Presentation by Dr. Hamed Alemohammad, Director of the Center for Geospatial Analytics, Clark University. 

Abstract

There is a rapid growth in developing AI foundation models for Earth observations (EO) including multi-modal models that combine inputs from various sensors in Earth orbit. These developments build on the success of deploying various supervised and semi-supervised techniques for EO in the last several years, and publication of a large number of benchmark datasets. In the first part of this presentation, I will provide an overview of the recent advancements at the intersection of AI and EO, and the applications that have been enabled by these advancements. Then, I will discuss how curation and publication of geospatial benchmarks have contributed to the development of various supervised and semi-supervised techniques for EO. In the second part, I will review foundation models and their utility for geospatial data analytics. Finally, I will introduce the Prithvi foundation model and showcase the results for various downstream tasks including cloud gap filling, land cover/crop type mapping, and burn scar detection.

Bio

Hamed Alemohammad is an Associate Professor at Clark University Graduate School of Geography and Director of the Clark Center for Geospatial Analytics. He is an interdisciplinary scientist with expertise in remote sensing, earth science, and artificial intelligence (AI). His research interest lies at the intersection of geospatial analytics/AI and geography to use observations to better understand the changing Earth system. Hamed has been the PI for several projects focused on developing novel AI models for multispectral, microwave and synthetic aperture radar (SAR) satellite observations. Prior to Clark University, Hamed was the Executive Director and Chief Data Scientist at Radiant Earth where he established and led the development of Radiant MLHub - the open-access repository for geospatial training data and AI models. He received his Ph.D. in Civil and Environmental Engineering from MIT.

Video available upon request.