About

Michael Baldea is the Henry Beckman Professor in the McKetta Department of Chemical Engineering and a core faculty member in the Institute for Computational Engineering and Sciences (ICES) at The University of Texas at Austin. He earned his Diploma and M.Sc. in Chemical Engineering from "Babes-Bolyai" University in Cluj-Napoca, Romania, and completed his doctorate in Chemical Engineering at the University of Minnesota. Before joining The University of Texas, he held industrial research positions at Praxair Technology Center in Tonawanda, NY, and GE Global Research in Niskayuna, NY. His research interests focus on the dynamics, optimization, and control of process and energy systems. He has co-authored three books, five book chapters, and over 200 peer-reviewed journal and conference articles in these areas. Dr. Baldea serves as the Executive Editor of Industrial & Engineering Chemistry Research and has received numerous awards and distinctions, including the AIChE Institute Award for Excellence in Industrial Gases Technology (2019), the NSF CAREER award (2015-2020), and the Outstanding Young Researcher Award from the Computing and Systems Technology Division of AIChE (2017).

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Mathematical optimization
• Engineering
• Control engineering
• Industrial engineering
• Physical chemistry
• Physics
• Biological system
• Mathematics
• Thermodynamics
• Operations research
• Materials science
• Chemistry

Selected publications

• Plasma-Enabled Active Site Regeneration for Selective Liquid Fuel Production across Catalyst Binding Regimes in CH4-CO2 Conversion

  ChemRxiv · 2026-02-18

  articleOpen access

  The selective conversion of CH4 and CO2 to liquid fuels is constrained in thermal catalysis by linear scaling relationships, overoxidation of oxygenate intermediates, and irreversible surface poisoning. Nonthermal plasma-enabled catalysis circumvents some of these limitations by introducing non-equilibrium excitation (e.g., vibrational, electronic, and dissociative) of molecular reactants. However, performance remains hindered by catalyst deactivation due to carbon and oxygen accumulation on active sites, driven by distinct mechanisms tied to metal-adsorbate interactions. Here, we show how continuous active-site regeneration during plasma-catalysis can be achieved by coupling plasma-driven dissociative chemisorption with targeted co-reactant activation. This strategy enables selective removal of surface poisons and is applicable across distinct catalyst regimes. On weakly binding catalysts like Cu, plasma-generated species remove adsorbed oxygen atoms, restore CH3O* intermediates and triple methanol selectivity. On strongly binding catalysts like Ni, accumulated CHx* fragments are selectively removed, doubling C2 hydrocarbon yields by reactivating C-C coupling. Unlike thermal systems, plasma excitation decouples regeneration from equilibrium constraints that correlate adsorption and desorption kinetics to a single gas temperature, enabling continuous, in situ removal of poisons without cycling and disrupting steady-state conversion. Using a combination of surface characterization methods and density functional theory calculations, we identify the mechanism by which plasma-co-reactant synergy tunes surface intermediates and redefines the design space of heterogeneous catalysis under mild conditions (Tsur = 473 K, Tvib = 4200 K, p = 1 atm).

  PublisherOA PDFDOI

• Using the SEKF to Transfer NN Models of Dynamical Systems with Limited Data

  arXiv (Cornell University) · 2026-03-02

  preprintOpen accessSenior author

  Data-driven models of dynamical systems require extensive amounts of training data. For many practical applications, gathering sufficient data is not feasible due to cost or safety concerns. This work uses the Subset Extended Kalman Filter (SEKF) to adapt pre-trained neural network models to new, similar systems with limited data available. Experimental validation across damped spring and continuous stirred-tank reactor systems demonstrates that small parameter perturbations to the initial model capture target system dynamics while requiring as little as 1% of original training data. In addition, finetuning requires less computational cost and reduces generalization error.

  PublisherDOI

• Festschrift Honoring Professor Phillip E. Savage

  Industrial & Engineering Chemistry Research · 2026-03-25

  articleCorresponding
  PublisherDOI

• A unified view of energy storage options for thermal process electrification

  Applied Energy · 2026-04-30

  article
  PublisherDOI

• A multiscale Bayesian optimization framework for process and material codesign

  AIChE Journal · 2026-02-10

  articleOpen access1st authorCorresponding

  Abstract The simultaneous design of processes and enabling materials such as solvents, catalysts, and adsorbents is challenging because molecular‐ and process‐level decisions are strongly interdependent. Sequential approaches often yield suboptimal results since improvements in material properties may not translate into superior process performance. We propose a multiscale Bayesian Optimization (BO) framework that explicitly couples molecular‐ and process‐level design in a bi‐level structure. The inner loop solves deterministic process models, while the outer BO loop explores molecular descriptors, reducing dimensionality, improving sample efficiency, and handling process constraints. A case study on multiscale reactor and catalyst codesign demonstrates that this hybrid strategy achieves optimal performance with substantially lower computational effort than direct BO over the full decision space. BO, when aligned with the natural process—material hierarchy—thus provides an efficient methodology for multiscale design.

