Helmholtz funds 19 AI projects to solve urgent grand challenges
The Helmholtz AI Cooperation Unit (Helmholtz AI) strengthens the application and development of applied artificial intelligence (AI) and machine learning (ML). In the first call for proposals for Helmholtz AI Projects, a top-class international panel of experts selected 19 collaborative high-risk, high-reward research projects. Helmholtz is investing a total of 7.2 million euros in these novel approaches – half of which is provided by the Association’s Initiative and Networking Fund.
“Artificial intelligence and machine learning are powerful tools for developing solutions for large and complex tasks such as climate change or future mobility,” says Helmholtz President Otmar D. Wiestler. “The 19 selected projects use the latest AI processes and sustainably promote the social application of these future technologies. I wish all involved scientists every success – in the knowledge that research with these novel methods is not always straightforward and can also lead to unexpected, outstanding research results”.
55 project proposals were submitted in the first call for Helmholtz AI Projects. The 19 selected projects use novel analytical tools to solve pressing societal challenges using AI. The projects promote the testing of these new approaches, are supported by several partners and will be implemented in up to three years – with the potential to quickly spawn larger follow-up projects.
“This opens up many opportunities; we can achieve enormous things in applied AI at Helmholtz,” says Fabian Theis, scientific director of Helmholtz AI. “The Helmholtz AI Projects make it possible for the first time to pursue joint approaches in AI between disciplines and Helmholtz Centers in order to exploit the immense potential of the large and complex data sets from the six Helmholtz Research Fields. We want to further strengthen this dynamic community”.
With the Helmholtz AI platform, Helmholtz is investing 11 million euros annually in six innovative research units and a transdisciplinary network for applied AI. This network builds on the community's strengths in AI and its unique data sets. In this way, Helmholtz AI contributes to solving the grand challenges of our time, fostering cross-field and cross-center collaboration, also with university partners. Further funding rounds will expand the network – the next call for proposals is planned for summer 2020.
Further information about Helmholtz AI and the calls for proposals for Helmholtz AI Projects: www.helmholtz.ai
Selected AI Projects
The following 19 projects will receive funding of up to 400,000 euros each over a total funding period of two to three years.
- AI4Flood: AI for emergency mapping during floods
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.
Prof. Dr Mahdi Motagh, email@example.com (GFZ) and Dr Sandro Martinis, Sandro.Martinis@dlr.de (DLR)
- AINX: AI for neutron and X-ray scattering experiments
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.
Dr. Marina Ganeva, firstname.lastname@example.org (FZ Jülich) and Dr. Thomas Kluge, email@example.com (HZDR)
- aN0: Improving simulations on high-performance computers
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.
Dr. Robert Speck, firstname.lastname@example.org (FZ Jülich)
- ARTERY: AI for the application of precise radiotherapy
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.
Dr. Stefan Bartzsch, email@example.com (HMGU)
- Autonomous Accelerator: Machine learning for autonomous accelerators
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.
Dr. Annika Eichler, firstname.lastname@example.org (DESY)
- DeepSAR: Improving remote sensing data through Deep Learning
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.
Dr Ronny Hänsch, email@example.com (DLR)
- DeGeSim: Deep Learning for most precise high-energy particle physics at the Large Hadron Collider
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).
Dr. Dirk Krücker, firstname.lastname@example.org (DESY)
- EDARTI: AI approaches for improved electron diffraction inversion
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.
Prof. Dr. Knut Müller-Caspary, email@example.com (FZ Jülich) and PD Dr. Wolfgang zu Castell, firstname.lastname@example.org (HMGU)
- FluoMap: Create global fluorescence maps from satellite data with ML
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.
Dr. Miguel Pato, Miguel.FigueiredoVazPato@dlr.de (DLR)
- i2Batman: Intelligent battery management through spectroscopy and ML
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.
Prof. Dr. Josef Granwehr, email@example.com (FZ Jülich)
- LearnGraspPhases: Enabling smooth movements in robots
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.
Dr. Friedrich Lange, Friedrich.Lange@dlr.de (DLR)
- MOMONANO: ML enables molecular nanorobots
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.
Dr. Christian Wagner, firstname.lastname@example.org (FZ Jülich)
- Noise2NAKO(AI): Using AI to identify the impact of environmental factors on health
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.
Dr. Kathrin Wolf, email@example.com (HMGU)
- PRO-GENE-GEN: Virtual cohort data for personalized medicine
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.
Dr. Matthias Becker, Matthias.Becker@dzne.de (DZNE) and Prof. Dr. Mario Fritz, firstname.lastname@example.org (CISPA)
- ProFiLe: Better prediction of protein structure and function with AI
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.
Dr. Achim Basermann, Achim.Basermann@dlr.de (DLR)
- REPORT-DL: Detecting earthquakes with AI
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.
Prof. Dr. Andreas Rietbrock, Andreas.Rietbrock@kit.edu (KIT)
- SC-SLAM-ATAC: From Single Cell Multiomics to Gene Regulatory Networks
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.
Dr. Jan Philipp Junker, JanPhilipp.Junker@mdc-berlin.de (MDC)
- ULearn4Mobility: AI for the prediction of mobility patterns
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.
Dr. Florian Pfaff, email@example.com (KIT)
- UniSeF: Training data for sharpest images
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.
Dr. Philipp Heuser, firstname.lastname@example.org (DESY)