Funded projects from our Helmholtz AI project calls

2022 - 10 funded projects

More information on each projects in the upcoming weeks.

  • CMILE: Smile vectors of climate change - exploring the latent space of Earth system dynamics

Contact: Jan Saynisch, (GFZ)

  • tomoCAT: Machine-learning-driven context-based macromolecular identification in cryo-electron tomograms for structural analysis

Contact: Artur Yakimovich, (HZDR)

  • RBPAI4Virus: Learning the language of host-viral protein-RNA interactions: new possibilities for short and long-term intervention

Contact: Annalisa Marsico, (HMGU)

  • AI-Receptor: AI- and HPC-based Design of Synthetic Receptor Assays for Continuous Metabolite Sensing

Contact: Frank Biedermann, (KIT)

  • BrainAge4AD: Brain-age Estimation for Clinical Application in Alzheimer‘s Disease

Contact: Elizabeth Kuhn, 

  • AI-quifer:  Making Artificial Intelligence fit to determine off-shore groundwater as key to coastal water management

Contact: Laura Haffert,

  • DeepVar: DeepVar: Deep learning genotype-to-phenotype models for cancer and rare diseases

Contact: Brian Clarke, (DKFZ)

  • ARTIST: AI-enhanced differentiable Ray Tracer for Irradiation-prediction in Solar Tower Digital Twins

Contact: Max Pargmann,

  • MADRNA: MAchine learning force field Development for RNA

Contact: Alexander Schug, (FZJ)

  • AISPA: AI-driven instantaneous solar cell property analysis

Contact: Thomas Kirchartz, (FZJ)


2021 - 10 Funded Projects


  • AI-4-XAS: Artificial Intelligence for X-ray Absorption Spectroscopy (HZB + Hereon)

    The theoretical prediction of X-ray spectra for very large molecules is currently beyond the capabilities of the most powerful high-performance compute clusters. The core of this project is to utilize molecular graphs in combination with the probabilistic analysis of molecular motifs for a supervised machine learning prediction trained on data obtained for smaller building blocks of the huge molecules of interest.

    Contact: Annika Bande, (HZB)
  • ALEGRA: Active Learning-enabled Generation of (Patho-)Physiological Lung Architectures for Pulmonary Medicine (DKFZ + HMGU)

    ALEGRA aims to discover new insights into the morphology, physiology, and functionality of mammalian lungs. Therefore, quantitative parameters will be extracted from light sheet fluorescence microscopy images featuring comprehensive annotations of unprecedented detail for structures of interest such as hollow airways, blood vessels, as well as alveoli. These annotations are made possible by a novel active learning approach for semantic segmentation, nnActive, which will be developed as part of this project.

    Contact: Paul Jäger, (DKFZ)
  • COMPUTING: COnnecting Membrane Pores and prodUction parameTers via machine learnING (Hereon + DKFZ)

    Isoporous block-copolymer membranes play a crucial role in the separation of molecules from liquids and can be used, for example, for the purification of drinking water. Despite recent efforts, the production process of these membranes is still not understood, currently requiring multiple trial-and-error experiments to produce the desired output characteristics for each new batch of raw materials. This project aims at streamlining the manufacturing process and ultimately unlock the production of designer membranes by developing methods that predict the required production parameters given some desired morphology and raw material characteristics.​

    Contact: Martin Held, (Hereon)
  • DIADEM: Diabetes Detection from Histopathologic Images of Human Pancreas (HMGU + DKFZ)

    Type 2 diabetes is a chronic, often debilitating disease, which is essentially determined by a complex dysfunction of pancreatic islets resulting in reduced insulin secretion. In this project, we aim to recognize patterns associated with islet dysfunction by leveraging deep learning in a unique set of histopathologic images with clinical and laboratory data from patients with and without type 2 diabetes. While key challenges of the project involve gigapixel-sized images with different histologic stainings and varying sample quality, explainability of the models will advance our current understanding of diabetes.

    Contact: Robert Wagner, (HMGU)
  • NACHMO: Neural Network-based Atmospheric Chemistry Module for Weather and Climate Models (Hereon + KIT)

    Realistic atmospheric chemistry is crucial for simulating and predicting climate, weather and air quality, but is currently computationally infeasible. We will design and train neural networks to accelerate simulations of atmospheric chemistry, using specialized architectures and loss functions to enforce conservation laws, maintain accuracy and ensure long-term numerical stability. Our ultimate aim is to provide a fast, accurate chemistry module for weather, climate, and Earth system simulations beyond previous computational limits.

