Finetuning the Geospatial Foundation model for Land Cover mapping
- 2024
- KDD 2024
Bianca Zadrozny is currently a senior research manager at IBM Research Brazil, leading the Spatiotemporal Modeling group. The group's mission is to advance the state-of-the-art in the development, evaluation and uncertainty characterization of spatiotemporal predictive and generative models, using data-driven machine learning approaches, physically-driven mathematical modeling approaches as well as hybrid techniques combining both, with a focus on climate & sustainability applications. Bianca is also currently co-leading a global IBM Research initiative on AI Modeling for Climate.
Bianca got her PhD in Computer Science from University of California, San Diego in 2003. After that, she has worked as a researcher at IBM T.J. Watson Research Center, New York and as a professor at Federal Fluminense University, Brazil. In 2011, she joined IBM Research Brazil.
Bianca has published more than 50 scientific articles in peer-reviewed conferences and journals (with over 7000 citations) and has 10 patents granted by the U.S patent office. She has served in the editorial board of the Journal of Machine Learning Research (JMLR) and the Data Mining and Knowledge Discovery (DMKD) journal and also in the program committees of conferences such as ICML, KDD, ECML and NeurIPS.