Archives: Team

I graduated from Charles University in Prague with a master’s degree in remote sensing, geoinformatics, and cartography.

Being a member of the EO4Landscape research team and a PhD candidate at the same university, my primary area of interest is the large-scale land cover classifications derived from medium-resolution satellite imagery in accordance with the LULUCF Nomenclature. For this purpose I primarily concentrate on deep learning techniques, which allow to incorporate information from the neighbourhood of the classified pixel into the algorithms.

Also, I’m interested in land cover classification in southern Ethiopia in collaboration with the Czech Geological Survey as well as work on the cloud-based Google Earth Engine platform, which allows for the quick creation of a product from a collection of hundreds of satellite pictures. I also assist Prague Zoo in choosing appropriate locations to reintroduce Przewalski’s horses using remote sensing. Overall, I participate in instructional initiatives promoting remote sensing and GIS at all levels of education, from primary schools to universities.

I am currently a PhD student at the University of Valencia (UV), working on the development of machine learning techniques to assess precursor conditions for extreme hurricane development. I am also helping with the practical implementation of climate-related assessment tools being developed at the AI4OCEANS Group. I hold a MSc on Remote Sensing from the UV. 

Julia is a PhD candidate in computer science at the Leiden Institute for Advanced Computer Science (LIACS) and the SRON Netherlands Institute for Space Research. She designs AutoML algorithms that automatically create and configure neural networks for Earth Observation tasks. 

After finishing his M.Sc. degree in autonomous systems with a thesis on scalable hyperparameter tuning using Bayesian Optimization and a short stay in industry working in an MLOps startup in Stockholm, Kai is now doing his PhD at ETH Zurich.  In his work he focuses on using machine learning methods and earth observation data to improve our understanding of cloud formation processes and aerosol-cloud interactions. Next to his studies, he is part of the core team of Climate Change AI.

Kelsey Doerksen is a 3^rd year PhD Candidate in the Autonomous Intelligent Machines and Systems Program at the University of Oxford, a part of the Oxford Applied and Theoretical Machine Learning Group. Her research focuses on the utilization of AI with Earth Observation data to tackle global climate and humanitarian challenges. Kelsey was previously a Visiting Researcher at the NASA Jet Propulsion Laboratory with the Machine Learning and Instrument Autonomy Team, working on the Scientific Understanding from Data Science Initiative to understand the drivers of air pollution. She has two years of experience as a satellite operator at Planet, operating the world’s largest Earth Observation satellite constellation. Kelsey holds a Masters degree from the University of Western Ontario in Electrical and Computer Engineering, and a Bachelor’s degree in Aerospace Engineering: Space Systems Design from Carleton University.