    Contact: David Greenberg, (Hereon)
  • Opt4Bio: principled optimization of structured deep learning models for multimodal biological data integration (HMGU + CISPA)

    We will develop new efficient and theoretically sound optimization methods to train structured deep learning models for multimodal data integration. Such models are of particular interest in biology and health applications where datasets often consist of a mixture of structured and unstructured data (e.g., tabular data from high-throughput sequencing, and medical imaging data, respectively). Our focus on biological and health data is intended to facilitate the transfer of these techniques to clinically relevant applications, including fast biomarker detection in microbiome data.

    Contact: Christian Müller, (HMGU)
  • RESEAD: Robust Environmental Sensor data using Explainable data-driven Anomaly Detection (KIT + UFZ)

    The increasing amount of sensor data requires robust automated quality control (QC). Within the project RESEAD we will go a significant step beyond existing QC methods by leveraging the full spatiotemporal information contained in the data of large distributed environmental sensor networks. We will develop a ready-to-use software pipeline consisting of a dense embedding method for sparse spatially distributed sensor data, a GAN-based data imputation, and a module to make the results of our DeepLearning-QC-pipeline explainable.

    Contact: Christian Chwala, (KIT)
  • SedimentAI: Automated particle detection in Sediments using imaging flow-cytometry and Artificial Intelligence (UFZ + AWI)

    Past climate reconstruction based on paleobotanical records of sediments is limited in throughput due to manual counts of experts. In SedimentAI we want to test the innovative combination of multispectral imaging flow cytometry and a semi-supervised learning approach for this challenge. The project will substantially advance the field of paleobotany and would furthermore provide a deeper understanding of past ecosystem dynamics with respect to climate change.

    Contact: Susanne Dunker, (UFZ)
  • SURF: (Semi/Un)supervised machine learning flood damage assessment (DLR + GFZ)

    In the last decade, flood events have left 1 billion people without a home. To improve the early response of crisis management, SURF aims to develop an approach to rapidly assess building damage after flood events. Particularly, we propose to explore three machine learning-based approaches to provide a near real-time solution that benefits from existing global urban mapping data and information collected in the early stage of the flood.

    Contact: Andrés Camero Unzueta, (DLR)
  • UNITY: UNcertainty and explainabilITY for unsupervised deep learning (MDC + DZNE)

    The old adage that AI is a “black box” is quickly eroding: Algorithms from "explainable AI" can identify the most important input features, and neural networks can provide uncertainty estimates about predictions and their interpretations. UNITY will push the development of such uncertainty and interpretability approaches for the example application of unsupervised integration of multimodal, sparse, high dimensional genomics data, to increase our molecular understanding of disease trajectories.

    Contact: Uwe Ohler, (MDC)


2020 - 17 Funded Projects

  • AI²: Eyesight to AI: Discovery of efficient corrosion modulators via predictive machine learning models (Hereon + HMGU)

    The fundamental concept of the project is to develop a pattern recognition routine that enables high-throughput quantification of the effect of small organic additives on the degradation of a magnesium alloy by automated classification of corrosion imprints. Subsequently, the quantified optical signal will be used as a target parameter for different supervised and semi-supervised learning approaches to predict the performance of untested additives. Accuracy and robustness of the developed models will be validated by experimental blind tests. More information.

    Contact: Christian Feiler, (HZG)
  • AI4GNSSR: Artificial Intelligence for GNSS Reflectometry: Novel Remote Sensing of Ocean and Atmosphere (GFZ + DLR)

    More information.

    Contact: Milad Asgarimehr, (GFZ)
  • AI-InSu-Pero: Artificial intelligence guided in-situ analysis of scalable perovskite thin film deposition (KIT + DKFZ + FZJ)

    As much as AI methods are already advancing some pioneering fields such as medical image diagnostics, they are suited to revolutionize combinatorial materials science and processing. In this project, AI algorithms are developed that are required for the detection of defects and inhomogeneities as well as film quality correlations in in-situ image data of solution-processed perovskite thin films.

    Contact: Ulrich Wilhelm Paetzold, (KIT)
  • AMR-XAI: Crushing antimicrobial resistance using explainable AI (HZI + CISPA)

    Antimicrobial resistance is perhaps among the most urgent threats to human health. AMR-XAI proposes to learn a small set of easily interpretable models that together explain the resistance mechanisms in the data using statistically robust methods for discovering significant subgroups. Key to our success will be the tight integration of domain expertise into the development of the new algorithms and early evaluation on real-world data.

