Materials Discovery

Novel Material Generation uses AI to propose candidate materials with target properties, enabling faster R&D cycles and lower discovery costs, by generating and evaluating candidate structures against desired performance and sustainability criteria, across materials research workflows.

Discovering materials with desired properties through traditional trial-and-error laboratory methods is slow and costly, limiting the pace of product innovation across manufacturing and life sciences industries.

The AI generates novel candidate material structures by learning from known material property datasets and applying generative models to propose structures that meet specified performance and sustainability criteria.

Reduces time and cost to identify validated novel materials; measured as reduction in experimental cycles needed to reach a qualifying candidate.

• •A dataset of known materials with characterised properties is available for training
• •Computational simulation infrastructure capable of evaluating generated structures is in place
• •Target property specifications are defined and machine-readable