IN-DEEP - DOCTORAL CANDIDATES

Shima Baharlouei (Doctoral Candidate #1, UPV/EHU, Spain)

Short bio: My research interests lie at the intersection of Numerical Analysis, Scientific Computing, and Machine Learning. Currently, I work on developing and analyzing numerical methods for solving Partial Differential Equations (PDEs), employing techniques such as Deep Neural Networks (including Physics-Informed Neural Networks – PINNs) and Discontinuous Galerkin methods. I have also contributed to developing specific approaches, such as the Least-Squares-based Neural Network (LS-Net), for tackling parametric PDEs. I hold prior degrees (BSc and MSc) in Applied Mathematics from universities in Iran.

PhD research topic: Optimized explainable deep learning algorithms for inverse problems. Applications in geophysics.

Host institution: University of the Basque Country (UPV/EHU), Bilbao, Spain

PhD Enrolment: University of the Basque Country (UPV/EHU), Bilbao, Spain

Supervisors: Dr. David Pardo, University of the Basque Country (UPV/EHU, Spain), Dr. Judit Muñoz-Matute, Basque Center for Applied Mathematics (BCAM, Spain)

Ivan Bioli (Doctoral Candidate #2, University of Pavia, Italy)

Short bio: I am pursuing a PhD in "Computational Mathematics, Learning, and Data Science" at the Università di Pavia. My research focuses on developing efficient and mathematically grounded deep learning methods for PDEs, with applications to inverse problems in computational oncology. My academic interests span numerical methods for PDEs, numerical linear algebra, and scientific machine learning. I hold an MSc in Computational Science and Engineering from EPFL and a BSc in Mathematics from the University of Pisa. Previously, I interned with the Alfa Romeo ORLEN F1 Team, contributing to AI-driven race strategy optimization. Looking ahead, I aim to become a modern computational scientist, combining strong mathematical foundations with the ability to address real-world problems, whether in academia or industry.

PhD research topic: Mathematically certified deep learning algorithms for inverse problems governed by PDEs. Application to the personalized treatment plans in oncology

Host institution: University of Pavia (UniPV), Italy

PhD Enrolment: University of Pavia (UniPV), Italy

Supervisors: Dr. Alessandro Reali, University of Pavia (UniPV, Italy), Dr. Giancarlo Sangalli, University of Pavia (UniPV, Italy), Dr. Claudio Canuto, Polytechnic University of Turin (POLITO, Italy)

Mikel Mendibe (Doctoral Candidate #3, Tecnalia, Spain)

Short bio: I grew up in the Basque Country and completed a Bachelor's degree in Industrial Engineering. However, the rise of AI soon started to pique my interest, which led me to the United States to pursue a Master's in Computational Decision Science. After spending some time in the Industry, I realized that what truly excited me wasn't just building solutions, but understanding them deeply. That's what drew me to research. I am currently a PhD candidate at Tecnalia and the University of the Basque Country, where I work on applying Physics-Informed Machine Learning to Computational Oncology. My research focuses on making these models more transparent and trustworthy by understanding the limitations and confidence of their predictions. In a time when trust in technology is more important than ever, I’m driven by the goal of using AI to tackle one of the most pressing challenges we face: providing faster, more accurate, and more reliable cancer prognostics.

PhD research topic: Uncertainty-aware deep learning for parametric PDEs modelling tumor growth

Host institution: Tecnalia Research & Innovation, Spain

PhD Enrolment: University of the Basque Country (UPV/EHU), Bilbao, Spain

Supervisors: Dr. Javier Del Ser (Tecnalia, Spain), Dr. Alessandro Reali, University of Pavia (UniPV, Italy)

Meike Tütken (Doctoral Candidate #4, Siemens, Belgium)

Short bio: I completed both my Bachelor's in Engineering Science and Master's in Computational Science and Engineering at the Technical University of Munich (TUM), where I had the opportunity to enrich my academic journey through exchange semesters at Nanyang Technological University in Singapore and the University of Tokyo in Japan. I am now a PhD candidate at the KU Leuven in Belgium and hosted by Siemens Digital Industries Software. My research focuses on advancing the intersection of machine learning and structural mechanics, with a particular emphasis on addressing shear locking phenomena. Drawing from my mechanical engineering foundation and computational expertise, I explore how modern machine learning approaches can enhance classical numerical methods like FEM, while ensuring reliability and trustworthiness in these hybrid approaches. I am excited to bridge the gap between academic research and industrial applications, collaborating with partners across Europe to develop innovative solutions in computational engineering. My work aims to build something new by combining the best of both traditional numerical methods and state-of-the-art machine learning techniques.

PhD research topic: Machine Learning & AI methods for solver acceleration and improvement

Host institution: Siemens Digital Industries Software, Belgium

PhD Enrolment: KU Leuven, Leuven, Belgium

Supervisors: Dr. Gwendal Jouan (Siemens, Belgium), Dr. Bert Pluymers (KU Leuven, Belgium), Dr. Maciej Paszynski (AGH, Poland)

Nicolás Zamorano (Doctoral Candidate #5, POLITO, Italy)

Short bio: Since my Bachelor's degree in Mathematics, I have been deeply interested in the development and analysis of numerical methods for solving Partial Differential Equations (PDEs). During both my Bachelor's studies and my Master's degree in Computational Simulation, I learned and studied deep learning techniques to solve PDEs. I am currently working on the development and analysis of deep PDE solvers, with the aim of developing reliable and efficient estimators to speed up the computations through the use of adaptive strategies. For the future, I intend to continue in this field and build a strong research career.