    Contact: Olga Kalinina, (HZI)
  • CausalFlood: Identifying causal flood drivers (UFZ + DLR)

    Contact: Jakob Zscheischler, (UFZ)
  • DEEPROAD: AI-based development of next-generation diagnostics and precision medicine for Alzheimer’s disease (HMGU + DZNE)

    More information.

    Contact: Ali Ertürk, (HMGU)
  • DeGen: Deep Generative Models for Causal Prognosis using Neuroimaging Data (DZNE + FZJ)

    More information.

    Contact: Martin Reuter, (DZNE)
  • FoAIm: Coupling of complex multiscale structural foam characteristics with AI based methods (DLR + KIT)

    The long term vision of this project is to accelerate the characterization of material properties and thus considerably facilitate the development of new materials and components e.g. for future vehicles. As a first step the project partners will develop a ML architecture including explainable AI approaches to fulfill the tasks of characterizing mechanical properties from microstructure images and tailoring microstructures to desired macroscopic behavior for structural foams. More information.

    Contact: Alexander Greß, (DLR)
  • GANCSTR: GAN-based calculation of concentrated radiation on solar tower receivers (DLR + FZJ)

    Within GANCSTR machine learning methods are developed for very accurate prediction forecasts in solar thermal power plants. Such power plants consist of a large number of mirrors, so-called heliostats, which must be optimally controlled in order to achieve a very low levelized cost of energy. Generative adversarial networks are used to determine the distribution of solar radiation reflected from each heliostats and maximize the power plant's energy output.

    Contact: Daniel Maldonado Quinto, (DLR)
  • GLAM: Generative lung architecture modeling (MDC + HMGU)

    Complex 3D tissue disease models are being used as surrogates for pre-clinical drug development. However, current methods for fabricating artificial tissues are based on image-derived, or manually designed tissue architectures, and lack high-throughput applicability. This project is developing generative methods for designing bio-printable lung tissues across a spectrum of disease severity in the specific context of mouse and human lung disease.

    Contact: Kyle Harrington, (MDC)
  • PAI: Pollination artificial intelligence (UFZ + DLR)

    Pollination artificial intelligence (PAI) will transfer existing large-scale applicable AI-methods to the field of pollination ecology. PAI will train a hierarchical deep learning approach capable of identifying thousands of European pollinators from in-field observations, by using existing image databases and expert knowledge attributes. The successfully trained AI model will have its performance systematically tested in field studies. More information.

    Contact: Tiffany Knight, (UFZ)
  • PCDL-QuaSPA: Physics-constrained deep learning framework for quantifying surface processes across the Arctic region (GFZ + AWI)

    The permafrost-laden landscape of the Arctic is highly susceptible to degradations in the warming climate, and harbours the potential to exacerbate climate change due to its huge store of soil organic carbon. Large-scale monitoring and fast predictive simulations of permafrost-related features and natural systems are thus urgent and important. The project aims to develop both a deep-learning model capable of detecting and quantifying permafrost-landscape changes, and a physics-informed deep-learning framework to enable rapid modelling of complex Arctic surface-processes systems. More information.

    Contact: Hui Tang, (GFZ)
  • PSDAI: Patient-specific diagnostic AI-systems via one-shot domain adaptation (DKFZ + DLR)

    Patient-specific diagnostic AI-systems via one-shot domain adaptation deep learning has shown its potential in medical image analysis, but the lack of adequate generalization impedes the translational step to the clinic. This project aims to develop an approach that uses patient-specific information at inference time to improve generalization for that particular setting.

    Contact: Titus Brinker, (DKFZ)
  • SuperPI: Deep-learning empowered super-resolution plankton imaging (GEOMAR + HMGU)

    The goal of SuperPI is to provide AI-based solutions for improving the optical resolution of underwater plankton imaging. Particularly, developing algorithms for novel "enhanced depth-of-field" imaging technology will allow to combine high optical resolution in large sample volumes. Thus, the project is envisioned to push the boundaries of plankton imaging applications, as well as optical microscopy in general.

    Contact: Jan Taucher, (GEOMAR)
  • SynRap: Machine-learning based synthetic data generation for rapid physics modeling (DESY + HZDR)

    SynRap investigates the generation of simulated (“synthetic”) data using surrogate models, which will be used in a second step for efficient training of neural networks. A unified surrogate model framework will be developed and used to tackle common challenges in two different research areas – high-energy physics (HEP) and high energy-density (HED) phenomena.

