(6hz) Process Design and Optimization Leveraging Multiscale Modeling and Machine Learning | AIChE

(6hz) Process Design and Optimization Leveraging Multiscale Modeling and Machine Learning


Gao, H. - Presenter, Massachusetts Institute of Technology
Research Interests:

Computation and modeling have played an important role in chemical engineering on multiple scales. For example, microkinetic modeling provides ways of exploring complex reaction systems for which experimental measurements are challenging; Optimization algorithms can be used to guide efficient design of experiments and improvement of processes. More recently, the advance of data science and machine learning has also demonstrated their strength in elucidating complicated patterns from molecular structures and reaction systems. While they have been powerful individually, the synergies between these multi-scale modeling techniques would provide much more benefits. I am excited about combining these modeling techniques, both theoretical and data-driven, to study chemical reaction and process systems, in order to better elucidate the underlying implications of experimental results and thus enabling more effective experimental efforts and speed up process development and optimization.

Research Experiences:

My PhD dissertation at Northwestern University focuses on simulation and optimization of radical polymerization processes, combining mechanistic kinetic modeling and optimization algorithms. I developed schemes to accelerate kinetic Monte Carlo (KMC) method, which is used to simulate the explicit sequence of polymer chains during polymerization process. These methods significantly reduced the computational cost of KMC simulations so that they were successfully incorporated into derivative-free optimization algorithms to design and optimize polymer sequence distributions.

During my post-doc at MIT, I worked on a large collaborative project on synthesis route design and evaluation for organic molecules. Specifically, I developed a hierarchical neural network model trained on large reaction databases to recommend conditions (catalyst, reagent and solvent) for given organic molecules with a high accuracy. Embeddings extracted from the model were used to quantify the similarity of solvents/reagents/catalysts and compatibility of reactions, which aids pathway-level evaluation of synthetic routes. I also quantified model uncertainty to indicate whether or not a reaction is out of scope, which can inform reaction evaluation and retrosynthesis.

Teaching Interests:

As a chemical engineer by training, I am capable of and passionate about teaching core chemical engineering courses in general. I am especially enthusiastic about and good at developing interactive class sessions that provokes creative and critical thinking. During the 4thyear of my PhD, I participated in the Teaching Apprenticeship Program at Northwestern University and taught half of the graduate class, Chemical Kinetics and Reactor Design, with Prof. Justin Notestein. Some lectures on stochastic kinetic modeling were very popular and I was invited to give the lectures again the next year. I have also been the teaching assistant for multiple classes including Phase Equilibrium and Staged Separations, Analysis of Chemical Process Systems, and Chemical Engineering Design Projects.


  • Gao, H., Struble, T. J., Coley, C. W., Green, W. H., Jensen, K. F. (2018). Using Machine Learning to predict suitable conditions for organic reactions. Submitted for publication in ACS Central Science.
  • Gao, H., Konstantinov, I. A., Arturo, S. G., Broadbelt, L. J.(2018). A Simulation-based Derivative-free Optimization Framework Using the Kinetic Monte Carlo Method for Controlling Polymer Molecular Weight and Sequence Distribution Synthesized via Free Radical Polymerization. Computers & Chemical Engineering, 108, 268-275.
  • Gao, H., Konstantinov, I. A., Arturo, S. G., Broadbelt, L. J. (2017). On the Modeling of Number and Weight Average Molecular Weight of Polymers. Chemical Engineering Journal, 327, 906-913
  • Gao, H., Konstantinov, I. A., Arturo, S. G., Broadbelt, L. J. (2016). Acceleration of Kinetic Monte Carlo Simulations for Free Radical Copolymerization: a Hybrid Approach with Scaling of Kinetic Parameters. AIChE Journal, 63(9), 4013-4021.
  • Gao, H., Oakley, L. H., Konstantinov, I. A., Arturo, S. G., Broadbelt, L. J. (2015). Acceleration of Kinetic Monte Carlo Method for the Simulations of Free Radical Copolymerization through Scaling. Industrial & Engineering Chemistry Research, vol. 54(48), 11975-11985. Selected as the ACS Editor’s Choice for October 26th, 2015
  • Regatte, V. R., Gao, H., Konstantinov, I. A., Arturo, S. G. and Broadbelt, L. J. (2014). Design of Copolymers Based on Sequence Distribution for a Targeted Molecular Weight and Conversion. Theory Simul., vol. 23 (9), 564-574
  • Leperi, K., Gao, H., Snurr, R.Q., & You, F. (2014). Modeling and Optimization of a Two-stage Mof-based Pressure/vacuum Swing Adsorption Process Coupled with Material Selection. Proceedings of the 17th Conference on Process Integration, Modelling and Optimization for Energy Saving and Pollution Reduction (PRES). Chemical Engineering Transactions, 39, 277-282
  • Zhang, G.; Zhang, L.; Gao, H.; Konstantinov, I. A.; Arturo, S. G.; Yu, D.; Torkelson, J. M.; Broadbelt, L. J. (2016). A Combined Computational and Experimental Study of Copolymerization Propagation Kinetics for 1-Ethylcyclopentyl methacrylate and Methyl methacrylate. Macromol. Theory Simul., vol. 25(3), 263-273