Max Planck Gesellschaft

Research group: Flora Incognita

Twitter
Facebook
Flora Incognita website


Mission

We develop methods and technologies that enable efficient, rapid and automated monitoring of biodiversity in different habitats and landscapes in order to track the development of ecosystems, species communities and populations and to analyze causes of change.


Team

Name Position E-mail Phone Room
Jana Wäldchen Group leader jwald +49 3677 69 4849 TU Ilmenau
Michael Rzanny PostDoc mrzanny ...6222 C3.005 (tower)
Ladislav Hodac PostDoc lhodac +49 3677 69 1202 TU Ilmenau
Negin Katal PhD student nkatal ...6222 C3.005 (tower)
Alice Deggelmann Scientific assistant adeggel +49 7172 9329311 C3.005 (tower) or TU Ilmenau
Ulrich Weber Technical assistant uweber ...6285 C1.010 (tower)

Open positions

sorry, no open position a.t.m.

updated 27.01.2022

Thesis offers

If you´re interested in writing your thesis within a project of our group, please contact Jana Wäldchen


Current Projects

Flora Incognita - interactive plant species identification with mobile devices


Flora Incognita website

Aim/Objectives
In order to make change/loss of biodiversity visible, species knowledge is key - not only among experts, but for anyone. The research group "Flora Incognita" developed a mobile app that leverages modern computer vision techniques such as deep neural networks with a "connected data" approach, using site information (e.g. climate, geology, phenology) and plant morphological traits for semi-automatic species identification. The collected data are used to answer questions of plant species monitoring and phenology. The app is available for iOS and in the Google Play Store.

Find more information on the Flora Incognita organization, latest news and how to join Flora Incognita activities on the project website . You can also follow us on Twitter or Facebook

Duration: 08/2014 - 07/2024

Collaboration: TU Ilmenau (Data-intensive Systems and Visualization Group)

Funding: Federal Agency for Nature Conservation (BfN), Federal Ministry for the Environment, Nature Conservation and Nuclear Safety (BMU), Thuringian Ministry for the Environment, Energy and Nature Conservation (TMUEN), Federal Ministry of Education and Research (BMBF), Stiftung Naturschutz Thüringen


AI4Biodiv – Artificial Intelligence in biodiversity research


Aim/Objectives
Next to climate change, biodiversity loss is one of the greatest threats to humankind. Biodiversity monitoring is critical for providing advance warning of impending species declines and/or extinctions, for establishing management measures, for quantifying the effectiveness of management practices to conserve biodiversity, and for providing the data to underpin metrics that reflect the status of biodiversity.
Effective and comprehensive biodiversity monitoring requires a wide range of methods and approaches. In the future, the most promising sources of new monitoring data will be in automated and semi-automated data collection and analysis methods that cover large spatial scales. Artificial intelligence will play an indispensable role here.
The AI Research Unit will develop methods and technologies that enable efficient, rapid and automated monitoring of biodiversity in different habitats and landscapes in order to track the development of ecosystems, species communities and populations and to analyze causes of change. Given the availability of a wide range of imagery and satellite data, powerful computers and mobile devices, the methods used in this field will change dramatically in the future.

Duration: 10/2020 - 09/2024

Collaboration: TU Ilmenau (Data-intensive Systems and Visualization Group)

Funding: Federal Ministry of Education and Research (BMBF)


NaturaIncognita - workflow platform for AI-based species identification


Aim/Objectives
The consistent use of the latest artificial intelligence approaches in combination with the constant availability of mobile devices such as smartphones and tablets make it possible to significantly simplify the identification of species, one of the basic tasks of biodiversity monitoring. During our Flora Incognita project on the automatic identification of plant species, we created an initial infrastructure that can be abstracted within the framework of an AI lighthouse project, so that in the future it will be much easier to extend automatic recognition to other species groups and a wide range of questions in the field of biodiversity research. Once a comprehensive infrastructure has been established, smaller projects focusing on specific questions should also be able to use this infrastructure easily.
The project aims to leverage the existing potentials of both the Flora Incognita and the AI Lighthouse projects and take them to the next level. The initial infrastructure of the Flora Incognita project can be abstracted within the framework of the AI Lighthouse project, enabling it to extend the automatic recognition to other species groups.
This comprehensive infrastructure will make answering a wide range of questions on changing biodiversity easier, for example in smaller projects focusing on specific topics.

Duration: 12/2020 - 11/2023

Collaboration: TU Ilmenau (Data-intensive Systems and Visualization Group)

Funding: Federal Ministry for the Environment, Nature Conservation and Nuclear Safety (BMU)


BetterWeeds: Knowledge-based site-specific analysis for environmentally sustainable weed management in integrated crop production


Betterweeds website

Aim/Objectives
Herbicide application is currently the most widely used method to control weeds in conventionally managed arable systems. Against the background of negative impacts of chemical plant protection and an ongoing loss of arable weed diversity, there is a pressing need to develop innovative, environmentally-friendly methods for weed control. The greatest challenge here is creating a balance between an economically viable level of weed control and increasing political and social demands for a more biodiversity-friendly weed management.
To achieve innovative, environmentally-friendly methods for weed control, a) time- and cost-efficient tools for weed detection must be available, b) information on site-specific occurrence of weeds must be provided, and c) management strategies need to be derived from these site-specific weed maps.
The aim of the project is to develop a framework for sustainable weed management using autonomous weed detection, AI-based identification of weed species, and geo-referenced weed distribution maps taking site-specific characteristics of the individual field into account. Based on these maps, management strategies for weed control on the respective fields will be developed and tested under field conditions.
These management strategies will be focused on protecting desirable species with high value for the agro-ecosystem and, at the same time, providing sufficient control of undesirable, highly competitive species.

You can find more information on this project on the BETTER-WEEDS website.

Duration: 05/2021 - 04/2024

Collaboration:

Funding: Federal Ministry of Food and Agriculture (BMEL)



Key papers

Mäder, P., Boho, D., Rzanny, M., Seeland, M., Wittich, H. C., Deggelmann, A., Wäldchen, J. (2021). The Flora Incognita app – interactive plant species identfication. Methods in Ecology and Evolution, 12(7), 1335-1342. doi:10.1111/2041-210X.13611.
Rzanny, M., Mäder, P., Deggelmann, A., Chen, M., Wäldchen, J. (2019). Flowers, leaves or both? How to obtain suitable images for automated plant identification. Plant Methods, 15: 77. doi:10.1186/s13007-019-0462-4.
Wäldchen, J., Mäder, P. (2018). Machine learning for image based species identification. Methods in Ecology and Evolution, 9(11), 2216-2225. doi:10.1111/2041-210X.13075.

Follow link for a complete list of publications by the research group.

Directions | Disclaimer | Data Protection | Contact | Internal | Webmail | Local weather | PRINT | © 2011-2022 Max Planck Institute for Biogeochemistry