Find your Host Supervisor

Researcher profiles

Scroll down and discover the profiles of potential Host Supervisors at different Helmholtz Centers that would like to welcome a HIDA Trainee for a short term research stay in their group. Get to know on which kind of projects these researchers are currently working on, how you can contribute and what you can learn from their specific research approaches.

    

Jana Schor

Helmholtz Centre for Environmental Research - UFZ: Data Science group at the department of bioinformatics

Short summary of your group's research: The new research group Data Science under the supervision of Dr. Jana Schor focuses on Data Science methods, like Machine Learning and Data Integration, to boost the extraction of knowledge from human and environmental health Big Data sets. We apply and develop respective computational methods on public and in-house data sets, mainly in the field of environmental and health research, to generate novel hypotheses, and make predictions on a large scale. To increase the credibility of our AI approaches we introduce explainability and methods for the quantification of uncertainty into our applications. We further attach great importance on the principles of reproducible research.           

What infrastructure, programs and tools are used in your group? High performance computing infrastructure at the UFZ and storage as well as data integration capabilities of the European Open Science Cloud; Software is developed in R, and Python, and is provided in Singularity containers and/or in public gitlab repositories at the HZDR; for training our deep learning models or other computationally expensive calculations we use the GPUs that are integrated into our servers and the HPC system.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? A participant of the HIDA Trainee Network will learn to organize his/her data analysis or software development projects according to clear data management plans and with SOPs that allow shared and joint code development, respective documentation, and the reproducibility of research results. We offer to share our expertise in the application of machine learning approaches and respective data pre-processing strategies. Further, we are experienced in story telling with data and offer to teach respective principles to the participants. We welcome participants with a background in machine learning who are interested in the applications of their methods to our research questions, e.g. in the field of predictive toxicology. We also invite researchers with a chemistry, (eco-)toxicological or biological background who might inspire us with interesting research questions and who are willing to learn helpful data science strategies.

    

Ulisses Nunes da Rocha

Helmholtz Centre for Environmental Research - UFZ: Microbial Data Science at the department of Environmental Microbiology

Short summary of your group's research: Our group strives to assess environmental health of terrestrials and man made environments by predicting how resilient/stable microbial communities are to disturbances. A special emphasis is put on the development of concepts and theories to scale microbial interactions to the real diversity found in nature. The key research topics  of the Microbial Data Science group are based on genetic potential of microbial communities, multi-omics integration and  predictive biology. Currently these topics cover:

  1. Use of (in silico) mock microbial communities to test microbial ecology theories;
  2. From microbial 'Big Data' to novel ecological concepts and theories;
  3. Predictive analytics in microbiology, microbial ecology and environmental microbiology.          

What infrastructure, programs and tools are used in your group? We use the High-Performance Computing (HPC) Cluster EVE as our main computational resource. We develop and use tools to analyze, resolve and interpret multi-omics data, specially metagenomes. Eg.: tools for the recovery of multi-domain genomes (prokaryotes, viruses and eukaryotes) from metagenomic data. As programming languages, we mostly use Python, R, Bash and Perl to handle and process microbial big data.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? A participant from the HIDA Trainee Network will learn how to download, process and interpret metagenomic data using both publicly available datasets as well as in-house generated data. Further, the participant will work with hands on experimental design and predictive analytics using omics data. We welcome participants from a broad range of fields (e.g. microbiology, ecology, computer/data science) that are eager to learn and/or expand their knowledge in computational biology/data science.

    

Martin Frank

Karlsruhe Institute of Technology (KIT):  Computational Science and Mathematical Methods

Short summary of your group's research: The research group Computational Science and Mathematical Methods (CSMM) under the supervision of Prof. Dr. Martin Frank is an interdisciplinary research group working on different challenges in mathematical modeling.  We are unified by our interest in method-oriented mathematics, in mathematical modeling inspired by applications, and in the didactics of mathematical modeling. Our research focuses on bringing modern mathematical techniques such as modeling, simulation, optimization, inverse problems, uncertainty quantification, and machine learning/artificial intelligence into the real-world. Furthermore, we take an interest in kinetic theory, developing models, numerical methods and software implementations and combining them with the aforementioned techniques.

