Publications

Last updated March 2024; please see Google Scholar for an up-to-date list.

Working Papers

• P Sosnin, C Tsay. Scaling mixed-integer programming for certification of neural network controllers using bounds tightening. [arXiv]
• A Alcántara, C Ruiz, C Tsay. A quantile neural network formulation for two-stage stochastic optimization. [arXiv]
• JP Folch, C Tsay, RM Lee, B Shafei, W Ormaniec, A Krause, M van der Wilk, R Misener. Transition constrained Bayesian optimization via Markov decision processes. [arXiv]
• JA Paulson, C Tsay. Bayesian optimization as a flexible and efficient design framework for sustainable process systems. [arXiv]
• J Huchette, G Muñoz, T Serra, C Tsay. When deep learning meets polyhedral theory: A survey. [arXiv]
• J Kronqvist, R Misener, C Tsay. P-split formulations: A class of intermediate formulations between big-M and convex hull for disjunctive constraints. [arXiv]

2024

• T McDonald, C Tsay, AM Schweidtmann, N Yorke-Smith. Mixed-integer optimisation of graph neural networks for computer-aided molecular design. Computers & Chemical Engineering, 185:108660, 2024. [doi]
• R Burtea, C Tsay. Constrained continuous-action reinforcement learning for supply chain inventory management. Computers & Chemical Engineering, 181:108518, 2024. (Invited for a special issue for FOCAPO/CPC 2023). [doi]

2023

• C Tsay, S Qvist. Optimal design and demand response operation of green hydrogen: bridging process and power grid models. AIChE Journal, 2023. (Invited for 2023 Futures Issue). [doi]
• JP Folch, RM Lee, B Shafei, D Walz, C Tsay, M van der Wilk, R Misener. Combining multi-fidelity modelling and asynchronous batch Bayesian optimization. Computers & Chemical Engineering, 172:108194, 2023. [doi]
• R Burtea, C Tsay. Safe deployment of reinforcement learning using deterministic optimization over neural networks. Computer Aided Chemical Engineering, 52:1643-1648. 33rd European Symposium on Computer Aided Process Engineering (ESCAPE), Athens, Greece, June 2023. [doi]
• JS Bermúdez, A del Rio Chanona, C Tsay. Distributional constrained reinforcement learning for supply chain optimization. Computer Aided Chemical Engineering, 52:1649-1654. 33rd European Symposium on Computer Aided Process Engineering (ESCAPE), Athens, Greece, June 2023. [doi]
• S Zhao, C Tsay, J Kronqvist. Model-based feature selection for neural networks: A mixed-integer programming approach. Lecture Notes in Computer Science. 17th International Conference on Learning and Intelligent Optimization (LION), Nice, France, June 2023. (48% acceptance rate). [arXiv]
• JP Folch, J Odgers, S Zhang, RM Lee, B Shafei, D Walz, C Tsay, M van der Wilk, R Misener. Practical path-based Bayesian optimization. NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World (RealML), New Orleans, LA, Dec 2023. [arXiv]
• S Zhang, JS Campos, C Feldmann, D Walz, F Sandfort, M Mathea, C Tsay, R Misener. Optimizing over trained GNNs via symmetry breaking. 37th International Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, Dec 2023. (CORE A*; 26.1% acceptance rate). [arXiv]

