WUR Scientific Machine Learning Network

Welcome to the official website of the Scientific Machine Learning Network of Wageningen University and Research.

What is SciML?

Scientific Machine Learning (SciML) is an emerging AI-discipline to bring scientific knowledge, often in the form of differential equations, to machine learning. In this way, machine learning gets a better scientifically based structure, making it more robust, better interpretable and more feasible for extrapolation.

On this website, we explain SciML and its backgrounds to the wider public. We provide links to useful SciML-resources.

News and Agenda

2024-11-06: Digital Innovation Expo with a talk by George van Voorn on Hybrid Machine Learning.
9^th SciML meetup: to be announced

Archive

2022-10-05: 1^st SciML meetup
2022-11-10: 2^nd SciML meetup: presentations by Bernardo Maestrini and Xuezhen Guo
2022-12-01: presentation on SciML for the Soil, Water and Land Use team of Wageningen Environmental Research (Joost Iwema and Dennis Walvoort)
2022-12-15: 3^rd SciML meetup: presentation by Dennis Walvoort
2023-01-26: SciML website officially launched
2023-03-09: 4^th SciML meetup: presentations by Jingye Han and Ben Noordijk
2023-04-07: WUR-SciML network Intranet group launched
2023-04-12: Towards physics-AI hybrid modeling in hydrology - Geneva
2023-06-08: 5^th SciML meetup: presentations by Sjoerd Boersma and Fakirah Maulana
2023-09-28: 6^th SciML meetup: presentations by Marc Russwurm and Xuezhen Guo
2023-11-16: SciML session at the WUR Model and Data Day
2023-11-23: CWI Symposium on the Applications of Scientific Machine Learning
2024-01-23 7^th SciML meetup: presentations by Yingjie Shao and Luan Pott
2024-05-23 8^th SciML meetup: presentation by Valdrich Fernandes
2024-07-09 — 2024-07-12: SciMLCon 2024 Eindhoven
2024-10-17: Wageningen Model and Data Day with two sessions on SciML:
- SciML: Gray-Box Physics-informed Neural Networks (PINNS) modelling in food-related domains by Xuezhen Guo & Ruud van de Sman;
- Hybrid Machine Learning and process-based modelling approaches for climate adaptation strategies by George van Voorn, Hajo Rijgersberg, Xinxin Wang, Cheng Liu, Charlotte Harbers & Xuezhen Guo