What infrastructure, programs and tools are used in your group? Among other things, we use the modern high performance computing infrastructure of KIT, namely bwUniCluster.  We develop software and tools in Julia, Python, C++ and Matlab, depending on the project. We employ several project specific software stacks for uncertainty quantification and medical image processing.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? As an interdisciplinary research group, we offer a lot of possibilities for a participant of the HIDA Trainee Network and many different interesting projects to support. A mathematically oriented participant could learn interesting aspects about machine learning based numerical methods for kinetic equations. Furthermore, the group offers projects in mathematical methods for uncertainty quantification and dynamical low rank.

An application-oriented participant may find interest in the project about neural network based medical image processing or uncertainty quantification in radiation therapy.

A participant, who is interested in teaching, can learn about bringing modern and method oriented mathematics to the classroom and can work on applied mathematical projects with high school students.

We develop an open source simulation toolkit for radiation therapy planning, which also offers the possibility to engage and participate. Detailed descriptions of our projects can be found on our group homepage.

   

Peter Sanders

Karlsruhe Institute of Technology (KIT):  Algorithm Engineering

Short summary of your group's research: Efficient algorithms and data structures are the basis of all nontrivial computer applications. Algorithmics – the systematic development of efficient algorithms – is therefore crucial for transforming technological potential into applications that are important for technology, business, science, and our daily lives. At the institute of theoretical informatics, our group focuses on the "basic toolbox" of methods that are needed in many applications, e.g., sorting, hash tables, index data structures, route planning in graphs, or partitioning graphs. A particular focus is on parallel algorithms ranging from shared-memory machines to the largest supercomputers. Here, basic tools we develop include load balancing, collective communication primitives, and (hyper)graph partitioning.

Helmholtz researchers outside computer science might profit from a cooperation with our group if improved basic tools can remove performance bottlenecks in their applications.

What infrastructure, programs and tools are used in your group? C++, MPI, Intel TBB, OpenMP. Our own software libraries for sorting, (compressed) hash tables, search trees, (hyper)graph partitioning, route planning,... Various parallel computers ranging from shared-memory machines to large supercomputers (e.g. SuperMUC-NG).

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? 

Learn: algorithm engineering (i.e., design, analysis, implementation and experimental evaluation as a holistic process), understanding of scalability issues. Use of our techniques and software.

Support: Develop improved basic algorithmic tools with us. Engineer you application with us using our techniques, algorithms, and software libraries. A goal would be to have a prominent joint publication.

   

Pascal Friederich

Karlsruhe Institute of Technology (KIT): Artificial Intelligence for materials science (AiMat), Department of Informatics

Short summary of your group's research: The AiMat group works on the development and application of AI and machine learning (ML) methods for materials science and chemistry. Focus topics are (graph) neural networks for the prediction of molecular and materials properties, the combination of interpretable AI methods, ML-enhanced simulations and automated experiments to autonomous materials acceleration platforms, and generative models for inverse materials design.

  

What infrastructure, programs and tools are used in your group? 

Infrastructure: HPC systems as BWUniCluster and HoreKa
Programs: Python and machine learning libraries, as well as quantum chemistry simulations

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?  We welcome participants with either a background in machine learning and methods development, who are interested in applying the models to interesting scientific questions, or participants with a background in materials science/chemistry/physics, who want to learn more about machine learning and teach us about their application areas!

    

Jan Cermak

Karlsruhe Institute of Technology (KIT):  Satellite Climatology

Short summary of your group's research: We focus on the development, validation and application of geophysical remote sensing techniques, with special attention to the Earth surface - atmosphere interface. Topics of special attention include cloud processes, air pollution, land-surface temperature and interactions between the land surface and lower atmosphere. Our methods are primarily remote sensing and machine learning.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? Collaboration is at the core of our approach to research. We can offer the opportunity to learn in this exchange about our topics and methods. KIT is one of the most exciting locations for atmospheric research, with world-class infrastructures, several seminar series and numerous project links to other institutions around the world. You will become part of this environment.

   

Jörg Meyer

Karlsruhe Institute of Technology (KIT):  Data Analytics, Access and Applications

Short summary of your group's research: The department Data Analytics, Access and Applications (D3A) at the Steinbuch Centre for Computing (SCC) performs research in applied Artificial Intelligence engineering, contributes to the European Open Science Cloud, has in-depth expertise in federated authentication and authorization infrastructures, and works on joint research of computer scientists and researchers from the field climate and environment. Recently, we launched a team working on the prospering field of Quantum Computing with a focus on hybrid quantum-classical machine learning algorithms. 

