecosystem functioning is fundamental to ecology. To capture the complex patterns of biodiversity change and ecosystem processes, we rely on diverse and heterogeneous datasets. Our research focuses on leveraging opportunistic citizen science data across multiple taxa and on developing statistical methods that make these increasingly data sources suitable for addressing a broad range of questions in biodiversity research and biodiversity monitoring.

Latest key publications:

Rzanny et al. (2024) Opportunistic plant observations reveal spatial and temporal gradients in phenology. npj biodivers 3, 5
Katal & Rzanny et al. (2023) Bridging the gap: how to adopt opportunistic plant observations for phenology monitoring. Front. Plant Sci. 14:1150956.

Citizen science, education & science communication

Tell me and I forget. Teach me and I remember. Involve me and I learn.

Within our group, and in collaboration with external partners, we conduct various citizen science projects to address ecological research questions. In addition, as part of the Flora Incognita project, we engage extensively in science communication. Our goal is to explore how participatory research can be advanced and effectively communicated, and how it can enhance both public understanding of nature and acceptance of science. Furthermore, we aim to investigate how automated species identification and citizen science initiatives in schools and universities can contribute to improved biodiversity literacy and scientific knowledge, and to identify the necessary steps to achieve these outcomes.

Latest key publications