Scientific machine learning (SciML) is an interdisciplinary field that merges the power of machine learning with traditional scientific methods.
The field develops techniques for scientific research which combine physics-based knowledge, like mathematical equations and models, with data-driven learning techniques, like deep neural networks.
These new techniques help us solve complex scientific problems that are computationally intensive, hard to model accurately, or that involve incomplete data.
SciML is empowering researchers to tackle the world’s most pressing problems, from dramatically accelerating weather forecasting, to being able to accurately predict the 3D structure of proteins, and helping us design sustainable nuclear fusion reactors.
Key SciML techniques include physics-informed neural networks, neural operators, neural differential equations, hybrid modelling, foundation models for science, and data-driven reduced-order models.
Learn more about SciML
What to learn more about SciML? Watch the AI in the Sciences and Engineering Master’s Course (taught by Dr. Ben Moseley and Prof. Sid Mishra @ ETH Zurich in 2024) freely available on YouTube for an in-depth introduction. Also have a read of Dr. Ben Moseley’s PhD thesis.
Leave a Reply