What infrastructure, programs and tools are used in your group? Depending on the topic we use various programming languages and computing environments such as high performance computing clusters. For many challenges Python turned out to be the first choice.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? As a candidate you will be part of our lively quantum computing team where you will gain or deepen your understanding on different aspects of quantum machine learning, our current research as well as algorithmic methods. You can further learn state-of-the-art software development methods by supporting us in extending and developing scientific open source software for quantum computing.
You can complement our interdisciplinary team by generalizing and evaluating our methods based on your own background and data and thereby enhance existing activities or even kickstart new activities.
Depending on your interests you can get an overview on other recent research topics in D3A and other research departments at SCC.

   

Uwe Ehret

Karlsruhe Institute of Technology (KIT):  Institute of Water and River Basin Management IWG

Short summary of your group's research: Our group has a wide range of hydrology-related interests comprising conceptual and physically based hydrological modeling, ecohydrology, application of thermodynamic principles to hydrology, data-infrastructures and data-based learning. In the context of HIDA, especially the latter topic is of interest: My colleague Ralf Loritz and I focus on applying machine-learning approaches to hydrological modeling,  and applying concepts from information theory for both hydrological system analysis and as a basis for building hybrid hydrological models merging information from data and knowledge.

What infrastructure, programs and tools are used in your group? We have developed and use a range of open-source Matlab- and Python-based tools for analysis and modeling in hydrological and geostatistical contexts. See more on Link.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? 

What you can learn from us:

  • Applying state-of-the-art tools for supervised and unsupervised learing in hydrological settings
  • Applying state-of-the-art machine-learning tools for hydrological forecasting and prediction
  • The beauty and generality of concepts from information theory, and how they can be used for hydrological analysis and model building

What we can learn from you:

  • A fresh look and feedback on what we do
  • New insights into our methods by applying them to your data and problems
  • Learn about alternative methods

   

Annika Bande

Helmholtz-Zentrum Berlin für Materialien und Energie (HZB): Young Investigator Group Theory of Electron Dynamics and Spectroscopy

Short summary of your group's research: The electronic Schrödinger equation encodes the excited states of any material and their interaction with light may it be in electron dynamics or spectroscopy. We solve the equations in particular for nanomaterials accounting for their chemical environment. Particular interest lies in employing the recent methods of data science and quantum computation along with the traditional theories.

What infrastructure, programs and tools are used in your group? Different commercial and self-written quantum chemistry codes            

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? Learn: Questions from the domain science quantum chemistry to data science, in particular handling of scarce data. Cutting-edge method development. Support: Overview knowledge on data science and experience in formulating questions properly for a data-driven solution.

   

Altuna Akalin

Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC): Bioinformatics and Omics Data Science Platform

Short summary of your group's research: We have a broad interest in gene regulation, specifically transcriptional regulation and association of transcriptional regulation with epigenomics. We are aiming to use data intensive computational methods to uncover patterns in gene regulation relating to cell differentiation and complex diseases.            

What infrastructure, programs and tools are used in your group? HPC, statistical and machine learning tools implemented in Python or R

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? Participant can learn domain specific data processing techniques and provide support in machine learning applications.

    

Laleh Haghverdi

Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC): Berlin Institute for Medical Systems Biology (BIMSB), Computational methodologies and omic analytics

Short summary of your group's research: We are a computational biology group working with a range of single-cell omic data modalities including proteomics, transcriptomics, epigenetics and genomics to study biological systems such as development, haematopoiesis or leukaemic stem cells and their niche.Establishment of efficient computational methodologies for analysis of large single-cell omic data sets, resolution of complex lineage trees, data integration and interpretation across multiple modalities and assays as well as mathematical formulation of the applied methods are of central interest in the group.            

What infrastructure, programs and tools are used in your group? Python, R, computational tools for single-cell data analysis

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? Hight-throughtput measurements of molecular states at the single-cell level are today accessible for biological and clinical studies, thanks to new and still evolving technological developments. Located in the cool central Berlin district, we are an interdisciplinary group trained in physics, mathematics, bioinformatics and molecular biology working together to address several aspects of computational analysis of such newly emerging datasets. We are interested in extending our machine learning and data science collaborations and contacts.