2022

• F Ceccon, J Jalving, J Haddad, A Thebelt, C Tsay, CD Laird, R Misener. OMLT: Optimization & Machine Learning Toolkit. Journal of Machine Learning Research, 23(349):1−8, 2022. (2022 COIN-OR Cup). [link]
• A Thebelt, J Wiebe, J Kronqvist, C Tsay, R Misener. Maximizing information from chemical engineering data sets: Applications to machine learning. Chemical Engineering Science, 252:117469, 2022. [doi]
• MT Kelley, C Tsay, Y Cao, Y Wang, J Flores-Cerrillo, M Baldea. A data-driven linear formulation of the optimal demand response scheduling problem for an industrial air separation unit. Chemical Engineering Science, 252:117468, 2022. [doi]
• A Thebelt, C Tsay, RM Lee, N Sudermann-Merx, D Walz, T Tranter, R Misener. Multi-objective constrained optimization for energy applications via tree ensembles. Applied Energy, 306:118061, 2022. [doi]
• Z Li, C Tsay. Defect detection in lyophilized drug products with convolutional neural networks. Patent US 11,263,738 B2 (World Patent WO2020081668A2), March 2022. [link]
• C Cronjaeger, RC Pattison, C Tsay. Tensor-based autoencoder models for hyperspectral produce data. Computer Aided Chemical Engineering, 49:1585-1590. 14th International Symposium on Process Systems Engineering, Kyoto, Japan, June 2022. [doi]
• A Thebelt, C Tsay, RM Lee, N Sudermann-Merx, D Walz, B Shafei, R Misener. Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spaces. 36th International Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, Nov 2022. (CORE A*; 25.6% acceptance rate). [arXiv]
• JP Folch, S Zhang, RM Lee, B Shafei, D Walz, C Tsay, M van der Wilk, R Misener. SnAKe: Bayesian Optimization with Pathwise Exploration. 36th International Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, Nov 2022. (CORE A*; 25.6% acceptance rate). [arXiv]

2021

• C Tsay. Sobolev trained neural network surrogate models for optimization. Computers & Chemical Engineering, 153:107419, 2021. (Invited for a special issue on Hybrid Data-Driven/Mechanistic Modeling in PSE). [doi]
• K Seo, C Tsay, TF Edgar, MA Stadtherr, M Baldea. Economic optimization of carbon capture processes using ionic liquids: Towards flexibility in capture rate and feed composition. ACS Sustainable Chemistry & Engineering, 9(13):4823–4839, 2021. [doi]
• C Tsay, J Kronqvist, A Thebelt, R Misener. Partition-based formulations for mixed-integer optimization of trained ReLU neural networks. 35th International Conference on Neural Information Processing Systems (NeurIPS), Virtual, Dec 2021. (CORE A*; 26% acceptance rate). [link]
• J Kronqvist, R Misener, C Tsay. Between steps: Intermediate relaxations between big-M and convex hull formulations. Lecture Notes in Computer Science, 12735: 299-314. 18th International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR), Vienna, Austria, July 2021. (CORE B; 40% acceptance rate). (Distinguished Paper Award). [doi]
• C Tsay, Y Cao, Y Wang, J Flores-Cerrillo, M Baldea. Identification and online updating of dynamic models for demand Response of an industrial air separation unit. IFAC-PapersOnLine, 54(3):140-145. 11th IFAC Symposium on Advanced Control of Chemical Processes (ADCHEM), Venice, Italy, June 2021. (Virtual). [doi]

2020

• K Seo, C Tsay, B Hong, TF Edgar, MA Stadtherr, M Baldea. Rate-based process optimization and sensitivity analysis for ionic-liquid-based post-combustion carbon capture. ACS Sustainable Chemistry & Engineering, 8(27):10242–10258, 2020. [doi]
• C Tsay*, F Lejarza*, MA Stadtherr, M Baldea. Modeling, state estimation, and optimal control for the US COVID-19 outbreak. Scientific Reports, 10:10711, 2020. (Editor’s choice: Epidemiological modelling). [doi]
• A Caspari*, C Tsay*, A Mhamdi, M Baldea, A Mitsos. The integration of scheduling and control: Top-down vs. bottom-up, Journal of Process Control, 91:50– 62, 2020. [doi]
• JM Simkoff, F Lejarza, MT Kelley, C Tsay, M Baldea. Process control and energy efficiency. Annual Review of Chemical and Biomolecular Engineering, 11:423– 445, 2020. [doi]
• C Tsay and M Baldea. Integrating production scheduling and process control using latent variable dynamic models, Control Engineering Practice, 94:104201, 2020. [doi]
• C Tsay, M Baldea. Non-dimensional feature engineering and data-driven modeling for microchannel reactor control. IFAC-PapersOnLine, 53(2):11295-11300. 2020 IFAC World Congress, Berlin, Germany, July 2020. (Virtual due to COVID-19). [doi]

