PolySCOUT

As helpful and prolific as plastics are in our lives today, their production and eventual litter also pose serious threats to our environment and health. In addition to their origin and the related greenhouse gas emissions during production, their end-of-life impact involves pollution and microplastics that seep into our soil and water, and consequently in our food and bodies. Therefore, the demand for plastics made from renewable carbon – recycled plastics, biomass, and captured CO₂  – is growing. In addition, there is a need for a safe and sustainable design with appropriate end-of-life options, such as recyclability or biodegradability. And that requires novel polymers with the right properties, feedstocks, price points, and availability to enable a smooth transition.

Designing and implementing new polymers typically takes 20-30 years of research and development, documentation and scaling. The scope of polymer design is vast and varied. Modelling polymer materials and predicting their behaviour is complex. In addition, the fossil-based polymers in use today have taken nearly 100 years to reach their current low-cost, highly effective level of maturity. In their search for novel biopolymers with the right properties, polymer producers, material scientists, and brand owners don’t have 100 years and unlimited budgets. They need efficient, economically feasible ways to find the right solutions with the right properties to transition the plastics industry by 2050. With such a limited time frame for such a complex task, acceleration of development is essential.

The PolySCOUT suite of models supports novel polymer development in two key ways. Primarily, polymer developers, material scientists, and brand owners can input design criteria for novel polymers that encompass mechanical and physical properties, and eventually also factors like environmental impact, safety, feedstock availability, or economic feasibility. PolySCOUT then suggests polymer compositions that meet those criteria. This can also be done in reverse: scientists who have already developed affordable, available, bio-based polymers can use the PolySCOUT models to uncover potential new applications for it. In this way, PolySCOUT offers acceleration of both types of innovation.

TNO has designed a unique portfolio of AI-based Machine Learning models that can vastly accelerate the research and discovery process for novel polymers. The PolySCOUT models learn from an ever-growing data set that includes all of TNO’s research in this area, technical data sheets from commercially available materials, as well as from roughly 2,000 scientific articles that focus on polymer development. The models deploy data-driven algorithms that connect important polymer descriptors to industrially relevant polymer properties. As such, these algorithms can predict properties of novel polymers. This feature can be used to match a novel polymer with a required property profile. With these models, developers, scientists and brands can identify novel, safe and sustainable polymers and validate them in a lab environment, which further feeds the models’ algorithms. All in a fraction of the time of a standard development cycle.

Want to learn more about using PolySCOUT to accelerate novel biopolymer design or learn about new applications for your existing biopolymer?