    

Pavlo Lutsik

German Cancer Research Center (DKFZ): Division of Cancer Epigenomics, Computational Cancer Epigenomics research group

Short summary of your group's research: We develop computational methods for the analysis of tumour-derived epigenomic data. One major research focus is reference-free deconvolution of cell mixture-derived DNA methylation profiles, for which we proposed original NMF-based solutions and workflows (Lutsik et al, Genome Biology, 2017; Scherer et al., Nat Protocols, 2020).  We continue this research using state-of-the-art machine learning approaches. We furthermore create user-friendly analysis tools for the epigenome analysis (Assenov et al., Nat Methods, 2014; Müller et al., Genome Biology, 2019; Mayakonda et al., Bioinformatics, 2020).  Finally, in collaboration with our colleagues at DKFZ we perform comprehensive epigenetic characterisation and cell-of-origin search in complex tumour entities, including prostate cancer (Gerhäuser et al, Cancer Cell, 2018), various types of  leukaemia (Wierzbinska et al., Genome Med, 2020; Mayakonda et al., Science Transl. Med), and a rare bone cancer entity, giant cell tumour of bone (Lutsik et al., Nat Commun., 2020).

What infrastructure, programs and tools are used in your group? 

Methodologically we explore the extensions of NMF, as well as novel deep-learning  methods, such as variational autoencoders. Our major collaborative platform is statistical language R, which is most widely used in bioinformatics. Project-dependent, we also employ python and other general and domain specific programming languages including Java and C++. We enjoy the powerful Linux-based computing infrastructure available at DKFZ, that includes modern HPC clusters and clouds.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? We can guarantee that you gain first-hand experience with state-of-the-art computational cancer biology. We look forward to applications from curious and original thinkers, who would be willing to apply classical and novel machine learning methods to non-standard problems, which can have direct benefits for cancer patients. Previous expertise with biological data analysis is not a must.

   

Klaus Maier-Hein

German Cancer Research Center (DKFZ): Division of Medical Image Computing

Short summary of your group's research: The Division of Medical Image Computing (MIC) pioneers research in machine learning and information processing in the context of image data analytics. We pursue cutting-edge developments at the core of computer science, with applications in but also beyond medicine. We are particularly interested in techniques for semantic segmentation and object detection as well as in unsupervised learning and probabilistic modelling.

What infrastructure, programs and tools are used in your group? 

  • Python Software Framework / Pytorch / Phabricator
  • A GPU cluster at DKFZ tailored to specific needs, ranging from nodes with RTX 2080ti all the way up to Nvidia’s DGX systems
  • The DKFZ has an Openstack cluster in which you can instantiate virtual machines for CPU heavy workloads.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? At MIC we pursue cutting-edge developments at the core of computer science, with applications in but also beyond medicine. We believe a sophisticated research software system and infrastructure are key for methodological excellence, for example to facilitate highly scalable data analysis in a federated setting. In cooperation with numerous (clinical) partners, we work on the direct translation of the latest machine learning advances into relevant clinical applications. Depending on the specific interests of the participant of the HIDA training exchange many interesting and challenging aspects could be addressed. Please find a list of ongoing research project in the department on our website in the "research" section.

   

Michael Bussmann

Helmholtz-Zentrum Dresden-Rossendorf (HZDR): Center for Advanced Systems Understanding (CASUS), Görlitz

Short summary of your group's research: The Center for Advanced Systems Understanding is a new center working in the field of data-driven systems science.
We strive to understand complex systems in an interdisciplinary way using newest digital technologies.
From modelling the formation of complete organisms from a single cell to studying the interplay between ecosystems and biodiversity, from understanding what exoplanets look like to working on the mobility of the future, CASUS provides a diverse and welcoming research culture. 

What infrastructure, programs and tools are used in your group?

We provide access to a large HPC systems for both high performance compute simulations and large-scale AI. We have expertise in high performance computing, scalable AI, human-machine interaction, and strive for the development of professional research software and solutions. We have access to some of the largest compute resources on the planet.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?  Trainees have a large variety of options, from learning High Performance Computing (including GPU and FPGA computing) to newest developments in AI (physics-informed NN, Invertible NNs, Normalizing Flows, ...), from applied mathematics and data science foundations to using their skills for a variety of applications in physics, ecology, digital health, autonomous systems, cyber security, earth systems science and more.