2019

• C Tsay and M Baldea. 110th Anniversary: Bridging the time and length scales of process systems with data, Industrial & Engineering Chemistry Research, 58(36):16696-16708, 2019. [doi]
• C Tsay, RC Pattison, Y Zhang, GT Rochelle, M Baldea. Rate-based modeling and economic optimization of next-generation amine scrubbing carbon capture processes, Applied Energy, 252:113379, 2019. (Honorable Mention for 2020 AIChE Environmental Division Graduate Student Paper Award). [doi]
• C Tsay, A Kumar, J Flores-Cerrillo, M Baldea. Optimal demand response scheduling of an industrial air separation unit using data-driven dynamic models, Computers & Chemical Engineering, 126:22-34, 2019. [doi]
• C Tsay and M Baldea. Fast and efficient chemical process flowsheet simulation by pseudo-transient continuation on inertial manifolds, Computer Methods in Applied Mechanics and Engineering, 348: 935-953, 2019. [doi]
• C Tsay, Z Li. Automating visual inspection of lyophilized drug products with multi-input deep neural networks. IEEE 15th International Conference on Automation Science and Engineering (CASE), 1802-1807, Vancouver, Canada, August 2019. (IEEE Robotics & Automation Society Travel Award). [doi]
• C Tsay, A Kumar, TF Edgar, and M Baldea. Integrating steady-state and dynamic models for multi-scale flowsheet optimization: A steam-methane reforming case study. Computer Aided Chemical Engineering, 47:403-409. Foundations of Computer-Aided Process Design (FOCAPD), Copper Mountain, CO, July 2019. [doi]

2018

• C Tsay, RC Pattison, M Baldea. A pseudo-transient optimization framework for periodic processes: Pressure swing adsorption and simulated moving bed chromatography. AIChE Journal, 64(8): 2982-2996, 2018. (2022 AIChE CAST Division W. David Smith, Jr. Graduate Publication Award). [doi]
• LS Dias, RC Pattison, C Tsay, M Baldea, MG Ierapetritou. A simulation-based optimization framework for integrating scheduling and model predictive control, and its application to air separation units. Computers & Chemical Engineering, 113:139-151, 2018. [doi]
• C Tsay and M Baldea. Scenario-free optimal design under uncertainty of the PRICO natural gas liquefaction process. Industrial & Engineering Chemistry Research, 57(17):5868-5880, 2018. [doi]
• C Tsay, RC Pattison, MR Piana, M Baldea. A survey of optimal process design capabilities and practices in the chemical industry. Computers & Chemical Engineering, 112:180-189, 2018. [doi]
• C Tsay, M Baldea, J Shi, A Kumar, J Flores-Cerrillo. Data-driven models and algorithms for demand response scheduling of air separation units. Computer Aided Chemical Engineering, 44:1273-1278. 13th International Symposium on Process Systems Engineering (PSE), San Diego, CA, June 2018. [doi]

2017

• C Tsay, RC Pattison, M Baldea. A dynamic optimization approach to probabilistic process design under uncertainty. Industrial & Engineering Chemistry Research, 56(3): 8606-8621, 2017. [doi]
• C Tsay, RC Pattison, M Baldea, B Weinstein, SJ Hodson, RD Johnson. A superstructure-based design of experiments framework for simultaneous domain restricted model identification and parameter estimation. Computers & Chemical Engineering, 107:408-426, 2017. [doi]
• RC Pattison, C Tsay, M Baldea. Pseudo-transient models for multiscale, multiresolution simulation and optimization of intensified reaction/separation/recycle processes: Framework and a dimethyl ether production case study. Computers & Chemical Engineering, 105:161-172, 2017. [doi]
• C Tsay, RC Pattison, M Baldea. Equation-oriented simulation and optimization of process flowsheets incorporating detailed spiral-wound heat exchanger models. AIChE Journal, 63(9): 3778-3789, 2017. [doi]