Loading Events

From Efficient Foundation Models to AI Agents for Foundation Model Recommendation to Advance Earth Observation

Webinar Speaker:

Begüm Demir

Affiliation:

TU Berlin

About the Webinar

In this talk, Prof. Demir will present the recent developments of her team in the context of foundation models for Earth observation (EO). Particular attention will be given to their ‘EO Foundation Model Database’ that is the first structured and schema-guided resource covering more than 150 EO foundation models trained using various EO data modalities, associated with different spatial, spectral, and temporal resolutions, considering different learning paradigms. Then, she will introduce REMSA (Remote-sensing Model Selection Agent) that is the first LLM agent for automated EO foundation model selection from natural language queries. During her talk, she will also discuss the efficiency of the existing EO foundation models and will present their recent efficient model with soft mixture-of-experts. Finally, she will present potential pathways for future research.

About the Speaker

TU Berlin: FG Remote Sensing Image Analysis Begüm Demir

Prof. Demir is currently a Full Professor and the founder head of the Remote Sensing Image Analysis (RSiM) group at the Faculty of Electrical Engineering and Computer Science, TU Berlin and the head of the Big Data Analytics for Earth Observation research group at the Berlin Institute for the Foundations of Learning and Data (BIFOLD). Her research activities lie at the intersection of machine learning and data management for Earth observation. She was awarded by the prestigious ‘2018 Early Career Award’ by the IEEE Geoscience and Remote Sensing Society for her research contributions in machine learning for information retrieval in remote sensing. In 2018, she received a Starting Grant from the European Research Council (ERC) for her project ’BigEarth: Accurate and Scalable Processing of Big Data in Earth Observation’. She is an IEEE Senior Member and Fellow of European Lab for Learning and Intelligent Systems (ELLIS).

Days
Hours
Minutes
Seconds

Looking for an older Event? See our Past Events. Events prior to April 2024 can be found in our Events Archive.