A critical step in transitioning to a green future is the accelerated discovery and mobilization of high-performance materials for clean technologies. Clean energy transition by 2030 requires at least 10X acceleration for production-ready energy materials. In addition to resource intensive and insufficient success rates, current research infrastructures and practices take 10 to 20 years to advance a new material from discovery to commercialization.
The development of next-generation materials for hydrogen technologies includes fabrication scale-up and integration with other cell components. R&D data assets are poorly utilized for developing new energy materials within emerging hydrogen technologies. The shortcoming in data utilization is largely driven by unstructured and complex data (type, category, quantity) from various experimental, synthesis, modelling and simulation sources. A unified data management approach, albeit a complex task, is essential for the discovery-to-device integration pipeline of new materials and components.
This presentation introduces opportunities and challenges in establishing a decentralised and adaptable future lab concept that speeds-up the development, integration, and innovation path for clean energy materials and technologies. In particular, the key challenges in availability of practical material-to-device data infrastructure within hydrogen technologies are articulated. We address the gaps in availability of AI-ready data sources, predictive models, and their role for accelerating development and early-prediction of materials properties and component performance.
Dr. Kourosh Malek is currently heading the research department “Artificial Materials Intelligence (AMI)” as part of the institute for energy and climate research (IEK-13) at Forschungszentrum Jülich GmbH. He is also the founder and managing director at ViMi Labs, a software solution that designs practical AI agents & virtual cloud labs for clean energy sector. The AMI division aspires to advance the discovery and integration of energy materials by streamlining the development workflow with AI. Specializing in deep learning for rapid image analysis for material characterization, innovative inverse molecular design for targeted synthesis, and comprehensive data management through design of ontology and graph databases, his team works toward enhancing data utilization at every step from lab to device integration.
Go to the Events page.