Stef De Sabbata
Leicester, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolStef De Sabbata is an Associate Professor and Smart Data Research UK Fellow specialising in Geospatial Artificial Intelligence, combining graph neural networks, spatially-explicit machine learning, and foundation models to advance urban analytics and cultural informatics. With 11 years of research experience across the University of Leicester and the Oxford Internet Institute, she translates cutting-edge AI methods into practical tools for understanding neighbourhoods, museum collections, and the geographies of online content. She chairs the GIScience Research Group at the Royal Geographical Society and serves as Turing academic liaison, reflecting a strong blend of academic leadership and national research coordination. Her work on geospatial mechanistic interpretability of large language models is an unusual cross between spatial analysis and model interpretability, revealing how LLMs encode geographic knowledge. Trained in computer science (MSc) and GIScience (PhD), she brings a rare combination of computational rigor and geographic insight to interdisciplinary problems.
11 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Geographic Information Science and Cartography, Doctor of Philosophy (Ph.D.), Geographic Information Science and Cartography at University of ZurichMaster of Science (M.Sc.), Computer Science, Master of Science (M.Sc.), Computer Science at Università degli Studi di Udine
Italian, English
Github Skills (53)
r-package10
raster10
gdal10
mapping-tools10
geographic10
mappings10
geo10
geos10
geography10
spatial10
science10
maps9
data-science9
r9
geospatial9
Programming languages (6)
Github contributions (5)
sdesabbata/r-for-geographic-data-science
May 2021 - Dec 2022
Contributions:2 releases, 126 commits, 118 pushes in 1 year 7 months
sdesabbata/2011-IEAC
Apr 2022 - Jul 2022
Contributions:41 commits, 46 pushes, 5 branches in 3 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.