    

Christian Feiler

Helmholtz-Zentrum Hereon: Department of Interface Modelling at the Institute of Surface Science

Short summary of your group's research: The research activities at the Institute of Surface Science revolve around the development of ultra‐light‐weight materials and surface protection technologies for the application areas air and ground transportation, infrastructures, regenerative medicine, as well as energy storage and functional materials. Gaining control over surface reactivity characteristics and a reliable prediction of service-life aspects of the employed materials are prerequisites to unlock their full potential in the respective application areas. In this context, we utilise information derived from multiscale simulations, experimental investigations in labs and field data from industrial end-users to gain a comprehensive insight into the material behaviour and employ a variety of supervised and unsupervised machine learning techniques for the discovery of effective additives prior to experimental testing as well as to predict how materials and structures behave during their service-life after exposure to the environment with focus on a sustainable circular economy.

What infrastructure, programs and tools are used in your group? Access to Hereon’s HPC Cluster, HPC workstations in the group for less demanding jobs, Several simulation software packages (DFT, MD, FEM) and tools to generate molecular descriptors (alvaDesc, rdkit), Python-based machine learning workflows.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?  

Our offer:

  • Insights into material science with focus on materials degradation and corresponding corrosion mitigation strategies.
  • Techniques to generate molecular descriptors for quantitative structure-activity/property relationship models and approaches to identify features that are relevant to the chosen target property as well as subsequent model development.
  • Opportunity to validate the robustness of your machine learning model(s) directly with our experimentalists who provide the training data.  

Your support:

  • You could either apply your machine learning knowledge to our existing training data or shape a new project together with our interdisciplinary team with focus on corrosion mitigation and/or predictive maintenance.
  • You could employ your experience in materials modelling to generate additional input features for our predictive models.
  • You could help us to develop tools that can be utilised by end-users without any domain expertise

   

Paul Jerabek

Helmholtz-Zentrum Hereon: Group for "Modeling of Hydrogen Storage Materials" at the "Institute of Hydrogen Technology"

Short summary of your group's research: We perform state-of-the-art multi-scale simulations of hydrogen storage materials, e.g. interstitial metal hydrides or complex hydride systems. For that, we develop digital workflows bridging the atomistic scale with the mesocopic regime by coupling accurate ab-initio calculations with thermodynamic modeling and phase-field simulations. Our set out goal is to be able to understand and accurately predict materials properties as independently from experimental input as possible.

What infrastructure, programs and tools are used in your group? We have access to Hereon's own HPC cluster (more than 160 nodes with 48 CPUs/node) that we utilize for running various molecular and periodic quantum chemical program packages (VASP, QuantumEspresso, CASTEP, ORCA, Gaussian etc.)

Furthermore, we use open-source software to perform thermodynamic modeling (OpenCALPHAD) and phase-field simulations (FiPy, MOOSE).

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?  

What you can learn in our group:

  • You will be able to gain or deepen your understanding in quantum chemical methods like DFT or AIMD for structural optimization, calculation of reaction energies and pathways and prediction of spectroscopic properties
  • You will learn how to perform thermodynamic modeling to predict phase diagrams for multi-component systems via an ab-initio assissted CALPHAD methodology
  • You can be trained in utilizing phase-field simulations for prediction of microstructure evolution and kinetic properties of materials on the mesoscale

How you can support us:

  • You can complement our team by working with our established methodologies on your own project on the topic of hydrogen storage materials
  • You can help with automatizing and streamlining some of our scale-bridging, digital workflows
  • You can kickstart our planned activities for utilizing machine-learning techniques for some of our computational methods

   

Jochen Küpper

Deutsches Elektronen-Synchrotron DESY: Controlled Molecule Imaging (Photon Service)

Short summary of your group's research: We develop innovative methods to obtain full control over large molecules and nanoparticles. These methods and the created controlled samples are exploited in fundamental physics and chemistry studies to unravel the underlying mechanisms of chemistry and biology by watching molecules at work. This is coupled with advanced experimental control and data acquisition software, including on-the-fly data reduction, as well as theoretical and computational physics – both utilizing machine learning approaches for improved performance.

What infrastructure, programs and tools are used in your group? 

Have a look on our website.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? Machine learning in theoretical physics and quantum chemistry and in real-time data reduction – benefit from current expertise and improve our approaches.

