If you are an industrial chemical producer dealing with the slow pace of R&D for carbon-neutral processes — this project developed IRIS, an autonomous lab that reduces discovery timelines by up to 90%. This allows you to find high-performance catalysts for value-added chemicals much faster.
AI-Driven Robotic Lab for Rapid Discovery of Carbon-Neutral Fuel Catalysts
Imagine trying to find a needle in a haystack by hand; that is how discovering new chemical catalysts usually works. This project builds a smart robot that does the searching, testing, and learning automatically. It is like having a high-speed digital chef that experiments with thousands of recipes until it finds the perfect one for turning CO2 into fuel.
What needed solving
Catalyst discovery is too slow and expensive, typically taking 20 years and millions of euros, which delays the transition to carbon-neutral industrial processes.
What was built
The IRIS platform, an autonomous lab combining robotic synthesis, electrochemical testing, and physics-informed AI models in a closed-loop system.
Who needs this
Who can put this to work
If you are a green fuel startup dealing with multi-million-euro R&D expenses — this project developed a closed-loop AI system that cuts R&D costs by 60-70%. This makes the development of carbon-neutral fuels financially viable.
If you are a CCU plant dealing with inefficient conversion of captured CO2 — this project developed a data-driven discovery platform that identifies catalysts capable of converting CO2 under realistic operating conditions.
Quick answers
How does this impact R&D costs?
The technology cuts R&D costs by 60-70% compared to conventional catalyst discovery methods.
Can this be scaled to industrial levels?
Based on available project data, the system transforms catalyst R&D into a scalable, data-driven industrial process using robotics and AI.
What is the IP or licensing model?
Based on available project data, the project creates a strategic data and technology asset, but specific licensing terms are not disclosed.
How much faster is the discovery process?
The system reduces discovery timelines by up to 90% compared to traditional methods.
How is the system integrated into existing workflows?
It integrates laboratory automation, experiment orchestration, and machine-learning models into one end-to-end workflow.
Who built it
The project is led by a single German SME, Dunia Innovations UG. With a 100% industry ratio and no university or research partners, the project is lean and focused on commercial application rather than academic exploration.
Contact Dunia Innovations UG in Germany
Talk to the team behind this work.
Contact us to explore partnerships for AI-driven catalyst discovery.