Gabriel D. Patrón

Brief Biography:

My research group works at the intersection of process systems engineering and interpretable machine learning. We aim to mathematically model novel process systems, develop algorithms for autonomous process operation, and computationally design new processes and chemicals. We use tools like neural networks (e.g., quantile and physics-informed), decision trees, Bayesian and classical optimization, and process control to solve problems in sustainability, energy systems, electrification, and nanomedicine applications.

Current & Upcoming Research Projects

• Symbolic regression for real-time optimization of continuous processes.
• Physics-informed neural network-based control of semi-batch processes.
• Neural network surrogates for stochastic optimization of electrified processes.
• Learnable and interpretable decision-making for chemical plant planning.

Currently accepting graduate students? YES

• MASc
• PhD

Memberships

American Institute of Chemical Engineers (AIChE)
Canadian Society for Chemical Engineering (CSChE)
International Federation of Automatic Control (IFAC)

Research Interests

Our group seeks to employ interpretable ML to answer some of the most pressing questions in sustainability. To achieve this, we decompose the sustainable supply chain by spatiotemporal scale.

Process Scale Hybrid Real-Time Optimization:

Given a partial understanding of the mathematical models that govern new sustainable chemical processes, can their underlying phenomena be learned from data to determine optimal operating policies? We take a real-time approach to solve this problem, where plant inputs are optimized using learned models that adapt as the plant evolves dynamically.

System Scale End-to-End Demand Response Scheduling:

What non-market factors can be used to predict the markets involved in sustainable chemical and energy systems? Can these predictions be efficiently embedded into system models to achieve optimal performance while satisfying consumer demand? We use neural networks to learn market distributions and embed these into optimal system scheduling problems.

Nation Scale Learned Heuristics for Investment Planning:

What are the key decisions that influence the uptake of new sustainable chemical projects over time? Can we take a data-driven approach to isolate these factors? We aim to learn heuristic rules to produce interpretable policies that inform future technology investment.

Selected Publications

See a complete list of publications here

Langdon, B., Patrón, G.D., Kappatou, C.D., Lee, R.M., Shafei, B., Qing, J., Misener, R., van der Wilk, M., Tsay, C., 2026. Meta-Learning for Sample-Efficient Bayesian Optimisation of Fed-Batch Processes. arXiv:2605.05382.

Patrón, G.D., Zhang, D., Ghilardi, L.M.P., Blom, E., Goodridge, M., Solis, E., Hamidreza, J., Angarita, J., Ganesan, N., West, K., Shah, N., Tsay, C., 2025. Risk-constrained stochastic scheduling of multi-market energy storage systems. arXiv:2510.27528.

Patrón, G.D., Tsay, C., Ricardez-Sandoval, L, 2025. Deep-learning-aided modifier adaptation: synergies with process intensification. Chemical Engineering and Processing – Process Intensification 219, 110581.

Ghilardi, L.M.P., Patrón, G.D., Alcántara, A., Tsay, C, 2025. Integrated design and scheduling of hydrogen processes under uncertainty: a quantile neural network approach. Industrial & Engineering Chemistry Research.

Stordy, B.P.*, Sepahi, Z.*, Patrón, G.D., Yang, W., Goodson, A.D., Blackadar, C., Tavares, A.J., Lin, G., Malekjahani, A., Ling, B., Ravichandran, R., Hicks, D.R., Shapiro, M.G. Zhang, M., King, N.P., Baker, D., Ricardez-Sandoval, L.A., Chan, W.C.W., 2025. The Binding Affinities of Serum Proteins to Nanoparticles. Journal of the American Chemical Society 147(24), 20475–20492.

Patrón, G.D., Ricardez-Sandoval, L., 2024. Economically optimal operation of recirculating aquaculture systems under uncertainty. Computers and Electronics in Agriculture 220, 108856.

Patrón, G.D., Toffolo, K., Ricardez-Sandoval, L., 2024. Economic model predictive control for packed bed chemical looping combustion. Chemical Engineering and Processing – Process Intensification 198, 109731.

Patrón, G.D., Ricardez-Sandoval, L., 2022. An integrated real-time optimization, control, and estimation scheme for post-combustion CO2 capture. Applied Energy 308, 118302.

Patrón, G.D., Ricardez-Sandoval, L., 2020. A robust nonlinear model predictive controller for a post-combustion CO2 capture absorber unit. Fuel 265, 116932.