  

Thomas White

Deutsches Elektronen-Synchrotron DESYPhoton Science, CFEL Coherent Imaging Division

Short summary of your group's research: We are developing computational tools for processing large crystallographic datasets consisting of many hundreds of thousands of individual frames.  Recently, we are moving towards real-time data processing, with the aim of making the data analysis step "disappear" - becoming part of the data acquisition process.  Our main product embodying this work is the free and open source "CrystFEL" software package.

   

What infrastructure, programs and tools are used in your group? 

Infrastructure: Gitlab, DESY "Maxwell" cluster

Tools: HDF5, SLURM, GSL, OpenCL, ZeroMQ, MessagePack, CMake, Meson, GTK and more

Languages: C/C++, Python, Lisp and others         

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? As well as working with large-scale accelerator-based photon facilities (PETRA III and European XFEL, plus other facilities worldwide), you would gain insight into developing a widely-used (>100 worldwide users) domain-specific software package.  For instance, how to balance the implementation of cutting-edge scientific methods with other considerations such as stability and reliability.  During your stay, you could contribute (for example) by experimenting with a new way of processing data, speeding up existing processing methods, or implementing one of the many requested features in CrystFEL.

Gabriele Cavallaro

Forschungszentrum Jülich: Jülich Supercomputing Centre (JSC)       

Short summary of your group's research: The joint research group ''High Productivity Data Processing (HPDP)'' at JSC and University of Iceland is highly active in developing parallel and scalable machine (deep) learning algorithms for remote sensing data processing and many other types of applications (i.e., medical research and retail sectors).  The main backbone of the research group is the large number of PhD students that are jointly supervised with the University of Iceland. Furthermore, the HPDP works actively with the Cross-Sectional Team Deep Learning (CST DL) and the Helmholtz AI consultant team at JSC.

What infrastructure, programs and tools are used in your group? By being located at JSC, HPDP can rely on HPC technologies with MPI, OpenMP and CUDA (with TensorFlow, Keras, pyTorch, Chainer, Horovod) but also on innovative quantum computing systems.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? Learn how data intensive computing approaches have become indispensable tools to deal with the challenges posed by applications from a diverse range of applications.

    

Timo Dickscheid

Forschungszentrum Jülich: Institute of Neuroscience and Medicine Structural and functional organisation of the brain (INM-1) - Big Data Analytics Group (BDA)

Short summary of your group's research:  The Big Data Analytics group in Jülich develops software and methodology to build a microscopic resolution 3D model of the human brain, which includes detailed information about distributions of neuronal cells and nerve fibers, and microstructurally defined 3D maps of brain areas. This requires microscopic imaging and analysis of large quantities of histological brain sections at high throughput, leading to image datasets at the Petabyte scale.

  

At the intersection of neuroinformatics, computer vision and artificial intelligence (AI), our research addresses

  • Data and workflow management for high throughput microscopic imaging,
  • Machine learning and computer vision algorithms for biomedical image analysis on high performance computers,
  • Software development for structured access to large image datasets and interactive 3D exploration of high-resolution brain atlases over the web.

What infrastructure, programs and tools are used in your group?  The trainee will be part of the local Helmholtz AI unit in Jülich. Our data management and image analysis workflows run on a distributed environment which includes Jülich’s modular high-performance computing systems. Image acquisition of whole-brain sections at micrometer resolution is performed on a high throughput microscopy facility. Outputs of our research are typically integrated with the human brain atlas hosted in the European research infrastructure EBRAINS, to which we contribute key developments. Most of our software is implemented in Python. Image analysis and machine learning approaches use common Deep Learning frameworks, typically PyTorch or Tensorflow.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?

A trainee in our group can learn about

  • biomedical computer vision, especially processing and analysis of high resolution image data using state of the art AI methods
  • distributed workflow management and parallel processing of big image data on supercomputers
  • neuroinformatics.

A trainee can support our group with practical experience in machine learning approaches for image analysis from the point of view of another application domain. A trainee could also contribute with experience in inverse modelling, simulation, or computer graphics.

   

Simon Eickhoff

Forschungszentrum Jülich: Brain and Behaviour (INM-7)

Short summary of your group's research: We develop and apply novel methods to better understand  the organization of the human brain and to relate it to behavioral phenotypes in healthy and as biomarkers in clinical populations. To do so, we capitalize on machine learning approaches. In addition to these scientific objectives, we also develop open access methods and tools for data management and reproducible research.           

