The Scalable Scientific Machine Learning Lab is led by Dr. Ben Moseley and is part of the Department of Earth Science and Engineering at Imperial College London.
We accelerate scientific research by designing scientific machine learning (SciML) algorithms and applying them to impactful problems across science.
We develop SciML techniques such as physics-informed neural networks, hybrid ML-numerical algorithms, and physics-based computer vision, and use them to accelerate simulations, better extract knowledge from data, discover new physical models, and improve experiment design. We focus on designing SciML algorithms which are 1) robust, designing physically-grounded workflows that generalise well, and 2) scalable, building algorithms that inherently handle multi-scale, high-dimensional, noisy, and realistic systems.
We have applied our SciML algorithms to many impactful problems, including to improve the accuracy of multi-scale simulation, de-noise low-light satellite images of the Moon’s surface, and extract new insights about quantum theories. We collaborate with many academic and industry partners to identify and solve impactful problems.
We are a highly cross-disciplinary team: our members are experts across machine learning, applied mathematics, high-performance computing, and in domain-specific areas including geophysics, climate science, and planetary science.
Please get in touch if you are interested in working with us!
Not sure what SciML is? Check out our blog post: So, what is scientific machine learning?
Research areas
scientific machine learning, AI for science, physics-informed neural networks, neural differential equations, foundation models for science, hybrid modelling, learned inverse algorithms, high-performance computing
Tags
Chemical Engineering Climate Science Computer Vision Game Theory JAX Mathematics Neural Differential Equations Physics Physics-Informed Neural Networks Planetary Science Simulation