Mr. Filip Rękas | Computational Modeling | Best Researcher Award

Rzeszów University of Technology, Poland

Profiles

• ORICD Profile

Early Academic Pursuits

Mr. Filip Rękas began his academic journey at the Rzeszów University of Technology in Poland, where he earned both his Bachelor of Engineering and Master of Science in Engineering in Chemical Technology. He graduated with the highest distinction (5.0 / A) for his master’s degree. His early interests centered on polymer synthesis, process modeling, and Monte Carlo simulations, which laid the groundwork for his computational research career.

Professional Endeavors

Currently a PhD student in Chemical Engineering, Mr. Rękas focuses on advanced computational techniques, particularly the integration of machine learning into chemical process modeling and optimization. A self-taught programmer, he independently develops customized simulation software and machine learning models that bridge the gap between chemical engineering and artificial intelligence. His research embodies an interdisciplinary approach, combining classical engineering, computer science, and applied mathematics.

Contributions and Research Focus

Mr. Rękas specializes in machine learning applications for chemical engineering, with a specific focus on physics-informed neural networks (PINNs) for solving complex partial differential equations. His models, named A1 and A2, have demonstrated the ability to predict concentration profiles in gradient liquid chromatography (GLC) under various elution conditions. These include nonlinear gradients, fast and slow gradient adjustments, and systems with mass transfer resistances. By embedding system dynamics into the loss functions of the neural networks, he achieved high prediction accuracy while reducing computation time by a factor of 272 compared to the OCFE method—highlighting his contributions to real-time process optimization.

Collaborations

Mr. Rękas collaborates with several prominent researchers. He works closely with Prof. Krzysztof Kaczmarski, an internationally recognized expert in chromatographic modeling and process scale-up, and with Dr. Eng. Marcin Chutkowski, a specialist in powder process modeling using the Discrete Element Method (DEM). Their joint research involves applying machine learning to enhance gradient liquid chromatography. Additionally, he collaborates with Prof. Jaromir Lechowicz on modeling polymerization and degradation phenomena, using Monte Carlo simulations and artificial intelligence for advanced material behavior predictions.

Impact and Influence

Although early in his research career, Mr. Rękas has already contributed to high-impact computational methods that address complex chemical systems. His innovative use of machine learning in chemical process engineering demonstrates potential for revolutionizing process design and optimization in industry and academia. His work significantly reduces simulation times and enhances accuracy, which is critical for scalable and sustainable chemical manufacturing.

Academic Citations and Recognition

Mr. Rękas has published one peer-reviewed journal article and contributed a chapter to a scientific monograph (ISBN: 978-83-67881-52-4). While his citation count currently stands at 1, his work on PINNs and AI-driven chromatography modeling is rapidly gaining attention in specialized research communities.

Technical Skills

He possesses extensive programming and modeling skills, with a focus on physics-informed neural networks, graph neural networks (GCNs, GATs), recurrent networks (RNNs, LSTMs, GRUs), XGBoost, and SVMs. His technical toolkit includes Monte Carlo simulations, process modeling frameworks, and custom algorithm development—demonstrating both depth and versatility in computational chemical engineering.

Teaching and Mentorship

Though not formally a lecturer, Mr. Rękas actively shares his expertise with peers and junior researchers in machine learning applications and scientific programming, contributing to knowledge exchange in research groups and seminars within his university.

Legacy and Future Contributions

With a strong foundation in both chemical engineering and artificial intelligence, Mr. Rękas is poised to become a leading figure in data-driven chemical process innovation. His future goals include expanding the use of neural networks in real-time industrial systems, enhancing predictive modeling in chromatography and polymer science, and contributing to the broader adoption of AI in engineering. His work exemplifies a new generation of scientists blending scientific rigor with computational agility.

Notable Publications

Application of physics-informed neural networks to predict concentration profiles in gradient liquid chromatography
Authors: Filip Rękas, Marcin Chutkowski, Krzysztof Kaczmarski
Journal: Journal of Chromatography A
Year: 2025