Pro2Tech Research Cluster Machine Learning & Data Science

In an era marked by the rapid advancement of technology and availability of data, the Pro2Tech Machine Learning and Data Science Research Cluster is bridging research efforts and industry to bring new technologies to practice.

In our cluster, we have a clear vision for the future of machine learning and data science in industrial practice. To achieve this vision, we bring together researchers from key technical fields including computer science, chemical engineering, and control engineering.

This facilities the quick takeoff of our developments and long-term maintenance. Ultimately, we aim to create win-win situations creating value for all partners and society. To set this up, our technology and business developers help us to identify suitable partners, collaboration modes, and co-funding opportunities.

The cluster's research is divided into three primary areas of focus:

1. Machine Learning for Process Operation: This area explores the application of machine learning techniques to enhance process engineering, including the use of soft sensors for monitoring and control. By leveraging data-driven models, the cluster aims to improve the efficiency, reliability, and sustainability of manufacturing and processing operations. Topics of interest include predictive maintenance, process optimization, and the integration of IoT technologies to create smart, adaptive systems.
2. Machine Learning for Process Design and Development: This area aims to support the process design and development to optimize process efficiency, reduce time-to-market, and enhance the sustainability. Key endeavors include hybrid modeling, surrogate modeling, and (superstructure) optimization. Moreover, we develop generative AI methods for the design of novel (chemical) processes.
3. Machine Learning for Product Engineering: In the realm of product engineering, the cluster seeks to revolutionize the design and development of new materials and chemicals through molecular machine learning. This innovative approach combines computational chemistry, biology, and machine learning to predict molecular properties and behaviors, accelerating the discovery and creation of novel materials and molecules for a wide range of applications. Areas of exploration include drug discovery, material science, and the development of environmentally friendly chemicals and materials.

The Machine Learning and Data Science Research Cluster is committed to advancing fundamental research, as well as applying its findings to real-world applications. By working closely with industry partners and other academic disciplines, the cluster aims to not only push the boundaries of what is scientifically possible but also to deliver practical, impactful solutions that address the pressing needs of society.

Key topics of interest for the cluster include:

• Advanced algorithms for machine learning and data analysis.
• Development and implementation of soft sensors in industrial settings.
• Computational methods for molecular property prediction and material design.
• Data-driven optimization of process engineering and product development.
• Integration of artificial intelligence with traditional engineering disciplines to create innovative solutions.

The overarching goal of the Machine Learning and Data Science Research Cluster is to lead the way in the application of machine learning and data science in engineering. By fostering a collaborative environment that bridges the gap between theoretical research and practical application, the cluster aims to make significant contributions to the fields of process and product engineering, ultimately enhancing efficiency, sustainability, and innovation.