Staff Scientist in
Machine learning
at Illumina

Interested in working and teaching machine learning
for process optimization, modeling and control engineering

Find Out More


Research interests

Machine Learning for Automating Process Design and Control
Policy Optimization using Reinforcement Learning
Hybrid Modeling For Pharmaceutical Applications
Model-Based Design of Experiment Under Uncertainty
Feedback Control Theory And Its Applications

Selected Publications (More Here)

Safe model-based design of experiments using Gaussian processes
P. Petsagkourakis,F. Galvanin
2021, Computers & Chemical Engineering
Real-Time Optimization Meets Bayesian Optimization and Derivative-Free Optimization: A Tale of Modifier Adaptation
P. Petsagkourakis, E. A. del Rio-Chanona, E. Bradford, J. E. Alves Graciano, B. Chachuat
2021, Computers & Chemical Engineering
Simultaneous Process Design and Control Optimization using Reinforcement Learning
S. Sachio, E. A. del Rio-Chanona, P. Petsagkourakis
2020, Machine Learning 4 Engineering, 34th Conference on Neural Information Processing Systems (NeurIPS 2020)
Simultaneous Process Design and Control Optimization using Reinforcement Learning
E. Pan, P. Petsagkourakis, M. Mowbray, D. Zhang, E. A. del Rio-Chanona
2020, Challenges of Real-World Reinforcement Learning , 34th Conference on Neural Information Processing Systems (NeurIPS 2020)
Chance Constrained Policy Optimization for Process Control and Optimization
P. Petsagkourakis, E. Bradford, I.O. Sandoval, F. Galvanin, D. Zhang, E.A. del Rio-Chanona
2020, Review
Constrained Reinforcement Learning for Dynamic Optimization under Uncertainty
P. Petsagkourakis, E. Bradford, I.O. Sandoval, D. Zhang, E.A. del Rio-Chanona
2020, IFAC World Congress 2020
Reinforcement Learning for Batch Bioprocess Optimization
P. Petsagkourakis, E. Bradford, I.O. Sandoval, D. Zhang, E.A. del Rio-Chanona
2020, Computers & Chemical Engineering
Robust Stability of Barrier-Based Model Predictive Control
P. Petsagkourakis, W. P. Heath, J. Carrasco, C. Theodoropoulos
2020, Transactions on Automatic Control (Accepted)
Stability analysis of piece-wise affine systems with multi-model predictive control
P. Petsagkourakis, W. P. Heath, C. Theodoropoulos
2020, Automatica
Hybrid physics-based and data-driven modeling for bioprocess online simulation and optimization
D. Zhang, E.A. Del Rio-Chanona, P. Petsagkourakis, J. Wagner
2019, Biotechnology and bioengineering
Reduced order optimization of large-scale nonlinear systems with nonlinear inequality constraints using steady state simulators
P. Petsagkourakis, W. P. Heath, C. Theodoropoulos
2019, Chemical Engineering Research and Design
Reduced order optimization of large-scale nonlinear systems with nonlinear inequality constraints using steady state simulators
P. Petsagkourakis, I. Bonis, C. Theodoropoulos
2018, Industrial and Engineering Chemistry Research


Process system engineering research scientist with a strong background in machine learning and control to successful generate safe and reliable control systems based on partial knowledge and data of the process.
Excellent team player and reliable builder of prolific collaborations with four different universities in different aspects of basic and applied research resulting in successful research projects and >10 peer-reviewed publications.
As a research scientist, I not only provide creative solutions, I am seeking for excellence resulting in 11 academic awards in my career.
Collaborations across different contexts and teams (National Technical University of Athens, University of Manchester, University College London, University of Leeds, Imperial College London)

Suggested Books


Convex Analysis by R.T. Rockafellar
One of my favourite books to learn theory of optimization. It is an advanced book, but the chapters have been constructed to be as independent as possible. You can refer to this book to find more details or theoretical understanding of a specific subject.
Convex Optimization by S. Boyd and L. Vandenberghe
Great resourse for convex optimization, it contains a great amount of theoretical conceptes, deriviations, examples and exersice to familiarize with most consepts in convex optimization.
Numerical Optimization by J. Nocedal and S. J. Wright
Classic book for numerical methods in optimization. It is a great sourse from beginners to advanced readers.
Primal-Dual Interior-Point Methods by S. J. Wright
A specialized book in iterior-point method. This book will give you a good understanding of practical and computational aspects.
Nonlinear and Mixed-Integer Optimization: Fundamentals and Applications by C. Floudas
Great about mixed-integer nonlinear optimization, mainly convex. There are many illustrative and practical examples to graps the otherwise complex concepts.

Dynamic Optimization and Optimal Control

Nonlinear and Dynamic Optimization: From Theory to Practice by B. Chachuat
Dynamic optimization and optimal control is fun subject to read. This book offers a great balance of introductory and advanced concepts, as well as illustrative examples.
Dynamic Programming and Optimal Control by D. P. Bertsekas
Great sourse for dynamic programming and optimal control. This book can serve as introduction to theoretical aspects of dynamic programming and Markovian decision problem.
Optimal Control by R. Vinter
In this book, you can find theory of optimal control in terms of calculus of variations with special emphasis on nonsmooth analysis
Model Predictive Control: Theory, Computation, and Design by J. B. Rawlings, D. Q. Mayne and M. M. Diehl
Certainly one of my favourite books. This book has a great introduction to model predictive control (MPC), it provides great theoretical aspects, and advanced schemes of MPC. The 2nd edition also have some practical examples close related to dynamic optimization

Control Systems

Essentials of Robust Control by K. Zhou and J. C. Doyle
Foundamental aspects of robust control theory, provides theory, examples and analysis of classic control H2 control and balanced model reduction.
The Analysis of Feedback Systems by J. C. Willems
This is certainly an advanced book that provides mainly theoritical aspects of input-output analysis of dynamic systems for feedback control.
Feedback Systems: Input-Output Properties by C. A. Desoer and M. Vidyasagar
Each chapter in this book contains a comprehensive analysis of interconnected systems in closed-loop. It also provides some great appendices for concepts like Fourier transofrmations, integrals etc.

Machine Learning

Deep Learning by I. Goodfellow, Y. Bengio and A. Courville
The Deep Learning book has become a classic resource for both students and practitioners of machine learning. It covers almost huge range of deep learning and provides theory and practice.
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow by A. Géron
Great book for learning to apply the machine learning technques. This book is not recommending for theoretical understanding.
Reinforcement Learning: An Introduction by R. Sutton and A. Barto
Reinforcement learning has gained a significant attention in the machine learning community, and this book contain great introduction to concepts and algorithms.

Let's Get In Touch!

If you are interested in collaborating, send me an email and I will get back to you as soon as possible!