What infrastructure, programs and tools are used in your group? Python, R, MATLAB, HPC, machine learning, neuroimaging

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?  A HIDA trainee can choose from diverse topics from machine learning, data management to biomarker discovery. For technically oriented trainees we offer opportunities to contribute to our growing set of tools. For application-oriented trainees we offer participation in ongoing projects to uncover brain-behavior relationships.

    

Fabio Fiorani

Forschungszentrum Jülich: Juelich Plant Phenotyping Center/Institute of Bio- and Geosciences, IBG2: Plant Sciences

Short summary of your group's research: We focus on the application and development of high-throughput, non-invasive phenotyping methods for screening of plant shoot and root productivity traits. In our group teams of plant biologists, engineers and image processing specialists cooperate to realize screening methodologies for shoot and root growth and architecture combined with physiological measurements of plant performance and plasticity to environmental challenges. Interpretation of results requires the evaluation of multi-dimensional data structures which include dynamic changes of plant phenotypes over time, environmental and imaging sensors data.

What infrastructure, programs and tools are used in your group? We have developed and operate a unique set of automated experimental platforms to analyze plant phenotypes in a minimally-invasive fashion, please click here to learn more.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?  Participants to the HIDA Trainee Network would benefit from learning: a) methodologies for high-throughput screening in plants; b) data analyses and visualization of complex data sets; c) experimental designs for plant phenotyping.  HIDA Trainee Network participants would support our continued efforts in improving and automating data analyses using existing data stored in several institutional databases. 

   

Eric von Lieres

Forschungszentrum Jülich: Modeling and Simulation @ Institute of Bio- and Geosciences 1 

Short summary of your group's research: We provide our local colleagues and the scientific community with state-of-the-art models, algorithms and software. Current challenges in strain selection and optimization as well as process analysis and development are addressed in a strongly data-driven fashion in close collaboration between theory, simulation and experiment. Typical projects involve data analysis, model calibration or training, uncertainty analysis, experimental design. Model predictions are applied for testing hypotheses and focusing experimental work.             

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?  Many projects require advanced numerical methods and high-performance computing, in particular when machine learning/ artificial intelligence, Monte Carlo simulations, global optimization or CFD simulations are applied. We develop and maintain dedicated software packages, most of which are published as open source code (https://github.com/modsim).

    

Andreas Lintermann

Forschungszentrum Jülich: Simulation and Data Laboratory "Highly Scalable Fluids & Solids Engineering" (SDL FSE), Jülich Supercomputing Centre (JSC), Institute for Advanced Simulation (IAS)

Short summary of your group's research: The SDL FSE's research focuses, amongst others, on lattice-Boltzmann methods, artificial intelligence, high-performance computing, heterogeneous computing on modular supercomputing architectures, high-scaling meshing methods, efficient multi-physics coupling strategies, and bio-fluidmechanical analyses of respiratory diseases. Furthermore, the SDL FSE aims at supporting users from engineering sciences who have already developed parallel codes but need support for the use of massively parallel systems regarding high scalability, memory optimization, programming of hierarchic computer architectures, and performance optimization on compute nodes.  

What infrastructure, programs and tools are used in your group? The group mainly uses the high-performance computing (HPC) systems available at JSC for its various simulation applications. As a simulation code, a massively parallel multi-physics framework , jointly developed with the Institute of Aerodynamics and Chair of Fluid Mechanics, RWTH Aachen University, is employed. The big data outputs generated by the simulation tools are post-processed, e.g., by in-house developed tools, ParaView, machine-learning algorithms, or by Jupyter-based scripts.        

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? The student will have access to the latest supercomputing hardware installed at JSC and will learn from the experts in the group to develop, adapt, and optimize simulation codes. He or she will support the member of the SDL FSE in running large-scale simulations on the production HPC machines at JSC and post-process the data to gain new insights to physical phenomena in the realm of fluid mechanics. Furthermore, the student will be able to learn how research in a European Center of Excellence in Exascale Computing is performed and has the opportunity to contribute to the corresponding cutting-edge research in bringing AI technologies along various use-cases to exascale.

