Lunch Talk: Dr. Eleni Tzirita Zacharatou, Transforming heterogeneous spatial data into insights

Abstract: The recent proliferation of spatial remote sensing datasets from satellite missions has created new opportunities for data-driven approaches in domains such as climate change monitoring and disaster management. To extract meaningful information from satellite images, researchers and practitioners often need to combine them with additional datasets encompassing sociodemographic, economic, and public administration information. However, existing spatial systems provide limited functionality in processing heterogeneous spatial data and differ significantly in terms of interfaces, architecture, and performance, making it difficult for users to select the best system for their workload. In this talk, I will show how we address this challenge with a framework that offers users a unified interface across multiple spatial systems serving as execution backends. Additionally, I will delve into the performance of loading heterogeneous spatial data stored in diverse file formats using different libraries, highlighting the impact of file format and library on loading throughput and micro-architectural behaviour.

Bio: Eleni Tzirita Zacharatou is an assistant professor in the Computer Science Department at the IT University of Copenhagen (ITU). Her research focuses on developing data management tools that improve the efficiency of modern data analytics and data science workloads, with an emphasis on spatial workloads. Before joining ITU, she was a postdoctoral researcher at the Technical University of Berlin (TUB) and a junior fellow at the Berlin Institute for the Foundations of Learning and Data (BIFOLD). She earned her PhD in 2019 from École Polytechnique Fédérale de Lausanne (EPFL), where she was advised by Prof. Anastasia Ailamaki. During her doctoral studies, she also spent four months as a visiting researcher at New York University (NYU) with Prof. Juliana Freire. Her dissertation research focused on query processing for spatial and temporal data exploration. She obtained a Diploma M.Eng. degree in Electrical and Computer Engineering from the National Technical University of Athens (NTUA) in 2013.

The BIFOLD Lunch Talk series gives BIFOLD members and external partners the opportunity to engage in dialogue about their research in Machine Learning and Big Data. Each Lunch Talk offers BIFOLD members, fellows and colleagues from other research institutes the chance to present their research and to network with each other.
The Lunch Talk takes place at the TU Berlin. For further information on the Lunch Talks and registration, contact Dr. Laura Wollenweber via email.