Research Activities

Our research lies at the intersection of process systems engineering, life cycle assessment, mathematical optimization, and artificial intelligence (AI)/machine learning (ML). We focus on energy-critical systems across chemical, environmental, and biological domains. Driven by growing resource constraints—especially water scarcity—we aim to rethink conventional production systems and uncover how water management strategies influence energy production and sustainability.

Process Design for Energy, Water, & Critical Minerals Recovery

We develop novel processes for sustainable energy generation, water treatment, and recovery of critical minerals such as lithium, with an emphasis on circularity, heat integration, and resource reuse. Our work spans desalination, brine management, and separation technologies, supported by techno-economic analysis (TEA) and life cycle assessment (LCA) to evaluate performance, cost, and environmental impact.

Process Flowsheet for Lithium Extraction from Geothermal Brines. Nikkhah et al. Resources, Conservation and Recycling 212 (2025): 107980.

Selected Publications:

  • H Nikkhah, A Di Maria, G Granata, B Beykal. Sustainable process design for lithium recovery from geothermal brines using chemical precipitation, Resources, Conservation and Recycling, 2025, 212, 107980.
  • H Nikkhah, D Ipekci, W Xiang, Z Stoll, P Xu, B Li, JR McCutcheon, B Beykal. Challenges and opportunities of recovering lithium from seawater, produced water, geothermal brines, and salt lakes using conventional and emerging technologies, Chemical Engineering Journal, 2024, 498, 155349.
  • H Nikkhah, B Beykal. Process Design and Technoeconomic Analysis for Zero Liquid Discharge Desalination via LiBr Absorption Chiller Integrated HDH-MEE-MVR System, Desalination, 2023, 558, 116643.
  • H Nikkhah, B Beykal, MD Stuber. Comparative life cycle assessment of single-use cardiopulmonary bypass devices. Journal of Cleaner Production, 2023, 425, 138815.

 

Artificial Intelligence & Machine Learning for Process Systems Engineering

We leverage AI and machine learning to advance the modeling, optimization, and control of complex process systems. Our work includes discovering governing equations through symbolic regression and explainable AI, identifying feasible and optimal operating regions using reinforcement learning, and applying these tools to challenges in environmental health, reactor modeling, and oil reservoir management.

Application of machine learning algorithms for identifying the endocrine disrupting potential of toxic chemicals. Aghayev et al. Chemical Engineering Science, 2023, 281, 119086.

Selected Publications:

  • BG Cohen, B Beykal, GM Bollas. Physics-informed genetic programming for discovery of partial differential equations from scarce and noisy data, Journal of Computational Physics, 2024, 514, 113261.
  • Z Aghayev, D Voulanas, E Gildin, B Beykal. Surrogate-Assisted Optimization of Highly Constrained Oil Recovery Processes Using Classification-Based Constraint Modeling, Industrial & Engineering Chemistry Research, 2025, 64, 15, 7751–7766.
  • Z Aghayev, AT Szafran, A Tran, HS Ganesh, F Stossi, L Zhou, MA Mancini, EN Pistikopoulos, B Beykal. Machine Learning Methods for Endocrine Disrupting Potential Identification Based on Single-Cell Data. Chemical Engineering Science, 2023, 281, 119086.
  • Y Zhang, A Purohit, Z Aghayev, Y Wang, J Liang, B Beykal, Y Luo, M Qiao. Optimization and evaluation of a simplified green biorefinery for alginate extraction from sugar kelp (Saccharina latissima), International Journal of Biological Macromolecules, 2025, 309(4), 143147.

 

 

Process Operations & Supply Chain Management

Surrogate-Assisted Optimization of Highly Constrained Oil Recovery Processes. Aghayev et al. Industrial & Engineering Chemistry Research, 64(15), 7751-7766.

We design integrated frameworks for planning, scheduling, and real-time operations to enhance efficiency and sustainability in process industries. Our work includes waterflooding optimization for reservoir management and multi-echelon supply chain modeling and optimization under demand uncertainty.

Selected Publications:

  • Z Aghayev, D Voulanas, E Gildin, B Beykal. Surrogate-Assisted Optimization of Highly Constrained Oil Recovery Processes Using Classification-Based Constraint Modeling, Industrial & Engineering Chemistry Research, 2025, 64, 15, 7751–7766.
  • H Nikkhah, Z Aghayev, A Shahbazi, VM Charitopoulos, S Avraamidou, B Beykal. Bi-level data-driven enterprise-wide optimization with mixed-integer nonlinear scheduling problems, Digital Chemical Engineering, 2025, 14, 100218.
  • B Beykal, S Avraamidou, EN Pistikopoulos. Data-Driven Optimization of Mixed-integer Bi-level Multi-follower Integrated Planning and Scheduling Problems Under Demand Uncertainty, Computers & Chemical Engineering, 2022, 156, 107551.
  • S Kivanc, B Beykal, O Deliismail, H Sildir. Dynamic and Stochastic Optimization of Algae Cultivation Process, Computers & Chemical Engineering, 2025, 198, 109087.

 

Data-Driven Optimization & Algorithms

We develop advanced optimization algorithms to address complex large-scale engineering problems in a computationally efficient way. Our work focuses on high-dimensional, highly constrained nonlinear optimization; bi-level mixed-integer nonlinear optimization; and multi-objective optimization. Applications span food-energy-water nexus, integrated planning and scheduling, and energy systems design.

DOMINO: Data-driven Optimization of bi-level Mixed-Integer NOnlinear Problems. Beykal et al. Journal of Global Optimization, 78(1), 1-36.

Selected Publications:

  • B Beykal, EN Pistikopoulos. Chapter 5 – Data-Driven Optimization Algorithms. Artificial Intelligence in Manufacturing. Academic Press, 2024, Paperback ISBN: 9780323991346, eBook ISBN: 9780323996723.
  • B Beykal, S Avraamidou, IPE Pistikopoulos, M Onel, EN Pistikopoulos. DOMINO: Data-driven Optimization of bi-level Mixed-Integer NOnlinear Problems. Journal of Global Optimization, 2020, 78, 1–36.
  • B Beykal, F Boukouvala, CA Floudas, EN Pistikopoulos. Optimal Design of Energy Systems Using Constrained Grey-Box Multi-Objective Optimization. Computers & Chemical Engineering, 2018, 116, 488-502.
  • B Beykal, F Boukouvala, CA Floudas, N Sorek, H Zalavadia, E Gildin. Global Optimization of Grey-Box Computational Systems Using Surrogate Functions and Application to Highly Constrained Oil-Field Operations. Computers & Chemical Engineering, 2018, 114, 99-110.