2026
Graph-Based, Time-Warped Embedding for Time Series Analysis and Process Monitoring
K. Territo, J. A. Romagnoli. Industrial & Engineering Chemistry Research, Vol 65/Issue 8 (2026)
Process Systems Engineering Research Group
Welcome
Welcome to PSE@LSU, a research group at Louisiana State University focused on optimization, process control, data-driven modeling, and decision-making for complex chemical, energy, and manufacturing systems.
About PSE
What is Process Systems Engineering?
PSE is a field of engineering focused on the design, optimization, and control of complex systems. It combines mathematical modeling, data analysis, and computational tools to improve how processes are developed and operated across industries such as energy, manufacturing, materials, and sustainability. By integrating fundamental principles with advanced computational methods, PSE enables engineers to better understand system behavior, enhance performance, and ensure safe and efficient operation under a wide range of conditions. Our research is particularly focused on advancing the field through the application of Artificial Intelligence and Machine Learning, enabling data-driven insights, adaptive decision-making, and next-generation solutions for complex industrial systems.
Research Areas
PSE at the Intersection of AI
Process Systems & Control
Optimization, advanced control strategies, and decision-making frameworks for complex chemical and energy systems, from unit operations to refinery-scale processes.
Data-Driven Modeling & Monitoring
Developing process models of industrial systems to gain insights into their behavior, optimize performance, and ensure safe and efficient operation.
AI for Chemical & Materials Systems
Application of artificial intelligence and machine learning to molecular design and materials discovery.
Intelligent Systems & Automation
AI-assisted decision-making, agentic frameworks, and autonomous systems for next-generation process operations and human-in-the-loop intelligence.
Our Group
Collaborative, Diverse, and Experienced.
Available Products
Easy to use. Advanced features. Better insights.
FastMAN
Data-driven tool for dimensional reduction, clustering, and visualization to extract insights from large multivariate datasets.
SimWiz
Interactive platform to simulate chemical plants with a user-friendly, no-programming interface.
ProcessLens
Study plant operations with advanced analytics and LLM-assisted insights.
MolDesignAI
AI-guided molecular exploration, property prediction, and molecule generation.
GeauxTune
Software tool to help teach traditional process control concepts.
TigerSense
Unified platform for real-time data processing and AI-driven reasoning.
TigerChem
Interactive computational platform for molecular property research.
AUTO-PILOT
Reinforcement learning-based platform for autonomous process control.
WARP-MaP
Framework for uncovering time series dynamics through warped data alignment.
Resources
Supporting Textbooks and Learning Resources
Publications
Recent publications
2026
Toward harnessing AI for surfactant chemistry: Prediction of critical micelle concentration
G.T. Marchan, T.O. Balogun, K. Territo, D. Das, T. Olayiwola, R. Kumar, J. A Romagnoli. Computational Materials Science, Vol. 265, pp.114548 (2026)
2026
Uncovering Structure–Conductivity Relationships in Anion Exchange Membranes (AEMs) Using Interpretable Machine Learning
P. Naghshnejad, D. Das, J. A. Romagnoli, R. Kumar, J. Chen. Membranes, 16(1), 12 (2026). DOI
Thanks to our Supporters
Sponsors and Collaborators
Get in Touch
Interested in collaborating with us?
Contact the group to discuss research partnerships, student opportunities, and more.
email: jose@lsu.edu