Scientific Machine Learning Group
10 Jul 2020
Yes
-  

 

 

The core focus of the Scientific Machine Learning (SciML) Group is AI for Science.

No

​​​​​​​​​​​​​​​

 

As such, the mission of the group is to explore how the use of Machine Learning and other AI technologies can help scientists analyse the vast amounts of experimental data now being routinely generated by the large experimental facilities at the Rutherford Appleton Laboratory (RAL) and STFC’s Harwell campus. With the rapid development in detector technologies and the emergence of new experimental techniques, such as cryoEM electron microscopy, there are now major challenges for scientists to manage and process  very large datasets. The group  develops/applies various  state-of-the-art machine learning or AI technologies to accelerate the process of scientific discovery. As such, the group routinely works with beamline scientists various facilities at RAL, such as Diamond Light Source, Central Laser Facility , ISIS Neutron and Muon Source, Technology Department, and NERC's Centre for Environmental Data Analysis and their JASMIN service.  The group provides a national AI computing service for Turing and STFC researchers working on AI for Science along with various training courses on scientific machine learning.  

The group is a partner with the Alan Turing Institute in their ‘Data Science for Science’ theme, and is a Turing Hub at Harwell. The group also has a number of strong links and collaborations with various national labs in the US.  The group’s activities at RAL complement the predominantly industry-focused work of the ​Data Science Group at the Hartree Centre, and the two groups collaborate in several joint activities. ​​​

​​PEARL AI Service​

The PEARL service, provided through a collaboration between The Alan Turing Institute and Science and Technology Facilities Council, is a state-of-the-art GPU-based system for AI and machine learning research. The system includes two NVIDIA DGX2 nodes, ​and a 600TB storage, linked by a fast interconnect. The system has several thousands of GPU cores, and a large amount of memory to support most AI or machine learning operations, such as training on large datasets. You can apply for access to PEARL here.​

Training Courses

​As a group, we offer various training courses focussed on AI for Science. For more information on training, please contact us​.

​SciML Seminars

​​We run a weekly seminar series welcoming talks covering a broad range of topics in machine learning and its applications to science from both internal and external speakers. Information on past and upcoming seminars can be found here​.

Contact: O'Sullivan, Marion (STFC,RAL,SC)