Skip to ContentSkip to Navigation
About us Faculty of Science and Engineering Data Science & Systems Complexity (DSSC) Research Results and Impact

European and nationally funded research

The DSSC and its members have been awarded several grants for their research and for PhD training in Data Science and Systems Complexity.

Data Science and Systems Complexity Doctoral Training Programme: Marie Curie COFUND

Today’s world is a highly complex system that is producing massive amounts of data daily. We can only progress towards urgent global priorities such as sustainable energy, personalized healthcare, safety or the creation of the data-driven economy if we can predict and control the dynamic nature of such systems. This challenge calls for an integrated approach that uses data to understand the behaviour of complex systems and for experts who can handle data and complexity problems for society at large. The DSSC Research Training Programme is a Marie Sklodowska-Curie COFUND action developed at the University of Groningen that will train 10 PhD students for 4 years to be part of the next generation of interdisciplinary data and complexity experts. The research areas of the DSSC COFUND Doctoral Programme are: Adaptive Models & Big Data; Complex Systems & Engineering and Advanced Instrumentation & Big Data. Please visit our website for more information.

Survey Network for Deep Imaging Analysis & Learning (SUNDIAL): Marie Curie ITN

A group of DSSC-researchers from the Kapteyn Institute and JBI have obtained an EU International Training Network to work on Big Data and Galaxy Evolution, with acronym SUNDIAL: Survey Network for Deep Imaging Analysis & Learning. The group will develop new imaging analysis algorithms and techniques, and apply them to some deep and large astronomical datasets in the optical, to study galaxy evolution and the role of the environment. The collaboration, including Reynier Peletier, Michael Wilkinson, Michael Biehl, Kerstin Bunte, Edwin Valentijn, Scott Trager, Peter Barthel, Gijs Verdoes Kleijn and Leon Koopmans in Groningen, includes universities in Spain, France, Italy, Belgium, UK, the Netherlands, Germany and Finland, as well as 5 private companies.

Though Big Data has become common in many domains nowadays, the challenges to develop efficient and automated mining of the ever increasing data sets by new generations of data scientists are eminent. These challenges span wide swathes of society, business and research. Astronomers with their high-tech observatories are historically at the forefront of this field, but obviously, the impact in e.g. commercial applications, security, environmental monitoring and experimental research is immense. The SUNDIAL project aims to contribute to this general discussion by training a number of young scientists in the fields of computer science and astronomy, focussing on techniques of automated learning from large quantities of data to answer fundamental questions on the evolution of properties of galaxies. While these techniques will lead to major advances in our understanding of the formation and evolution of galaxies, SUNDIAL will also promote, in collaboration with industry, much more general applications in society, e.g. in medical imaging or remote sensing. The project consists of astronomers and computer scientists, from academic and private sector partners, to develop techniques to detect and classify ultra-faint galaxies and galaxy remnants in a deep survey of the Fornax cluster, and use the results to study how galaxies evolve in the dense environment of galaxy clusters. With a team of young researchers SUNDIAL will develop novel computer science algorithms addressing fundamental topics in galaxy formation, such as the huge dark matter fractions inferred by theory, and the lack of detected angular momentum in galaxies. The collaboration is unique - it will develop a platform for deep symbiosis of two radically different strands of approaches: purely data-driven machine learning and specialist approaches based on techniques developed in astronomy. Young scientists trained with such skills are highly demanded both in research and business.

PERICO

DSSC co-chair is partner in 4 million euro ETN project PERICO The PERoxisome Interactions and COmmunication (PERICO) research programme, in which Prof. dr. Lambert Schomaker (Artificial Intelligence, Bernoulli Institute BI), DSSC co-chair and member, is a partner, was awarded 4 million euro as a Marie Curie European Training Network. The programme aims at placing peroxisomes in the centre of European science by uncovering how they participate in an intricate cellular interaction and signalling network. Loss of optimal peroxisomal function leads to devastating diseases. Understanding the function of peroxisomes has strong implications for dealing with serious metabolic health problems that range from obesity to malnutrition. Although structurally simple, peroxisomes display an unprecedented variety of functions and are crucial for cell vitality. They are among the last organelles to be discovered (in 1954), explaining why the knowledge on peroxisomes is still relatively weak. PERICO trains 15 Early Stage Researchers (ESRs) at 9 world-leading academic institutions, including 4 medical centres/university hospitals, and 6 non-academic companies, thus forming strong interdisciplinary relations between industry, life sciences and end-users. The principal investigator is prof. dr. Ida van der Klei of the Groningen Biomolecular Sciences and Biotechnology institute (GBB). The participation of DSSC is in the area of applying convolutional neural networks and deep learning for classification of organelles by means of new robotic (pan/zoom) microscopes (supervisor prof. dr. Lambert Schomaker).

