Projects linked to HDS-LEE

MiBioLab - Automated Bioprocess Development

HDS-LEE Scientific Director Prof. Wolfgang Wiechert is involved in a Helmholtz Enterprise Spin-off Program named “MiBioLab - Automated Bioprocess Development” funded by Helmholtz as an Helmholtz Innovation Labs in a second phase starting in 2023. The aim is to develop an automated microbioreactor platform to accelerate the development of sustainable bioprocesses. In 2017 the lab got a first funding from the Helmholtz Association to build a Helmholtz Innovation Lab. The goal was to apply the technology in joint research projects with industrial companies. This was the starting point of the Microbial Bioprocess Lab (MiBioLab) as a contract research organization. A digital twin of the lab robotic facility and on-line data processing plays a central role in MiBioLab. Laura Helleckes, a doctoral researcher of MiBioLab, was associated in HDS-LEE in 2021. HDS-LEE will highly profit from the platform and the generated high throughput experimental data.

Uncertainty Quantification - From Data to Reliable Knowledge

Prof. Alexander Mitsos (HDS-LEE PI), Prof. Dirk Witthaut (HDS-LEE PI), and Dr. Manuel Dahmen are FZJ PIs in the HGF Incubator Pilot Project “Uncertainty Quantification - From Data to Reliable Knowledge” (UQ) funded by Helmholtz Initiative and Networking Fund from December 2019 – May 2023. The UQ project is led by Prof. Martin Frank (KIT) and Prof. Christiane Fuchs (Helmholtz Munich) and connects researchers from four different Helmholtz research fields (Energy, Earth & Environment, Information, Health) with Helmholtz data science experts, applied mathematicians, and university partners. The Jülich PIs, together with Prof. Veit Hagenmeyer (KIT), focus on the uncertainties associated with renewable energy production, their propagation through power-grid systems, and optimal demand response of power-intensive production processes. Two doctoral researchers working on this project, Sonja Germscheid and Leonardo Rydin Gorjão, were associated to HDS-LEE in 2020.

Helmholtz Foundation Model Initiative

HDS-LEE PIs Prof. Martin Schultz and Prof. Stefan Sandfeld coordinate two pilot projects funded by the new Helmholtz Foundation Model Initiative (HFMI) to create a new generation of AI foundation models for science. They are involved in the projects "HClimRep: Capturing interactions between the atmosphere, ocean, and sea ice in a novel climate model" and "SOL-AI: Development and optimization of photovoltaic materials".

HClimRep

The HClimRep project aims to answer exactly these questions. By building one of the first AI foundation models for climate research, which combines data from the atmosphere, ocean, and sea ice, researchers are developing one of the most precise weather and climate models in the world. This deep-learning model, with billions of parameters, will be capable of conducting complex "what-if" experiments and other modeling tasks related to the ocean and atmosphere, thanks to extensive training on Europe's first exascale computer.

SOL-AI

SOL-AI aims to create a foundation model that will fundamentally reform materials informatics in this field. It is capable of integrating the diversity of experimental data and results in the research of photovoltaic materials, advancing innovations in various areas: from accelerated component development and optimization to the discovery of new solar materials. SOL-AI is expected to develop solutions that will have practical relevance for both research and industry.

DFG priority program

HDS-LEE Scientific Director Prof. Alexander Mitsos is the coordinator of the DFG priority program "Machine Learning in Chemical Engineering - Knowledge Meets Data: Interpretability, Extrapolation, Reliability, Trust" with the goal to enable the chemical industry’s transition renewable energy and raw materials by using machine learning as a catalyst. 

The goals of SPP 2331 include:

• Provide solutions to ChemEng problems for which current methods fail through ML
• Support young (female) researchers
• Foster collaborations
• National and international visibility

This program is a cooperation between research groups from RWTH Aachen University, Ruhr-Universität Bochum, TU Kaiserslautern, TU Berlin, and Otto-von-Guericke-University Magdeburg. The HDS-LEE PIs Prof. Martin Grohe, Prof. Alexander Mitsos are involved in projects under this priority program. Jan Rittig, a doctoral researcher of this program, was associated to HDS-LEE in 2021.

