CV

Education

• Ph.D in AI and Computer Vision for Remote Sensing, KU Leuven, 2025-2029 (expected)
• MSc in Artificial Intelligence, KU Leuven, 2021-2022 (Magna Cum Laude)
• MSc in Electronics Engineering, ECAM Brussels, 2019-2021 (Magna Cum Laude)
• BSc in Electronics Engineering, ECAM Brussels, 2015-2019 (Cum Laude)
• Exchange Student in Canada, Université Laval, 2019-2020

Work experience

• Computer Vision / Machine Learning Engineer, Esko, 2023-2025
  • Segmentation refinement pipeline: Developed a Python-based pipeline to enhance the accuracy of segmentation masks generated by the Segment Anything Model (SAM), by combining Conditional Random Fields, CNN-based models (CascadePSP), and the Watershed algorithm.
  • Barcode detection and processing: Built a CNN-based (YOLO) solution for barcode detection, and custom vision algorithms for barcode quality assessment.
  • Layout analysis of artwork documents: Trained YOLO and fine-tuned LayoutLM models to detect and classify structures in digitized artwork documents, combining object detection with BERT-based semantic classification
• Research Assistant in Construction Robotics, KU Leuven, 2022-2023
  • Contributed to a project of building robots for shotcreting operations.
• Master thesis student, KU Leuven, 2021-2022
  • Under the supervision of Prof. Dr. Renaud Detry, as part of the inVADER project led by NASA’s Jet Propulsion Laboratory, I developed machine learning models for automated mineral identification from Raman spectroscopy data, supporting scientific autonomy in planetary exploration.

Skills

• Languages: Python, C++, LATEX, SQL
• Tools: PyTorch, scikit-learn, Tensorflow, Keras, Numpy, Pandas, Jupyter Note- book, OpenCV, Unix, Cloud Computing Services (AWS, Azure)
• Project Management: Agile methodologies (scrum), Jira, Git

Publications

Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy

Deniz Soysal, Xabier Garcia-Andrade, Laura E. Rodriguez, Pablo Sobron, Laura M. Barge, Renaud Detry. (2025). "Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy." ACS Earth and Space Chemistry. DOI: 10.1021/acsearthspacechem.5c00136.