Hannah Habenicht
Source: https://www.biom.uni-freiburg.de/mitarbeiter/Hannah_en Parent: https://www.biom.uni-freiburg.de/mitarbeiter/dormann/prof.-dr.-carsten-dormann?set_language=en
Hannah Habenicht
Department of Biometry and Environmental System Analysis\ \ Tennenbacher Straße 4, 79106 Freiburg, Germany\ Room 03.059\ \ email: hannah.habenicht@biom.uni-freiburg.de
phone: +49 761 203-3748\ fax: +49 761 203-3751
Research Interests
- Interdisciplinary and Translational Communication
- Life Sciences
- Deep Learning
- Scientific Machine learning
- Process Modeling
- Explainable AI
Curriculum Vitae
| 2023-present | Doctoral researcher in the CRC 1597 'Small Data', Project B02. “Transfer learning for forecasting short environmental time series using process-guided neural networks” | |
| 2020-2023 2020 | MSc Neuroscience, Majoring in Neural Circuits and Behavior. University of Freiburg Germany. Master thesis, Imaging Memory and Consolidation (IMaC) Lab, Department of Neuropsychology Titled: “Shaping memory: the effects of proactive and retroactive contextual demand on memory consolidation”. Laboratory Assistant, Eurofins GeneScan GmbH, Freiburg. | |
| 2015-2020 2018 | BSc, Liberal Arts and Sciences Majoring in Life Science, University of Freiburg, Germany. Bachelor thesis, Institute of Anatomy und Cell Biology, Department of Molecular Embryology Titled: “Investigation into the molecular signalling pathways behind the morphological heterogeneity of reactive astrocytes at the glial scar border”. Research internship at German Aerospace Center (DLR), Department of Gravitational Biology, Cologne, Germany. | |
| 2017-2018 | Year Abroad: Chinese University of Hong Kong, Hong Kong | |
On-going project
https://www.smalldata-initiative.de/projects/b02/
Project summary:
In many fields of science, and particularly in environmental science, process models have been developed to represent our knowledge of the mechanisms underlying fluxes and states. We hypothesize that such process knowledge can substantially improve purely data-driven neural networks in small data settings. Thus, we want to expand approaches for process models in neural networks by augmenting neural networks with existing biophysical process knowledge and using explainable AI to improve process models.