    Contact: Isabell-Alissandra Melzer-Pellmann, (DESY)
  • T^6: ReacTive TransporT experimenT digiTal Twin (FZJ + GFZ)

    Reactive Transport Digital Twin (T6) develops an expanded toolbox for experimentalists integrating computer vision and AI/ML methods for ultra-fast forward coupled hydro-geochemical simulations, enabling real-time assessment and correction of microfluidic experiments. More information.

    Contact: Jenna Poonoosamy, (FZJ)
  • XAI-graph: Explainable AI and improved measurements of uncertainty for machine learning on (biomolecular) structure graphs (UFZ + HZI)

    The goal of XAI-graph is to increase the credibility of predictive approaches in toxicology by introducing explainability into existing AI approaches and by developing methods to quantify uncertainty of AI based predictions. The aim is to i) promote these principles in toxicology and transfer them into applications to support the prioritization of chemicals for regulatory testing, and ii) to gain new functional/biological insights through the investigation of decisive features.

    Contact: Jana Schor, (UFZ)


2019 - 19 Funded Projects

  • AI4Flood: AI for emergency mapping during floods (GFZ + DLR)

    This project aims to improve existing satellite-based emergency mapping methods from SAR data by training, testing and validating new ML algorithms for the extraction of water areas during flood events. More information.

    Contact: Prof. Dr Mahdi Motagh, (GFZ) and Dr Sandro Martinis, (DLR)
  • AINX: AI for neutron and X-ray scattering experiments (FZJ + HZDR)

    The project develops AI-supported data reduction and analysis techniques for neutron and X-ray scattering experiments. The researchers’ aim is to optimize beamtime utilization and to accelerate data analysis. More information.

    Contact: Dr. Marina Ganeva, (FZJ) and Dr. Thomas Kluge, (HZDR)
  • aN0: Improving simulations on high-performance computers (FZJ + KIT)

    The goal of AlphaNumerics Zero is to rethink the design of numerical methods on high-performance computers. The project uses reinforcement learning techniques so that the computer independently learns the optimal numerical solution method for a given simulation problem.

    Contact: Dr. Robert Speck, (FZJ)
  • ARTERY: AI for the application of precise radiotherapy (HMGU + HZDR)

    Artery is developing an innovative method of radiotherapy that uses multiple proton beams of a hair’s breadth that selectively destroy cancerous tissue. In the project, the researchers involved are examining irradiated tissue using high-resolution 3-D microscopy. AI supports the evaluation of the images and the analysis of radiation damage. More information.

    Contact: Dr. Stefan Bartzsch, (HMGU)
  • Autonomous Accelerator: Machine learning for autonomous accelerators (DESY + KIT)

    Modern particle accelerators offer extraordinary beams for new discoveries in science. Increasing beam requirements make their operation more demanding, and a fully autonomous accelerator seems a long way off. However, this project is taking its first steps towards implementation. It brings reinforcement learning to the linear accelerator operation at DESY and KIT. More information.

    Contact: Dr. Annika Eichler, (DESY)
  • DeepSAR: Improving remote sensing data through Deep Learning (DLR + AWI + UFZ)

    Despite the success of Deep Learning, important applications in remote sensing are still based on the inversion of physical models. The DeepSAR project combines both to compensate for their respective weaknesses and to improve the extraction of bio-/geophysical information from remote sensing data, in particular the estimation of forest height and ice penetration bias from SAR data. More information.

    Contact: Dr Ronny Hänsch, (DLR)
  • DeGeSim: Deep Learning for most precise high-energy particle physics at the Large Hadron Collider (DESY + FZJ)

    Scientific simulation calculations are often limited by their high demand for computing capacity. Generative Deep Neural Networks offer an efficient way to replace complex models and enable fast and precise simulations for the CMS and ATLAS experiments at the Large Hadron Collider (CERN).
    More information here.

    Project members: Dr. Dirk Krücker, Prof. Dr. Kerstin Borras, PD Dr. Judith M. Katzy, Dr. Jenia Jitsev, Dr. Wojciech T. Fedorko
    Contact: Dr. Dirk Krücker, (DESY)
  • EDARTI: AI approaches for improved electron diffraction inversion (FZJ + HMGU)

    In this project an interdisciplinary team of mathematicians and physicists is dedicated to decoding properties of material science and biological samples from 4-D diffraction images by further development of AI methods.

    Contact: Prof. Dr. Knut Müller-Caspary, (FZJ) and PD Dr. Wolfgang zu Castell, (HMGU)
  • FluoMap: Create global fluorescence maps from satellite data with ML (DLR + FZJ)

    FluoMap pursues the goal of extracting fluorescence signals from the measurement data of the satellite- or airborne imaging spectrometers DESIS and HyPlant using state-of-the-art AI methods. This will make it possible to generate global fluorescence maps, which will play a key role in the worldwide monitoring of the vegetation health status. More information.