  PublisherOA PDFDOI

• From continuous to interruptible distillation: Flexible electric heating column architecture with fast start‐up

  AIChE Journal · 2026-04-17

  articleOpen accessSenior authorCorresponding

  Abstract Electrification of distillation offers a promising route to reducing scope‐1 emissions from one of the chemical industry's most energy‐intensive unit operations. However, conventional adiabatic columns are dynamically inflexible: Long, energy‐intensive start‐ups make shutdown and restart impractical under variable electricity prices and renewable power availability. This work advances complementary dynamic and thermodynamic arguments for a new distillation architecture. Dynamically, a modular column design with hydraulic isolation preserves stage‐wise liquid holdup and composition during shutdown, enabling parallel stage reheating and rapid restart. Thermodynamically, distributed stage‐wise electric heating transfers heat along the column section, reducing exergy losses during transients. A unified dynamic model captures phase transitions, hydraulics, and control switching during shutdown and startup. A methanol‐water case study demonstrates a 79% reduction in startup time (20.1 h to 4.05 h), along with reductions in startup energy use and exergy losses of 56% and 58%, respectively. These results enable interruptible, demand‐responsive electrified distillation.

  PublisherDOI

• Using the SEKF to Transfer NN Models of Dynamical Systems with Limited Data

  arXiv (Cornell University) · 2026-03-02

  articleOpen accessSenior author

  Data-driven models of dynamical systems require extensive amounts of training data. For many practical applications, gathering sufficient data is not feasible due to cost or safety concerns. This work uses the Subset Extended Kalman Filter (SEKF) to adapt pre-trained neural network models to new, similar systems with limited data available. Experimental validation across damped spring and continuous stirred-tank reactor systems demonstrates that small parameter perturbations to the initial model capture target system dynamics while requiring as little as 1% of original training data. In addition, finetuning requires less computational cost and reduces generalization error.

  PublisherOA PDF

• Dynamic optimization for hydrogen pipeline network operations

  Computers & Chemical Engineering · 2026-04-07

  articleSenior author
  PublisherDOI

• A selective Kalman filtering approach to online neural network updating under system drift

  Scientific Reports · 2025-12-11

  articleOpen accessSenior author

  Neural network (NN) models often struggle to remain accurate when underlying systems drift from training conditions, necessitating costly and time-consuming model maintenance. Traditional approaches - such as full retraining or finetuning - are either computationally intensive or prone to generalization loss and require extensive hyperparameter tuning. To address these limitations, we propose the Subset Extended Kalman Filter (SEKF), an online learning method that updates only a strategically selected subset of network parameters to maintain model fidelity as system dynamics evolve. SEKF identifies the NN parameters with the greatest impact on prediction error by analyzing the gradient of the training loss function. It then applies Kalman filtering to update only these critical parameters when new data become available. This targeted adaptation preserves the network's structure while enabling efficient, real-time updates with predictable computational overhead and minimal manual effort. We validate SEKF through four case studies, ranging from synthetic systems to complex industrial processes, including a fluid catalytic cracker. Across all scenarios, SEKF outperforms conventional retraining and finetuning methods in both accuracy and efficiency, reducing computational time per iteration. The approach offers a practical path toward adaptive neural network deployment in industrial settings, where maintaining accuracy as the underlying physical system evolves.

  PublisherOA PDFDOI

• Fast Startup Dynamics of Diabatic Distillation with Electric Heating

  IFAC-PapersOnLine · 2025-01-01 · 2 citations

  articleOpen accessSenior authorCorresponding

  The electrification of process heating presents an opportunity to decarbonize distillation column operations and enhance operational strategies to save energy. Conventional column configurations are adiabatic and have low thermodynamic efficiencies due to heat degradation. Further, the startup process for conventional columns is slow and has significant energy requirements for re-establishing steady state hydraulic, composition, and flow profiles. In this paper, a speculative fully diabatic distillation column configuration with modular electric stage heating is introduced. A dynamic simulation model is built from first principles using a compartmentalization approach for equilibrium stages, as well as a hierarchical modeling framework for column control and auxiliary heating. We demonstrate that this structure has exceptionally small startup times compared to conventional columns through a simulation case study considering the binary separation of an equimolar mixture of acetic acid/propanol, as well as illustrate its significant energy savings over the startup period, which can translate into grid-integrated operating strategies for electrified distillation systems.

  PublisherDOI

Recent grants

• CAREER: Integrated Production Management and Process Control of Energy-Intensive Processes

  NSF · $500k · 2015–2021

• UNS: Sustainable Energy-Intensive Manufacturing via Demand Response Process Operations

  NSF · $269k · 2015–2019

• GOALI: A System Theoretical Framework for Modeling, Analysis and Closed-loop Management of Supply Chains of Perishable Products

  NSF · $453k · 2023–2027

• I-Corps: Robust Equation-oriented Chemical Process Optimizer

  NSF · $50k · 2017–2018

Frequent coauthors

• Thomas F. Edgar

  66 shared

• Pródromos Daoutidis

  University of Minnesota

  41 shared

• Calvin Tsay

  27 shared

• Richard C. Pattison

  Apeel Sciences (United States)

  27 shared

• Mark A. Stadtherr

  The University of Texas at Austin

  21 shared

• Rahul Bindlish

  Dow Chemical (United States)

  16 shared

• Leo H. Chiang

  Dow Chemical (United States)

  15 shared

• Fernando Lejarza

  The University of Texas at Austin

  15 shared

Labs

• UT Process and Energy Systems EngineeringPI

Education

• Ph.D., Chemical Engineering

  University of Minnesota

  2006

• M.S., Interface Process Engineering

  “Babeş-Bolyai” University

  2001

• Other, Chemical Engineering

  “Babeş-Bolyai” University

  2000

Awards & honors

• Institute Award for Excellence in Industrial Gases Technolog…
• Outstanding Young Researcher Award – Computing and Systems T…
• CAREER Award – National Science Foundation (2015-2020)
• Moncrief Grand Challenges Faculty Award – Oden Institute for…