Speaker :- Dr. Sandip Saha

Title of the Talk :- Exploring Data-Driven Potential Landscapes and Velocity Prediction

Date, Time and venue :- 21 April 2025, 5:00 PM - 6:40 PM at Seminar Hall, Dept of Mathematics.

About the speaker :- Dr. Sandip Saha is currently working as a Career Development Fellow at the National Centre for Biological Sciences (NCBS-TIFR), Bangalore, India. Previously, he did various postdoctoral positions at ISI Kolkata, TU darmstadt in Germany, and KAUST in Saudi Arabia. His current work focuses on optimizing Physics-Informed Machine Learning models for complex developmental processes, supported by Mathematical modelling. He obtained his Ph.D from the S.N. Bose National Centre for Basic Sciences.

Abstract :- Developing robust and predictive dynamical state-space models, such as ODEs, PDEs, and Boolean models, remains a key challenge in systems biology. These models often face difficulties due to limited data, leading to under-determined model structures and an extensive parameter space. This presentation focuses on Physics-Informed Machine Learning, combining Mathematical Modeling and Machine Learning with fundamental physical principles. By incorporating concepts like the Variational Principle, Lagrangian, and Hamiltonian into computational algorithms, we aim to enhance the predictive capabilities for systems biology dynamics. This includes creating a pipeline to construct potential landscapes for analyzing disease dynamics and predicting velocity data from position data in non conservative models. Through this integrative approach, which includes both modeling and simulation, we seek to improve our understanding of the complex dynamics in biological systems