    Contact: Dr. Miguel Pato, (DLR)
  • i2Batman: Intelligent battery management through spectroscopy and ML (FZJ + KIT)

    Within the i2Batman project, ML techniques for optimized battery management at the battery cell level will be developed and demonstrated. The aim is to achieve optimized fast charging behavior while at the same time ensuring that the battery life meets or even outperforms the industry standard.

    Contact: Prof. Dr. Josef Granwehr, (FZJ)
  • LearnGraspPhases: Enabling smooth movements in robots (DLR + KIT)

    Robots are known for their precision and power, but also for their somewhat jerky movements. These are mainly caused by abrupt transitions between successive actions. In LearnGraspPhases, DLR and KIT use joint databases and ML methods to learn models that lead to smooth transitions and a more natural robot motion. More information.

    Contact: Dr. rer. nat. Freek Stulp, (DLR)
  • MOMONANO: ML enables molecular nanorobots (FZJ + HZB)

    The aim of the project is to build complex functional nanostructures with single molecules as with LEGO bricks. However, the quantum mechanical simulations required for this are too time-consuming. Momonano combines expertise in ML, molecular simulations and nanorobotics to accelerate such simulations by orders of magnitude. More information.

    Contact: Dr. Christian Wagner, (FZJ)
  • Noise2NAKO(AI): Using AI to identify the impact of environmental factors on health (HMGU + DLR)

    The project uses innovative AI and ML methods to investigate long-term impacts of environmental factors on human health. In a case study, the participating researchers will first develop area-wide noise maps and then link these to health data from participants in the health study “German National Cohort (NAKO)” in order to identify vulnerable clusters at risk of hypertension. More information.

    Contact: Dr. Kathrin Wolf, (HMGU)
  • PRO-GENE-GEN: Virtual cohort data for personalized medicine (DZNE + CISPA)

    In the PRO-GENE-GEN project, DZNE and CISPA develop methods to generate virtual cohorts from existing genomic datasets. They will share the same characteristics as real patient data but do not allow the exposure of personally identifiable information. This allows large data sets to be shared for the development of new diagnostic approaches, which is central to personalized medicine. More information.

    Contact: Dr. Matthias Becker, (DZNE) and Prof. Dr. Mario Fritz, (CISPA)
  • ProFiLe: Better prediction of protein structure and function with AI (DLR + KIT)

    Proteins are the molecular basis of life and malfunctions can lead to diseases. ProFiLe is designed to predict protein structure by AI and improve the understanding of their function. The HeAT framework enables training with extremely large genome databases on supercomputers.

    Contact: Dr. Achim Basermann, (DLR)
  • REPORT-DL: Detecting earthquakes with AI (KIT + GFZ + GEOMAR)

    The REPORT-DL project aims to improve our understanding of earthquake hazards by adapting Deep Learning AI tools developed for natural language processing and image analysis to detect and locate the smallest earthquakes. The distribution of these micro-earthquakes allows conclusions to be drawn about the stress state of the Earth's crust but cannot be adequately determined using conventional methods.

    Contact: Prof. Dr. Andreas Rietbrock, (KIT)
  • SC-SLAM-ATAC: From Single Cell Multiomics to Gene Regulatory Networks (MDC + HMGU)

    The project deals with gene regulatory networks. They produce a large number of different cell types and underlie a misregulation of gene expression in diseases. The project uses ML to integrate single-cell measurements of open chromatin and gene expression dynamics (by RNA labelling) to reconstruct gene regulatory networks. More information.

    Contact: Dr. Jan Philipp Junker, (MDC)
  • ULearn4Mobility: AI for the prediction of mobility patterns (KIT + DLR)

    Events such as the spread of diseases are often subject to changes in time and place. In ULearn4Mobility, ML methods are developed for large-scale, evolving phenomena. The key application is the satellite-independent localization for future mobility and navigation within buildings. More information.

    Contact: Dr. Florian Pfaff, (KIT)
  • UniSeF: Training data for sharpest images (DESY + HZG)

    Synchrotron-based X-ray tomography enables the examination of samples at high resolution. The segmentation is the basis for the scientific interpretation of the tomograms. UniSeF developments include the segmentation of identical objects (instance segmentation), a guided interactive and iterative strategy for the annotation of training data, and a browser-based service. More information.

    Contact: Dr. Philipp Heuser, (DESY)