Data-Driven Process Systems Engineering Lab
At the Data-Driven Process Systems Engineering Lab, we develop hybrid mathematical models and optimization tools to understand, analyze, discover and design complex process systems operating under constraints and competing objectives. Our research spans multiple scales—from molecular and particle-level interactions to single process, to integrated systems, to enterprise-wide operations.
Highlights
Our Publications
By integrating data-analytics, machine learning, and operations research with chemical engineering principles, we create next-generation decision-making frameworks that enable the discovery of nontrivial, high-impact solutions —solutions that were previously unattainable. By leveraging diverse data sources and multifidelity simulations, we can now learn correlations and patterns that become objectives and constraints for the optimization of economical and sustainable process systems.
Our Projects and Tools
Our hybrid process-informed machine learning approaches have contributed to advancements in carbon capture system design, resilient power grid operations, plastics recycling technologies, and bioprocess optimization. We also have a strong interest in developing tools that can be used by us and others to tackle pressing engineering challenges, reinforcing our commitment to creating scalable, impactful, and sustainable solutions for the future.
Our Team
Meet the talented current researchers and alumni who drive innovation in the Data-Driven Process Systems Engineering Lab. We are a collegial and collaborative group, supporting each other as we tackle complex challenges. We foster a dynamic and inclusive environment where teamwork, mentorship, outreach and a shared passion for computational research go hand in hand—with plenty of fun along the way!