Daniel Klotz

Research group:

Ass.Prof. Daniel Klotz works on the intersection between machine learning and earth science. Specifically, he and his team study how we can learn and describe the variability and movement of water: When is how much water where? Finding answers to this question is especially important when we have too much or too little water. And, machine learning provides us with an opportunity to get better and more precise answers.  

Short bio:

Daniel Klotz works on the intersection between machine learning and earth science. In his research he focuses on developing and applying data-driven approaches for understanding, describing and reducing environmental risks. In short, the focus is on applied, cutting edge research developed in close relationship with real world applications. For example, a specific focus are hydrological phenomena such as floods and droughts — natural hazards that have severe impact on human lives. Floods are associated with high-rainfall intensities and can often happen in very short times. Droughts have a much larger spatial and temporal extent (that can persist over several years). Machine learning provides an avenue to develop comprehensive hydrological modeling approaches with the ability to depict the required scales across time and space.