   

Philipp Lohmann

Forschungszentrum Jülich: Institute of Neuroscience and Medicine, Medical Imaging Physics (INM-4): Brain Tumor Group

Short summary of your group's research:  The research of the Brain Tumor Group within the Institute of Neuroscience and Medicine focuses on multimodal imaging in patients with brain tumors, with particular emphasis on amino acid PET in combination with advanced high-field and ultra-high-field MRI. In addition to the development and evaluation of novel PET tracers and PET/MRI methods, the potential of advanced image analysis such as radiomics and deep learning for patients with brain tumors is explored. A major goal of our research is the correlation of imaging findings and radiomics with local neuropathology and histomolecular markers, for which the close collaboration with the surrounding university hospitals in Aachen, Bonn, Cologne, Düsseldorf, and others, is extremely valuable and furthermore offers a high potential for verification and translation of research results into the clinic.

What infrastructure, programs and tools are used in your group? Amino acid PET, advanced MRI, ultra-high-field MRI, hybrid MR/PET, Python, Pyradiomics, PyTorch, LifeX, PMOD, FSL, HDBET, HDGLIO, ITK-SNAP, OsiriX, Matlab, High performance computing, etc.

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? 

  • Amino acid PET in combination with advanced, ultra-high-field MRI in patients with brain tumors
  • Advanced image analysis including static and dynamic amino acid PET and MRI
  • Feature-based as well as deep learning-based radiomics based on PET and MRI in patients with brain tumors
  • Correlation of PET/MRI imaging findings and radiomics with local neuropathology and histomolecular markers
  • Establishment of an imaging database of amino acid PET imaging in patients with brain tumors for advanced image analysis

   

Wolfgang Wiechert

Forschungszentrum Jülich: IBG-1: Biotechnology 

Short summary of your group's research: Modeling, Simulation and Data Analytics in the fields of systems metabolic engineering and bioprocess development: Cell and process modeling, Omics and bioprocess data processing, process parameter estimation, microbial image analysis, digitalization in lab automation     

What infrastructure, programs and tools are used in your group? Hosting CADET and 13CFLUX2 software systems. Using and developing C++, python, Matlab toolboxes. High performance parameter estimation in complex systems, MCMC for parameter estimation and multi model analysis. Deep learning for image analysis. Supercomputing applications in process simulation.        

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group? 

Wanted: Expertise in cutting edge Bayesian methods, image analysis and high performance computing

Offering: Challenging realistic problems from the above mentioned fields

   

Dieter Weber

Forschungszentrum Jülich: Ernst-Ruska-Centrum

Short summary of your group's research: We are developing solutions for high-performance data processing, data management and automation in electron microscopy. This includes software like here as well as IT systems and infrastructure. Since modern detectors for electron microscopy can reach a data rate of 50 GB/s, datasets can contain terabytes of data, and electron microscopy is a visual and interactive method, these solutions can be characterized as interactive high performance computing.

  

What infrastructure, programs and tools are used in your group?

  • MapReduce-like processing, "divide and conquer", linear algebra, inverse problem solving
  • Python, NumPy, SciPy, Dask, Numba, CuPy, Torch, Jupyter, JupyterHub;
  • Linux, Windows;
  • Nextcloud, NAS, NFS, CIFS, SSH;
  • GitHub, GitLab, Azure Pipelines, PyPI, Zenodo;
  • Tox, Pytest, Sphinx;
  • product management, project management, software development, test-driven development, Agile;
  • PCIe 4.0, SSD RAIDs, 10 GBit Ethernet, AMD EPYC, GPGPU

What could a participant of the HIDA Trainee Network learn in your group? How could he or she support you in your group?  You can learn high performance data processing with Python, in particular throughput-oriented processing of large-scale data. That can also involve finding suitable mathematical approaches and implementation strategies to transform an existing "proof of principle" reference implementation into a production-ready high-performance tool. Typically, we achieve speed-ups of 100x to 1000x from a "naive" NumPy or Matlab-based implementation.

Furthermore, you can learn software development methodologies, in particular the "GitHub flow", in combination with quality assurance through automated tests and continuous integration.

Contributions to scientific Open Source software are highly appreciated as a form of support. That can involve software which we actively maintain and develop, work on upstream dependencies, or all other forms of contributions to the Open Source software ecosystem. Such contributions can be in-kind by simply improving existing software and/or releasing new software under an Open Source license, or by joint applications for funding where parts of the resources are dedicated to software development and maintenance.

    

download