Katsiaryna’s research focuses on physics-informed deep learning, integrating machine learning with prior knowledge of physical systems. Her work aims to develop more sample-efficient and interpretable models of physical systems, enabling latest advances in deep learning for applications in science and engineering.
Katsiaryna did her doctoral studies at Aalto University School of Science supervised by Prof. Pekka Marttinen and advised by Dr. Alexander Ilin. Currently she is a researcher at Exploratory Data Analysis group at University of Helsinki, led by Prof. Kai Puolamäki.
Selected publications:
[1] Katsiaryna Haitsiukevich, Alexander Ilin. Improved Training of Physics-Informed Neural Networks with Model Ensembles. In 2023 International Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia, pp. 1–8, June 2023. Link: https://ieeexplore.ieee.org/document/10191822
[2] Katsiaryna Haitsiukevich, Onur Poyraz, Pekka Marttinen, Alexander Ilin. Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systems. In IEEE International Workshop on Machine Learning for Signal Processing (MLSP), London, United Kingdom, September 2024. Link: https://ieeexplore.ieee.org/document/10734762
[3] Katsiaryna Haitsiukevich, Samuli Bergman, Cesar de Araujo Filho, Francesco Corona, Alexander Ilin. A Grid-Structured Model of Tubular
Reactors. In 2021 IEEE 19th International Conference on Industrial Informatics (INDIN), Palma de Mallorca, Spain, pp. 1–6, July 2021. Link: https://ieeexplore.ieee.org/document/9557382