Intern
    Data Science Chair

    Deep Learning for Dynamical Systems

    The "Deep Learning for Dynamical Systems" group aims to research and develop specialized deep learning algorithms that address research questions in the natural sciences, in particular the modeling of dynamic systems such as climate systems or bee colonies.

    We focus on learning system representations from the data only. To this end one focus of our research is learning partial differential equation system from data using NeuralPDEs, while another focus is on modeling dynamical systems using transformers.

    Currently, we are modeling elctro-magnetic fields in the MAGNET4Cardiac7T procject and bee behavior in the we4bee and BeeConnected projects.

    Core Research Topics include:

    • Representation Learning
    • Anomaly detection
    • Models for Imbalanced data
    • Modelling physical systems
    • Neural Partial Differential Equations

    Projects

    • AI@Knauf - Using machine learning to analyse and optimize the production of gypsum.

    • TissueNet - Developing machine learning based approaches for single cell analysis 

    • BeeConnected - Learning and researching with sensor data from smart beehives.

    • MAGNET4Cardiac7T - Predicting Electromagnetic Fields within a patient resting inside a MRI-Scanner

    Concluded Projects

    • BigData@Geo - Developing machine learning based approaches for regional environmental prediction models.

    • EveryAware - A project for collaborative collection of environmental sensor data with low cost sensors.

    • p2Map - Learning understandable maps of air pollution leveraging a combination of low-cost mobile sensors.

    Publications

    Here is a list of selected publications.

    • Anomaly Detection in Beeh...
      Anomaly Detection in Beehives using Deep Recurrent Autoencoders. Davidson, Padraig; Steininger, Michael; Lautenschlager, Florian; Kobs, Konstantin; Krause, Anna; Hotho, Andreas. In Proceedings of the 9th International Conference on Sensor Networks (SENSORNETS 2020), pp. 142–149. SCITEPRESS – Science and Technology Publications, Lda., 2020.
    • Participatory sensing, op...
      Participatory sensing, opinions and collective awareness. Loreto, Vittorio; Haklay, Mordechai; Hotho, Andreas; Servedio, Vito C. P.; Stumme, Gerd; Theunis, Jan; Tria, Francesca. Springer, 2017.
    • Collective Sensing Platfo...
      Collective Sensing Platforms. Atzmueller, Martin; Becker, Martin; Mueller, Juergen. In Participatory Sensing, Opinions and Collective Awareness, pp. 115–133. Springer, 2017.
    • Participatory Patterns in...
      Participatory Patterns in an International Air Quality Monitoring Initiative. Sîrbu, Alina; Becker, Martin; Caminiti, Saverio; De Baets, Bernard; Elen, Bart; Francis, Louise; Gravino, Pietro; Hotho, Andreas; Ingarra, Stefano; Loreto, Vittorio; Molino, Andrea; Mueller, Juergen; Peters, Jan; Ricchiuti, Ferdinando; Saracino, Fabio; Servedio, Vito D. P.; Stumme, Gerd; Theunis, Jan; Tria, Francesca; Van den Bossche, Joris. In PLoS ONE, 10(8), p. e0136763. Public Library of Science, 2015.
    • Awareness and learning in...
      Awareness and learning in participatory noise sensing. Becker, Martin; Caminiti, Saverio; Fiorella, Donato; Francis, Louise; Gravino, Pietro; Haklay, Mordechai (Muki); Hotho, Andreas; Loreto, Vittorio; Mueller, Juergen; Ricchiuti, Ferdinando; Servedio, Vito D. P.; Sirbu, Alina; Tria, Francesca. In PLOS ONE, 8(12), p. e81638. 2013.