ASCEND Project Launched in Berlin with €30 Million Funding to Revolutionize Catalyst Discovery via AI-Driven Closed-Loop Systems

EurekAlert! Germany

Overview

The ASCEND project, launched in Berlin with €30 million in funding, aims to usher in a new era of catalyst discovery. This project moves away from traditional trial-and-error by integrating AI models, high-throughput automated experiments, materials characterization, and human expertise into a closed-loop, AI-driven discovery system. This is expected to significantly reduce trial-and-error in catalyst development and dramatically accelerate the process to practical application of new catalysts.

In Depth

Key Findings

The newly launched ASCEND project in Berlin has secured a substantial €30 million (approximately $32 million USD) in funding from European funding bodies, announcing its aim to revolutionize the field of catalyst discovery. The project seeks to build a ‘closed-loop AI-driven discovery system’ that seamlessly integrates AI models, high-throughput automated experimentation, advanced materials characterization, and human expert knowledge, thereby fundamentally transforming traditional trial-and-error-dependent catalyst development processes.

Technical Details

The core of the ASCEND project lies in its innovative workflow, which combines the following key elements:

• AI-Driven Design and Prediction: AI models, trained on large catalyst datasets, predict and design new catalyst compositions and structures based on specific reaction conditions and target properties (e.g., activity, selectivity, stability). Generative AI techniques are particularly utilized to propose promising candidates that humans might not conceive.
• High-Throughput Automated Experimentation: AI-proposed catalyst candidates are rapidly synthesized and tested in an automated laboratory environment using robotic arms and microfluidic systems. This allows for the parallel evaluation of thousands of catalysts simultaneously, dramatically increasing experimental throughput.
• Advanced Materials Characterization: Synthesized and tested catalysts undergo detailed characterization using state-of-the-art analytical instruments such as X-ray diffraction, electron microscopy, and spectroscopy. This data is immediately digitized and added to the AI model’s training dataset.
• Closed-Loop Feedback and Learning: Data obtained from characterization is fed back into the AI model in real-time and utilized for the next round of design and experimentation. This continuous learning cycle enables the AI model to improve its performance over time, efficiently exploring for optimal catalysts.
• Integration of Human Expertise: While aiming for full automation, the deep expertise of human catalyst chemists and engineers plays a crucial role in validating AI models, solving complex problems, and generating new scientific insights.

This integrated approach is expected to significantly reduce the time and cost associated with catalyst development, potentially shortening processes that traditionally took years or decades into mere months.

Background and Industry Context

Catalysts are indispensable for the sustainability and economic efficiency of modern society across various sectors, including the chemical industry, energy conversion (fuel cells, hydrogen production), and environmental protection (emission control, CO2 capture). However, the discovery and optimization of new high-performance catalysts have been extremely challenging and time-consuming tasks due to their complex compositions and reaction mechanisms. The European Union (EU) has identified the rapid development of innovative catalyst technologies as a critical priority for achieving its Green Deal objectives. The €30 million funding for the ASCEND project reflects this strategic necessity, indicating that AI-driven catalyst discovery is becoming a major pillar in European R&D.

Future Outlook

The ASCEND project is poised to have a significant impact on shaping the future of catalyst discovery. Moving forward, this closed-loop AI-driven system is expected to be deployed for specific industrial applications such as automotive exhaust catalysts, biofuel production catalysts, and plastic recycling catalysts. Furthermore, insights gained from this platform will establish general principles for catalyst design, with ripple effects across other materials science fields. The success of ASCEND is projected to serve as a powerful model for how Europe can leverage AI and automation to accelerate the transition to a sustainable chemical industry and clean energy.

Get our weekly technology intelligence — free

Receive an infographic that lets you judge at a glance whether each field’s analysis report is worth reading.

Subscribe Free — Weekly Tech Intelligence

By subscribing, you’ll receive Troy-Technical’s weekly technology intelligence newsletter.

• Your email and selected fields are used only to deliver the newsletter.
• We never share your information with third parties.
• You can unsubscribe anytime via the link in each email.

See our Privacy Policy for details.

Agree & Continue ▶

Takes about a minute · Unsubscribe anytime