Dr.-Ing. Ocean (Anna) Krause

I received my Diploma in Electrical Engineering from the Technical University Dresden in 2009. In the same year, I joined Prof. Erich Barke's Electronic Design Automation Group at the Institute of Microelectronic Systems at the University of Hannover. I researched methods for automatically generating behavioral models of analog circuits with parameter variations. My thesis is on the adaptation of Support Vector Machines to generate models with interval-valued parameters. I received my doctorate degree from the University of Hannover in 2019. In 2016, I joined Robert Bosch GmbH Corporate Research as a research engineer. I joined the Chair X (Data Science) in 2019 as a post-doctoral researcher, where I am currently leading the Deep Learning for Dynamical Systems Group.

I am currently doing research in Environmental Sensing and Time Series Analysis. I am interested in furthering methods to enhance existing physics-based models - such as meteorological models, and to further our understanding based on data obtained by sparse and dynamic sensor networks.

Current Projects:

• SMART-TWIN
• BigData@Geo2

• Introduction to Algorithms and Data Structures: WS2020 WS2019
• Data Mining: SS2021 SS2020
• Seminar Selected Topics in Machine Learning SS2022 WS2022 SS2023
• Lecture: Machine Learning for Times Series Analysis and Anomaly Detection WS2023

• Organizer for the workshop "Neuro-Explicit AI and Expert-informed Machine Learning for Engineering and Physical Sciences" at ECMLPKDD2023
• PC member for ECMLPKDD 2021, 2022, 2023 (Research Track)
• PC member for the MIDAS workshop 2021, 2022
• Reviewer for Volkswagen Stiftung

• Best ML Innovation Award: "Deep Learning for Climate Model Output Statistics", Michael Steininger, Daniel Abel, Katrin Ziegler, Anna Krause, Heiko Paeth, Andreas Hotho at Tackling Climate Change with Machine Learning Workshop at NeurIPS 2020 (link)
• Best Student Paper Award: "Evaluating the multi-task learning approach for land use regression modelling of air pollution", Andrzej Dulny, Michael Steininger, Florian Lautenschlager, Anna Krause, Andreas Hotho at FAIML 2020
• Best Paper Award: "Financial Fraud Detection with Improved Neural Arithmetic Logic Units" by Daniel Schlör, Markus Ring, Anna Krause, Andreas Hotho on the Fifth Workshop on MIning DAta for financial applicationS Co-Hosted by ECML- PKDD 2020