LOKI - Integrated Early Warning System for Local Recognition, Prevention, and Control for Epidemic Outbreaks

The project “LOKI - Integrated Early Warning System for Local Recognition, Prevention, and Control for Epidemic Outbreaks“, funded by the Helmholtz Initiative and Networking Fund, was launched in July 2022 as an initiative to mitigate the consequences of epidemiologically relevant outbreaks of infections. In LOKI four Helmholtz centers HZI (Helmholtz Center for Infection Research), CISPA (Helmholtz Center for Information Security), FZJ (Forschungszentrum Jülich), and DLR (German Aerospace Center) are collaborating, supported by the Robert-Koch-Institute (RKI) and the Academy for Public Health Services (AÖGW), under the lead of Prof. Michael Meyer-Hermann (HZI). With Prof. Alexander Mitsos (FZJ), Prof. Wolfgang Wiechert (FZJ), and Dr.-Ing. Achim Basermann (DLR) three HDS-LEE PIs are involved in the successful proposal. The aim of LOKI is to provide the local health authorities (LHA) with a platform for early detection, prevention, and mitigation of epidemics with pandemic potential (e.g., SARS, MERS, COVID-19) and recurring outbreaks (e.g., seasonal influenza, measles). In LOKI, data streams from various sources are integrated in a privacy-preserving manner. Data-driven outbreak detection and model-based conditional forecasting are combined and run in fully automated evaluation workflows on HPC resources. An interactive web application allows the customized simulation of user-driven scenarios, empowering LHAs to perform “what-if” scenario calculations to test non-pharmaceutical interventions and to plan and optimize policy measures.

NFDI FAIRagro

HDS-LEE PI Prof. Björn Usadel (FZJ) is part of NFDI FAIRagro that is a community-driven initiative within the National Research Data Infrastructure (NFDI) funded by DFG (from 2023-2028). This NFDI consortium is an initiative of NFDI4Agri and focuses on the development of sustainable crop production and agroecosystems. FAIRagro works on an interoperable and scalable research data infrastructure for agrosystems research. It is a consortium of research groups at Leibniz Centre for Agricultural Landscape Research (ZALF), Federal Research Centre for Cultivated Plants (JKI), Information Centre for Life Sciences (ZB MED), Kuratorium für Technik und Bauwesen in der Landwirtschaft (KTBL), Senckenberg Leibniz Institution for Biodiversity and Earth System Research (SGN), Leibniz Institute for Information Infrastructure (FIZ Karlsruhe), Leibniz Institute of Plant Genetics and Crop Plant Research (IPK), University of Bonn, Thünen Institute, and World Agricultural Systems Center of Technical University Munich.

KI:STE

HDS-LEE PI Prof. Julia Kowalski successfully acquired the BMU “KI Leuchtturmprojekt” (AI Lighthouse Project) with the title “KI:STE- KI-Strategie für Erdsystemdaten” (AI strategy for Earth system data) together with her project partners from Forschungszentrum Jülich, University of Cologne, Rheinische Friedrich-Wilhelms-Universität Bonn, 52° North Initiative for Geospatial Open Source Software GmbH and Ambrosys GmbH.

The aim of the KI:STE project is to analyze and process data on the state of nature and the environment by using artificial intelligence (AI) and make it available to the public. Within this project, the technical requirements will be created to make high-performance AI applications on environmental data portable for future users and to establish environmental AI as a key technology. This will enable better prediction of weather extremes such as heavy rain and drought in the future.

The project is part of the funding initiative "AI Lighthouses for Environment, Climate, Nature and Resources." With this initiative, the German Federal Ministry for the Environment is funding projects that use artificial intelligence to tackle ecological challenges.

The doctoral researchers of the KI:STE project will join the HDS-LEE school and strengthen the network within the HDS-LEE community