06. June 2024.

Sebastian Dersch devoted his doctoral thesis to the exciting question of “Advanced single tree segmentation using high resolution remote sensing data” and successfully defended it on May 8, 2024 at the University of Freiburg.

For more than three years, he conducted research under the supervision of Prof. Dr. Peter Krzystek at the Institute for Applications of Machine Learning and Intelligent Systems. He was able to show that AI-based segmentation methods significantly outperform conventional methods in terms of accuracy and quality. One highlight of his work is the semi-supervised approach, which almost completely replaces the manual generation of training data.

“AI methods will make a huge contribution to creating a digital twin of the forest for the whole of Germany,” predicts Prof. Krzystek. "Sebastian was also able to show that excellent doctorates can be successfully completed at universities of applied sciences. A great career!"

We would like to congratulate Sebastian Dersch on this great success and wish him all the best for the future!