Skip to main content
Seminar | Environmental Science

Accelerating Spatio-temporal AI

EVS Seminar

Abstract: The world of digital discovery has been revolutionized by the ability to index and rapidly search and retrieve information. However, despite many advances, insights from spatio-temporal data — information collected across space and time, such as weather data and models, satellite and aerial imagery, map information and geocoded data from devices and sensors from the Internet of Things (loT) — are difficult to obtain, partially because such data cannot be quickly searched and discover due to its complexity, formats but most importantly to its enormous size.

In this presentation, we present new approaches for scalable spatio-temporal data indexing, processing, and analytics, which accelerate analytical tasks such as AI modeling by orders of magnitudes. The talk will include a series of examples illustrating complex analytics, ML and AI on multi-modal data sets including applications to weather, climate, agriculture, and renewable energy.

Bio: Hendrik Hamann is a Distinguished Research Staff Member and the Global leader for Climate and Sustainability Research in IBM Research. He is also the Chief Scientist for Climate and Sustainability in IBM. He received his PhD from the University of Göttingen in Germany.