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.

My research aims at the development of machine learning methods, which are particularly designed for the analysis of remote sensing data. I specifically focus on techniques for sophisticated feature learning and data analysis methods which integrate prior knowledge such as scientific domain knowledge. I 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. My 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.

Research interests:

  • Ocean remote sensing and plant phenotyping
  • Explainable and interpretable machine learning
  • (Deep) representation/feature learning
  • Theory-guided/informed machine learning