Successful PhD defense at the Doctoral College GIScience

Earth observation (EO) images are indispensable for many of the tasks when analyzing and monitoring the Earth. EO images yield quantifiable indicators and other objective information that can be used to assist in policy-making, decision-making, and status reporting – but information needs to be derived and classified from raw data. 

In his thesis, entitled "Evaluation of knowledge-based and machine learning models for Earth Observation and Geoinformatics applications", Omid Ghorbanzadeh, PhD candidate of the Doctoral College "GIScience" at the department of Geoinformatics - Z_GIS, developed methods for  detailed and timely assessment of disaster-affected regions and to categorize and spatially delineate disaster-prone areas. He developed artificial intelligence (AI) image analysis methods further and juxtaposed them to knowledge-based methods, particularly object-based image analysis (OBIA) methods. This thesis ultimately contributes to critically evaluate the possibility and efficiency of using AI methods for some EO and spatial modeling applications. This thesis shows the possibility of combining human knowledge and experience with AI methods to achieve more reliable results in EO and spatial modeling applications in 27 peer-reviewed publications in various case studies of human-made and natural disasters.

We wish Omid all the best for his future career.