Rate My Professor Esther Rolf

Rolf's research blends methodological and applied techniques in statistical and geospatial machine learning, with an emphasis on usability, data-efficiency, and fairness. Her work addresses reliable environmental monitoring using machine learning, satellite imagery analysis, data representation's influence on fair systems, and geospatial challenges like spatial error structures. Key publications include 'A generalizable and accessible approach to machine learning with global satellite imagery' in Nature Communications (2021, Rolf et al.); 'Representation matters: Assessing the importance of subgroup allocations in training data' at ICML (2021, Rolf et al.); 'Position: Mission critical–Satellite data is a distinct modality in machine learning' at ICML (2024, Spotlight, Rolf et al.); 'SatCLIP: Global, general-purpose location embeddings with satellite imagery' at AAAI (2025, Klemmer et al.); and 'Mapping on a Budget: Optimizing Spatial Data Collection for ML' at AAAI (2025, Betti et al.). She has received the SDG Digital Gamechangers Award (2023) from the United Nations Development Programme and International Telecommunication Union, best paper awards at ICML (2018), NeurIPS Workshop on AI for Social Good (2019), and ICLR Workshop on Machine Learning for Remote Sensing (2025, best student paper). Rolf teaches CSCI 5622: Machine Learning and CSCI 7000: Geospatial and Statistical Machine Learning at CU Boulder, and contributes to service through peer reviewing for NeurIPS, ICML, ICLR, and workshop organization including lead organizer for ICLR ML for Remote Sensing workshops (2025, 2026). She delivered a keynote at the NeurIPS Tackling Climate Change with Machine Learning workshop (2024).