Information & Data Science Pilot Projects

The Incubator continues to provide impetus for strengthening information and data-based research at the Association. For instance, the Incubator catalyzes the development of pioneering projects that cross the traditional boundaries between disciplines and research fields. Having initiated five innovative pilot projects in 2017, Helmholtz is strengthening the topic of Information & Data Science in a second call for applications for pilot projects and investing an additional 40 million euros in total in the future of the research.

To the press release

The Incubator continues to provide impetus for strengthening information and data-based research at the Association. For instance, the Incubator catalyzes the development of pioneering projects that cross the traditional boundaries between disciplines and research fields. Having initiated five innovative pilot projects in 2017, Helmholtz is strengthening the topic of Information & Data Science in a second call for applications for pilot projects and investing an additional 40 million euros in total in the future of the research.

Further Information and contact: Dr. Andreas Dietz (DLR), Andreas.Dietz(at)dlr.de

How will the climate develop, how secure is our energy supply, and what chances does molecular medicine offer? The rapidly increasing amount of data offers radically new opportunities to address today’s most pressing questions of society, science, and economy: Data, outcomes and predictions are, however, subject to uncertainties. The goal of the project Uncertainty Quantification is to understand these uncertainties through methods of probability theory, and to include them into research and outreach. The project connects applied researchers from the four research fields Earth & Environment, Energy, Health, and Information among each other and with Helmholtz data science experts, as well as external university partners from mathematics and econometrics.

Further Information and contact: Prof. Dr. Martin Frank (KIT), martin.frank(at)kit.edu & Prof. Dr. Christiane Fuchs (HMGU), christiane.fuchs(at)helmholtz-muenchen.de

 

Pilot Lab Exascale Earth System Modelling  researches specific concepts for Earth system models on exascale supercomputers. So-called extreme events – such as hurricanes caused by climate change as well as droughts or torrential rains – can lead to dramatic changes in our society and the environment. At the same time, current climate models aren’t precise enough to simulate these exact types of events and need to be made capable of working at a much higher resolution. But the computing power of today’s supercomputers cannot simply be increased – among other things, this would consume far too much energy. This means that completely new types of modeling concepts will be required. Researchers and IT experts are working together at PL-EESM to develop the necessary software and new hardware concepts.

Further Information and contact: PD Dr. Martin Schultz (FZ Jülich), m.schultz(at)fz-juelich.de

 

Ptychography is a computational method to use correlated measurements in order to reconstruct an object from diffraction images. Using such a ‘virtual lense’ allows to push microscopic imaging beyond the boundaries of classical optics.

The method recently gained much interest because of the availability of an iterative algorithm to solve the reconstruction problem and sufficient computing capacity to deal with large data sets and high computational demands.

The project embraces the challenge to push ptychography towards routine operation with various radiation sources (X-ray, electrons, XUV light). Towards this aim, optical expertise will be combined with data sciences. Hereby, Ptychography 4.0 follows the Industry 4.0 paradigm in separating data acquisition from processing such that resources will be used most efficiently.

Further Information and contact: PD Dr. Wolfgang zu Castell (HMGU), castell(at)helmholtz-muenchen.de & Prof. Dr. Christian Schroer (DESY), christian.schroer(at)desy.de

 

Satellite technology and in particular GPS- or GNSS-based systems are becoming vital for our society. Plasma density structures in the near-Earth space can significantly influence the propagation of GPS signals and hence influence the accuracy of GPS navigation. Moreover, space plasmas can also damage satellites. To carefully evaluate these effects of the space environment, it is important to develop an accurate model of the plasma density based on a variety of direct and indirect measurements.
In this initial project we will demonstrate how machine learning tools can be used to produce a real-time global empirical model of the near-Earth plasma density based on a variety of measurements. The model that will be developed as a follow-up to this current project will then utilize all available data and will be used by a broad range of stakeholders for GPS navigation and satellite operations.

Further Information and contact: Prof. Dr. Yuri Shprits (GFZ), yshprits(at)gfz-potsdam.de, Dr. Dominika Sörgel (GFZ), dominika.soergel(at)gfz-potsdam.de

 

 

 

Large, complex and high-dimensional data are now ubiquitous in essentially all areas of science and society. Machine learning and AI methods are already highly effective at exploiting such data for the purpose of prediction.

The project SIMCARD will develop novel machine learning tools that are truly robust and reliable and that can go beyond prediction to provide a deeper scientific understanding. In particular, the focus is on new methods for large-scale network modelling and reliable prediction. Designing scalable, principled and interpretable data science approaches is key for providing answers to pressing problems in various application areas. Specifically, the project addresses the fields of data-intensive biomedicine and weather prediction.

Further information and contacts: Melanie Schienle, Melanie.Schienle (at) kit.edu and Sach Mukherjee, sach.mukherjee (at) dzne.de

To solve future grand challenges, data, computational power and analytics expertise need to be brought together at unprecedented scales. Common computing systems exhibit a strong tendency towards centralized structures with disadvantages from a technical, legal, political and ethical perspective, especially regarding security or trust requirements. As an alternative, this interdisciplinary project facilitates the implementation of decentralized, cooperative data analytics architectures by bringing the algorithms to the data in a trustworthy and regulatory compliant way. TFDA addresses the technical, methodical and legal aspects by ensuring trustworthiness of analysis and transparency regarding the analysis in- and outputs. The project validates the results in a federated radiation therapy study and then disseminates the results more broadly.

 

Further information: https://tfda.hmsp.center

Contacts: Mario Fritz, fritz (at) cispa.saarland and Ralf Floca, r.floca (at) dkfz.de

 

Print Version

Contact

  • Photo of Andreas Kosmider
  • Photo of Jacqueline Bender
  • Photo of Dr. Sünje Dallmeier-Tiessen
  • Photo of Lars Mehwald
  • Photo of Susan Trinitz

Your Cookie Preferences

Our website uses cookies necessary for ensuring the technical functionality and accessibility of its online services. We also employ optional cookies to learn more about how you use our website and to optimise our services accordingly. Visit our privacy policy page for more details about cookie usage. There you can change your cookie setting anytime.

I accept the use of cookies.