Satyasaran Changdar

Satyasaran Changdar is an Assistant Professor in the Department of Food Science at the University of Copenhagen, where he works on modeling using Scientific Machine Learning, particularly in sustainable food process modeling and new food formulation. He works under the supervision of Prof. Serafim Bakalis and collaborates with Arla Foods. His research spans multiple disciplines including food science, plant physiology, coastal engineering, and biomedical applications.

His educational background includes:

• Ph.D. in Applied Mathematics from University of Calcutta (2019)
• M.Tech. in Computer Applications from IIT Delhi (2008)
• Master's in Mathematics from IIT Bombay (2005)

Changdar's research focuses on developing and applying machine learning techniques to solve complex scientific problems. His work in Physics-Informed Neural Networks (PINNs) has applications across diverse fields from food science to coastal engineering. He has developed deep learning models for sub-soil root image analysis through the RadiMax project, enabling non-invasive phenotyping of crop root systems. His research on multimodal agricultural data analysis contributes to understanding plant root function and resource uptake. In biomedical applications, he has worked on arterial blood flow modeling and brain tumor segmentation using advanced deep learning architectures.

His recent publications (2024-2025) demonstrate a strong interdisciplinary approach, bridging machine learning with domain-specific scientific challenges. The research spans coastal engineering (breakwater stability analysis), agricultural science (winter wheat phenotyping), biomedical engineering (arterial blood flow modeling), and medical imaging (brain tumor segmentation). A common thread through these diverse applications is the innovative use of physics-informed machine learning approaches to solve complex scientific problems with limited data.

Changdar actively collaborates across departments at the University of Copenhagen, working with researchers from Computer Science and Plant and Environmental Sciences. His GitHub profile shows active development of machine learning tools for scientific applications, with projects focusing on PINNs, symbolic regression, and agricultural machine learning. He is currently exploring quantum machine learning applications and seeking collaborations in healthcare, finance, food, agriculture, and sustainability sectors.