Gen AI Kemira, Cusp AI Design Materials to Remove Forever Chemicals from Drinking Water

Related Vendors

Kemira OYJ

Elementar Analysensysteme GmbH

Glatt Ingenieurtechnik GmbH

Italvacuum, Srl

Kemira, Cusp AI have utilized the Gen AI technology to design new materials for removing forever chemicals from drinking water and process water at trace concentrations. This is the first commercial partnership to apply generative AI end-to-end to the design of new materials for PFAS remediation.

Helsinki/Finland – Kemira and Cusp AI, the frontier AI materials science company, recently announced that they have used generative AI to design new materials targeting the removal of PFAS, so-called "forever chemicals," from drinking and process water at trace concentrations, using chemistry that is stable, sustainable, and manufacturable.

The materials discovery project explored a design space of approximately 300 trillion possible material structures and delivered over 5000 novel material designs with full property data for three priority PFAS molecules: GenX, PFBS, and PFOS. This was narrowed to approximately 20 selected priority candidates now advancing to further development. The program reached this stage in six months.

This is the first commercial partnership to apply generative AI end-to-end to the design of new materials for PFAS remediation. While academic groups and technology companies have explored AI for materials screening, no previous collaboration has taken a generative approach, designing entirely new structures from scratch against industrial performance criteria, and delivered candidates at this scale and speed.

"Kemira challenged us with finding new solutions to one of the most pressing environmental problems of our time, and in six months our partnership delivered," said Dr Chad Edwards, CEO and Co-Founder of Cusp AI. "The collaboration is now advancing to its next phase, with further projects already being scoped. We built Cusp AI to compress discovery timelines on problems that matter, and we are delighted to be creating real impact and value this early in our journey."

"This project combined Kemira's deep expertise in water treatment chemistry with Cusp AI's capabilities, and the results speak for themselves," said Sampo Lahtinen, Executive Vice President, Research and Innovation at Kemira. "Our teams worked closely together to ensure that every material candidate was evaluated against real industrial requirements. That rigor is what gives us confidence in taking these candidates forward."

"This partnership has shown us what AI-driven materials design looks like when it meets real industrial requirements," said Antti Salminen, President and CEO of Kemira. "We set a demanding brief: design new materials that can remove forever chemicals from water at trace concentrations, using chemistry that is stable, sustainable, and manufacturable, and speeding up the discovery phase of our discovery process. We now have a credible path toward a next-generation PFAS remediation product, and we look forward to further collaboration with the Cusp AI team."

Why this matters

PFAS (per- and polyfluoroalkyl substances) are persistent synthetic chemicals found in drinking water worldwide. They are subject to tightening regulation, including US EPA maximum contaminant limits in parts per trillion scale (announced 2024) and the EU Drinking Water Directive. Today's leading remediation technology is granular activated carbon (GAC). Kemira, which is already active in the activated carbon regeneration market, initiated this collaboration to explore whether AI-driven design could open a path to more selective and even longer-lasting alternatives.

What was delivered

Kemira defined the brief: discovery phase project of new materials that can remove specific PFAS molecules from water at sub-parts-per-billion concentrations, using chemistry that is water-stable, environmentally compatible, synthesizable, and cost-effective. Cusp AI's platform designed entirely new metal-organic frameworks (MOFs) from scratch, searching approximately 300 trillion possible structures and delivering over 5000 novel potential material designs with property data across all three target molecules, narrowed to selected priority candidates. The speed and scale of this discovery phase was unprecedented: record amount of structures was evaluated and it took 6 months to reach these results.

The project also uncovered new functional group chemistries with potential for development into broader adsorption products. The project is now moving into its next phase of further development and testing, and further programs across additional material classes are being scoped under the partnership's framework agreement.

(ID:50854287)