2022-06: The whole group is attending and presenting at the ISPRS Congress in Nice

2022-04: The preprint of our paper ,,GrowliFlower: An image time series dataset for GROWth analysis of cauLIFLOWER” is out now

2022-04: Johannes joins our team as a doctoral student

2022-03: Jana presents the GrowliFlower benchmark at DIGICROP2022 digital conference

2022-03: Ahmed joins our team as a doctoral student

2022-02: Acceptance of our paper ,,Behind the leaves: Estimation of occluded grapevine berries with conditional generative adversarial networks.” in the journal Frontiers in Artificial Intelligence

2022-01: Dr. Scarlet Stadtler joins our team as Visiting Researcher

2021-12: Open PhD position in the area of explainable machine learning. Apply now

2021-12: Congratulations to all students who completed their thesis in our group this year, namely Jean-Marie Hembach (B.Sc.), Erik Böhland (B.Sc.), Hidir Cem Altun (M.Sc.), Miro Miranda Lorenz (M.Sc.) and Qusai Marashdeh (M.Sc.)

2021-11: Funding of new Collaborative Research Center “Regional Climate Change: The Role of Land Use and Water Management” with participation of our group for Land Use and Land Cover (LULC) classification

2021-11: Lukas joins AI4EO Future Lab at Technical University Munich for one month

2021-11: Funding of new project WIKI: Re-analysis/prediction of water storage in Europe using AI

2021-10: Lukas discusses innovations and science communication in the bioeconomy with interdisciplinary early career scientists at Bioökonomie-Camp

2021-09: Eike, Jana and Lukas present their current projects at the Frontierts ofGeodetic Science (FROGS)

2021-07: Immanuel presents the ArtifiVe-Potsdam dataset at the IGARSS 2021 digital conference

2021-07: Timo Stomberg presents jUngle-Net at ISPRS digital conference 2021

Our mission

Remote sensing observations play an important role in the geo- and bioscientific community, since they enable various applications to accurately monitor the Earth and its changes – close-range as well as from space. Observation systems regularly provide data with a spectrally, spatially and temporally high resolution. Beside the challenge to deal with large amounts of data and limited class label information, current and future challenges comprise the definition and the way of integration of scientific domain knowledge, the learning of sophisticated features and the fusion of multiple types of sensor data.

Our research aims at the development of machine learning methods, which are particularly designed for the analysis of remote sensing data. We specifically focus on techniques for sophisticated feature learning and data analysis methods which integrate prior knowledge such as scientific domain knowledge. We believe that it is important to develop methods which ensure a high discrimination power and at the same time model the underlying structure of the data. Moreover, to take the next step in understanding geo- and biophysical phenomena, both data science models and theory-based models need to be combined to form powerful informed machine learning models. Our research also addresses explainable machine learning approaches which are able to tackle common challenges in the sciences such as the provision of reliable and scientific consistent results. These models give us a deeper understanding of what we have learned and can provide us with new scientific insights.

Current projects

Robotics and Phenotyping for Sustainable Crop Production
Optimization of cauliflower cultivation

AI Strategy for Earth System Data

Identification, tracking, and classification of ocean eddies in along-track radar altimetry data using deep learning