The BIG-MAP project, which is funded by the European Union (EU), aims to significantly shorten the time it takes to develop new types of batteries – with a special focus on sustainability. Karlsruhe Institute of Technology (KIT) and Ulm University are participating in the project via the CELEST research platform. At the same time, the project boosts the research activities in the joint POLiS cluster of excellence.
In order to achieve the climate neutrality targeted by the EU and Germany by 2050, greenhouse gas emissions from road traffic, among other things, must be reduced significantly. The systematic expansion of electromobility is expected to make a major contribution to this objective. However, this will require more cost-effective and sustainable alternatives to the existing batteries. “This is a huge challenge because the development of new batteries takes quite a long time using the current methods. In the BIG-MAP project, we want to accelerate this process significantly,” says Professor Maximilian Fichtner, scientific spokesman of CELEST and POLiS and Vice Executive Director at Helmholtz Institute Ulm (HIU), which KIT founded together with the Ulm University. The purpose of the BIG-MAP (BIG stands for Battery Interface Genome; MAP for Materials Acceleration Platform) EU project is to establish completely new methods and thus significantly boost battery development – among other things through systematic automation and the use of artificial intelligence (AI). In future, the methods established in BIG-MAP will speed up the development of sustainable and ultra-high performance batteries by a factor of ten.
AI and robots to speed up battery development
The BIG-MAP project aims to create a common European data infrastructure that will enable us to autonomously collect and process data from all stages of the battery development cycle and then use them in cooperative workflows. Physical access to the differently equipped test facilities will then not be necessary for BIG-MAP researchers any longer, and they will be able to collaborate across national borders and time zones. AI-orchestrated experiments and synthesis will be based on huge amounts of collected data, with a focus on battery materials, interfaces, and intermediate phases. The data will be generated by computer simulations, autonomous high-throughput material synthesis and characterization, in operando experiments, and device-level tests. Novel AI-based tools and models will use the data to “learn” how battery materials and interfaces interact, thus laying the foundation for the improvement of future battery materials, interfaces, and cells.