The project aims to develop a data-driven, semantic framework to accelerate redox flow battery research and optimisation. First, we will define a formal ontology to organise computational and experimental data with consistent metadata, ensuring that modelling and characterisation results are comparable and interoperable.

On this foundation, we will implement semantic search and analysis tools to efficiently discover relevant information and reveal patterns across datasets. Methodologically, we will combine high-throughput electrochemical screening with AI techniques, including pattern recognition for spectra and voltammetry, to extract knowledge from real operation data and build predictive models of battery behaviour.

Validation will occur through integrated workflows that link data ingestion, analysis, and model refinement. The expected outcomes include an open, shared knowledge base for the community, practical tools that speed up data-driven discovery, and AI-enabled methods that improve understanding of complex interrelations and guide better design and operational decisions for redox flow batteries.