Physics-Informed Machine Learning Team
The Physics-Informed Machine Learning group is part of the Organic Electronics and Photovoltaics activities at the ZHAW Institute of Computational Physics. We model physical processes with the aid of partial differential equations and numerical methods and combine this expertise with machine learning methods. Our goal is to establish a strong link between data-driven methods and modelling approaches.
Research
Physics-Informed Machine Learning is an emerging interdisciplinary research field comprising of mathematical modelling, physics, computer science and machine learning. Our goal is to integrate mathematical models into the machine learning approach and thereby reduce the amount of training data and replace it with domain knowledge. Our expertise in mathematical modelling (of optoelectronics devices) plays an important role and is key for Physics-Informed Machine Learning.
Research projects
Design and Development of Industry Compatible Characterization Equipment for Emerging Perovskite and Perovskite/Silicon Tandem Solar Cells
The only certainty is uncertainty: Uncertainty quantification in ML Prediction (UQML)
Enhanced blood flow and pressure measurements with PhysioCath-microcatheter for reliable diagnosis of 'Ischemia with Non-Obstructive Coronary Artery' (INOCA)
Advanced Imaging and Machine Learning for PV Quality Assurance (AIPV 2)