Zero-defect manufacturing control systems

Integrating models and real-time data for zero-defect manufacturing control systems DSSC member Bayu Jayawardhana (Engineering and Technology Institute Groningen ENTEG) received an NWO STW “Smart Industry" grant for his project "Integrating models and real-time data for zero-defect manufacturing control systems." For the past decades, the use of feedback and feedforward control systems has been essential in every automated process stage in advanced production systems for fulfilling tight and rigid product specifications at each stage. Yet, such systems cannot handle well natural variations in material properties and process conditions that can lead to waste due to nonconformity with the specifications which, in turn, can cost millions of euros a year in product, labor and energy waste for manufacturers. With the increasingly strict requirements for modern high-tech products, a new intelligent control strategy is needed that can take into account material variations in the complete control system, allow for flexible tolerances at each stage and meet the final product specification. The increasing use of ICT and internet-of-thing sensors in modern manufacturing has opened a new way for the development of novel control systems design that can lead to drastic improvements in production accuracy and will be the focus of this project.

The proposed research program aims at developing novel data analytics and control design methods for zero-defect manufacturing systems based on the complementary use of real-time product, process, as well as, material data and existing process models. In particular, we will firstly develop data analytic tools which will enable us to translate product and material data into process information based also on the use of existing high-fidelity (such as finite-element) process model. Such process information will contain important information on the stage-to-stage variation and product-to-product variation due to material variation and environmental conditions. Based on the process information, we will then develop new control reconfiguration strategies that are able to fine-tune/adapt the existing process control systems, in terms of both feedback and feedforward control systems, in order to compensate for the material and process variations. By using real-time monitoring of the process variation in the control systems, we will be able to adapt all process stages to natural material variation effectively and efficiently.

If successful, the proposed project will provide effective data analytics and control design methods to realize zero-defect manufacturing systems with minimal cost through the intelligent use of ICT and internet-of-thing sensors, recouping millions of euro loss in waste.

Visual Storytelling of Big Imaging Data

DSSC co-chair and member Prof. dr. Jos Roerdink (Computer Science, Bernoulli Institute BI) was awarded a eScience Disruptive Technologies (DTEC) grant for the project "Visual Storytelling of Big Imaging Data" developed with CIT and UMCG. Data produced by imaging systems is ever growing in size and complexity. Extracting, presenting, and communicating information from “big” (large, complex, heterogeneous) imaging data is a fundamental problem, which is relevant in many areas, ranging from medical care to high-tech information systems. The main research question in this project is how to develop IT support for diagnostic and decision-making processes based on large and complex imaging data. The approach is based on developing novel graphics, visualization, and interaction methods for the exploration of imaging data. A key element is the use of storytelling as a means of visual data communication. Visual storytelling is an innovative approach for visual presentation and communication that is especially important in situations where the data analyst is not the same person as the decision-maker, and information needs to be exchanged in an intuitive and easy-to-remember way. Diagnostics in radiology will be the primary use case to test the developed approaches. Because of recent developments in information technology and big data, the focus of radiology is shifting and disruptive technologies are required to allow radiology to position itself as a future-proof specialty in Healthcare.

Optimum control of integrated energy systems

Prof. dr. Kanat Camlibel (main applicant) (Bernoulli Institute BI) and Prof. dr. ir. Jacquelien Scherpen (Engineering and Technology Institute Groningen ENTEG), members of the DSSC steering committee, were awarded funding as part of the Netherlands Organisation for Scientific Research (NWO) Energy system integration - planning, operations and social embedding programme, for their project "Optimum control of integrated energy systems."

Partners: Gasterra and DNV GL. The project studies new algorithms designed to make integrated systems work as efficiently as possible for ‘prosumers’ (consumers who also produce energy) of gas and/or electricity. Security of supply is vital and it is important to make optimum use of the capacity of the gas and electricity grids to guarantee stability.

Funding from NWO: almost € 272,000. Funding from industry: € 63,000. 1 PhD student will work on this project.

Last modified:12 August 2020 11.54 a.m.