About the Lab
The Machine Learning for Physical Science group develops advanced computational methods combining Scientific Machine Learning, Deep Generative Modeling, and Deep Geometric Learning to accelerate scientific discovery. We focus on building efficient emulators from synthetic and experimental data, incorporating domain knowledge and physical principles to address challenges in materials science, mechanical engineering, fluid dynamics, and nuclear fusion.
Research profile
The Machine Learning for Science group develops advanced computational methods to accelerate discovery across diverse scientific domains. Our interdisciplinary team leverages expertise in Machine Learning, particularly at the intersection of Scientific Machine Learning, Generative Modeling, and Geometric Deep Learning, to address critical challenges in fields like Materials Science, Mechanical Engineering, Computational Fluid Dynamics, and Nuclear Fusion.
We are pushing the boundaries of deep generative modeling to overcome limitations inherent in scientific computing and the simulation of dynamical systems. Our research focuses on building highly efficient and precise emulators by developing Machine Learning models from both synthetic and experimental data. These emulators empower us to design novel materials with targeted chemical and mechanical properties, model complex pedestrian dynamics, and simulate plasmas within nuclear fusion devices, ultimately contributing to advancements in these respective fields.
A key aspect of our approach is the incorporation of domain knowledge. We leverage known symmetries and physical principles to develop data-efficient and scalable models. Furthermore, we are dedicated to establishing robust, domain-informed validation methodologies to ensure the reliability and trustworthiness of our solutions.
Working across a wide range of fields allows us to identify commonalities in both the challenges and their solutions. We therefore actively contribute to both the specific scientific disciplines and to the state of the art of Machine Learning. We strive to bring the rapid advancements of Machine Learning and High Performance Computing to fields that traditionally benefited from computational science with the aim to overcome many long standing challenges in these fields.
Nuclear Fusion
[Yoeri something]
Materials Science
[Marko and Fleur something here?]
Biology
Deep Cellular Potts & MicroRNA decoding
Fluid Mechanics
[Bubble etc.]
Pedestrians
[Not sure what field this would go under but deserves to be mentioned]
Selected publications
We have published numerous papers in top-tier journals. Our recent publications include:
