I’m organising a CWI Semester Programme on Scientific Machine Learning. Here’s a quick overview:
The future of computational science lies in the combination of physical modelling and data-driven techniques. In my research group at CWI, the Scientific Computing group, we develop new methods and algorithms that enable the transition to truly predictive models. For this purpose, we work at the intersection of different disciplines: uncertainty quantification, partial differential equations and discretization methods, computational fluid dynamics, machine learning, reduced-order modeling, and Bayesian inference.
The models that we develop are applied to a variety of (industrial) applications: for example, sloshing of liquid natural gas in tanker ships, aeroelastic predictions for wind turbines, and transport of multiphase flow in pipelines. Our work also forms an enabler for recent techniques such as Digital Twins.
Sloshing of liquid simulated with smoothed particle hydrodynamics. Courtesy of Yous van Halder.
In turbulence modeling, and more particularly in the Large-Eddy Simulation (LES) framework, we are concerned with finding closure models that […]
Reduced-order models are used widely to make fluid flow simulation computationally tractable for example for the purpose of real-time control [...]
When designing wind turbines, it is necessary to give proof that the turbine will be able to withstand the environmental […]
Sloshing of liquefied natural gas (LNG) in large transport tankers is an important issue that limits the operational envelope of […]
