Konstantin Klemmer

Konstantin Klemmer is an incoming assistant professor at University College London who specializes in the representation of geospatial phenomena in machine learning methods. His work focuses on developing statistical machine learning methods and self-supervised representation learning to better understand complex geospatial data, with applications ranging from urban environments to global climate change mitigation.

Konstantin is a leading researcher in the development of Earth embeddings — AI-native representations of Earth. He is the creator of SatCLIP and is pioneering a new class of foundation models that aim to learn the dynamics of our planet within the neurons of neural networks. In addition to his academic role at University College London, Konstantin is a researcher at LGND AI Inc., a geospatial infrastructure firm that utilizes machine learning to turn satellite imagery and Earth observation data into searchable, AI-ready insights.

He previously held positions as a postdoctoral researcher and research scientist at Microsoft Research and is a core team member of Climate Change AI, a global initiative fostering impactful work at the intersection of AI and climate change. Konstantin completed his Ph.D. at the University of Warwick.