Workshop: Machine learning for physics based modelling

The workshop is the second workshop organized in the context of the Indo-Dutch project, “Digital Twins for pipeline transport networks”. The aim of the project is to develop a digital twin that connects sensor data and advanced fluid solvers in order to detect possible leakage of fluid from the pipeline in real-time. Of particular interest is then also to develop machine learning based solvers for physics-based models, as traditional solvers are typically much too slow for real-time applications. Next to the presentations discussing the progress in the project, we have also invited speakers from outside the project, presenting their work on physics-based modeling and efficient computation. We thank the NWO (the Netherlands), MeitY (India) and Shell (the Netherlands) for funding the project. In the present workshop the following talks have been scheduled:

Part 1
10:00 CET / 14:30 IST  Karen Veroy-Grepl (TU Eindhoven) – Dimension reduction: Recent advances towards combining models and data
10:45 CET / 15:15 IST  Ankit Tyagi and Abhineet Gupta (Shell India) – Machine learning for multiphase flow modelling in pipelines
11:15 CET / 15:45 IST  Vineet Tyagi (IISc Bangalore) – Digital twin for real-time detection of leakages in water pipeline networks

Part 2
13:00 CET / 17:30 IST  Nikolaj Mücke (CWI) – Markov Chain Generative-Adversarial Neural Networks for Solving Bayesian Inverse Problems
13:30 CET / 18:00 IST  Deepak Subramani (IISc Bangalore) – Machine Learning in the Geosciences
14:15 CET / 18:45 IST  End of Workshop

This workshop will take place, online, via Zoom
[Meeting ID: 844 6918 1821;  Passcode: 515596]

More information about the speakers and their presentation you will find here.