Work Package 2 focuses on developing a comprehensive Digital Twin Platform to accelerate the design, screening, and testing of next-generation surfactants. This initiative aims to integrate cheminformatics, machine learning, and molecular simulations to create predictive models that can identify optimal surfactant structures and formulations with desired physicochemical and performance properties.

The work package involves the development of a database of surfactant molecules and formulation components, alongside AI/ML models for surfactant property prediction, formulation stability, and performance optimization. These digital modules will enable rapid, data-driven decision-making and reduce experimental iterations through in-silico design and virtual screening.

By combining computational tools with experimental validation, this work package aims to establish a digital ecosystem for sustainable chemical innovation — empowering industry and academia to co-create efficient, eco-friendly, and high-performance surfactant systems for diverse applications.