PhD research topic: Adaptive strategies for explainable Deep PDE solvers to speed up the generation of large and significant datasets.

Host institution: Polytechnic University of Turin (POLITO), Turin, Italy

PhD Enrolment: Polytechnic University of Turin (POLITO), Turin, Italy

Supervisors: Dr. Stefano Berrone (POLITO, Italy), Dr. Kristoffer Van der Zee, Dr. University of Nottingham (UoN, UK), Sandra Pieraccini, Politecnico di Torino (POLITO, Italy), Dr. Claudio Canuto, Politecnico di Torino (POLITO, Italy)

Elias Al Ghazal (Doctoral Candidate #6, ENSAM, France)

Short bio: I am currently pursuing a PhD in Paris, focusing on the integration of physics-based methods and machine learning for infrastructure health assessment. My research explores advanced techniques such as neural ODEs and the PU method to enhance predictive modeling. With a background in engineering and data science, I aim to bridge the gap between theoretical modeling and real-world applications. My career goal is to contribute to the development of intelligent, reliable systems for infrastructure monitoring and decision-making, both in academia and industry.

PhD research topic: Physics-aware methods combining traditional solvers and deep learning for infrastructures’ smart health assessment.

Host institution: Arts et Métiers Institute of Technology (ENSAM), Paris, France

PhD Enrolment: Arts et Métiers Institute of Technology (ENSAM), Paris, France

Supervisors: Dr. Francisco Chinesta, ENSAM, Paris, France, Dr. David Pardo, UPV/EHU, Bilbao, Spain

Elías Carú (Doctoral candidate #7, BCAM, Spain)

Short bio: I earned both my BSc and MSc in Mathematics at the Pontificia Universidad Católica de Valparaíso, where a brief spell as a lecturer confirmed my passion for research and for sharing mathematics. I am now a PhD candidate at the Basque Center for Applied Mathematics (BCAM), where I design novel deep-learning architectures for bioscience, aiming for models that are efficient, accurate, and trustworthy. Fascinated by the inner workings of increasingly sophisticated AI, I strive to bridge rigorous mathematical insight with real-world needs and to contribute to responsible, impactful advances in artificial intelligence.

PhD research topic: Leveraging deep PDE solvers with adaptive strategies and Fourier-based loss function. Application in computational biosciences.

Host institution: Basque Center for Applied Mathematics (BCAM), Bilbao, Spain

PhD Enrolment: University of the Basque Country (UPV/EHU), Bilbao, Spain

Supervisors: Dr. Judit Muñoz-Matute, BCAM, Spain, Dr. Giancarlo Sangalli, University of Pavia, Italy

Askold Vilkha (Doctoral candidate #8, AGH, Poland)

Short bio: I started my professional and scientific journey in my home city of Lviv, Ukraine, where I earned a Bachelor's degree in Physics and Astrophysics. Then, I continued studying Astrophysics in the United States, focusing more on its computational and statistical aspects. I obtained a Master of Science degree in Astrophysical Sciences and Technology from Rochester Institute of Technology (Rochester, NY, USA). I am now a PhD Candidate in Information and Communication Technology at the AGH University of Kraków, Poland. While studying and working on scientific research, I have realized that my main interests have switched from astrophysics to computational science and statistics, specifically towards AI and Machine Learning, as these areas are growing extremely rapidly now. In my experience, I found that the solution process of the scientific problems was no less exciting than the final solution. Hence, I realized I want to apply my various skills and expertise in physics, mathematics, programming, and statistics to real-world problems and work on developing explainable and reliable solutions for them. Looking to the future, I am flexible and open to the new opportunities that lie ahead of me. I certainly want to work in an interdisciplinary field, either in industry or academia.

PhD research topic: Fast certified graph neural networks for parametric PDEs modelling flow-simulation in porous-fractured geological formations

Host institution: AGH University of Krakow (AGH), Krakow, Poland

PhD Enrolment: AGH University of Krakow (AGH), Krakow, Poland

Supervisors: Dr. Maciej Paszynski, AGH University of Krakow, Dr. Sergio Gil López, Tecnalia, Bilbao, Spain.

Emin Benny Chacko (Doctoral candidate #9, University of Nottingham, UK)

Short bio: My research interests include neural networks, optimization, numerical analysis, and machine learning, with a particular emphasis on their mathematical foundations. I completed my bachelor's and master's degrees in mathematics in India, and my interest in machine learning was sparked during a research internship at Cochin University of Science and Technology. Currently, I am working on a deep learning minimal residual framework for damage identification in civil and industrial infrastructures, focusing on the design and analysis of Minimal Residual algorithms for stability and convergence. My goal is to contribute to the development of mathematically grounded methods in machine learning and to build a strong research career in this field.

PhD research topic: A deep learning minimal residual framework for damage identification in civil and industrial infrastructures

Host institution: University of Nottingham (UON), Nottingham, UK

PhD Enrolment: University of Nottingham (UON), Nottingham, UK

Supervisors: Dr. Kristoffer van der Zee, University of Nottingham, UK, Dr. Francisco Chinesta, ENSAM, France

Google Sites

Report abuse

Sponsors