Computational Modeling and Simulation Lab

At the Informatics Institute in Istanbul Technical University, we specialize in advancing the fields of biomechanics and cardiovascular medicine through cutting-edge computational research. Our team, which includes experts in computational fluid dynamics, cardiovascular mechanics, biomedical engineering and advanced simulation technologies, works to understand how vascular system operates. We collaborate closely with doctors and other medical professionals to ensure our research translates into real-world solutions that improve human health and medical technologies. Join us in exploring how our innovative work is shaping the future of biomedical engineering and cardiovascular biomechanics.

Interested in becoming part of our interdisciplinary research team? Join us to explore academic and research opportunities in computational biomechanics, AI-CFD, developing VR applications, modelling and simulation.

We are also currently seeking interns and volunteer undergraduate students who are eager to contribute to ongoing projects and gain hands-on research experience in a dynamic academic environment.

PhD Candidate Afrah Farea Introduces a New QCPINN: A Quantum-Classical Approach to Solving PDEs

by Hacer Duzman | Sep 26, 2025
Physics-informed neural networks (PINNs) are widely recognised as powerful tools for solving partial differential equations (PDEs) by embedding physical laws directly into neural network architectures.
Afrah_QCPINN

Physics-informed neural networks (PINNs) are widely recognised as powerful tools for solving partial differential equations (PDEs) by embedding physical laws directly into neural network architectures. Yet, classical PINN models often require a very large number of parameters to reach acceptable accuracy, making them computationally demanding especially for complex PDEs.

To address this challenge, Afrah Farea, a PhD candidate has introduced the Quantum-Classical Physics-Informed Neural Network (QCPINN), a framework that integrates quantum and classical computing components. This approach enables the solution of PDEs with significantly fewer parameters, while maintaining accuracy and convergence rates comparable to classical PINNs.

The full implementation is available open-source on GitHub.

Leave a comment

Events

Show All