skip to content

 

This NERC workshop is organised by Dr Henry Moss and hosted by the Institute of Computing for Climate Science (ICCS) at the University of Cambridge. It will equip the next generation of NERC or UKRI funded climate scientists with the necessary knowledge, skills, and support to integrate machine learning (ML) into their research during their PhDs and future careers. The workshop will incorporate hands-on exercises using real-world climate data, providing participants with practical experience in a collaborative, project-based environment. 

This course will be the first of its kind for NERC or UKRI PhD students in the UK and as such has two non-standard foci that are critical when applying ML to climate science, but often overlooked in standard introductory courses:

  • Firstly, to ensure ML is appropriately deployed, our programme will focus heavily on its limitations. As a field enjoying significant publicity, ML is often oversold to practitioners and there is a disconnect between typical ML advancements and their ability to solve real-world scientific problems. Therefore, in order to successfully use ML to support their research, students must learn how to appropriately interrogate and interpret new ML advances.
  • Secondly, as understanding uncertainty is crucial when communicating potential risks and impacts of climate change, we will focus on Bayesian ML, which unlike many traditional ML methods can quantify uncertainty in interpretations and predictions. The course will take advantage of the substantial Bayesian ML expertise in Cambridge and the active community of researchers across the university and the British Antarctic Survey (BAS) already applying these methods to problems in climate science. Tutorials will be provided on crucial topics such as Bayesian neural networks and Gaussian processes.

By focusing on these topics, we will prepare students to integrate ML into their research effectively and communicate their findings to policymakers and the public. The full schedule of the workshop will be released soon.

 

Workshop logistics, registration, and funding

The workshop will be held in-person at the Centre for Mathematical Sciences in Cambridge from Monday 25th March 2024, finishing at lunchtime on Wednesday 27th March 2024. Registration is now closed and participants have been informed.

The workshop will be entirely free of cost, including accommodation (including breakfast) from Sunday to Wednesday, and we will reimburse any travel costs incurred up to a maximum £160 per person. Free lunches and dinners will also be included in the event. ICCS will also consider requests for additional funding that may help participants to attend this event, including childcare costs, and there will be space to apply for this funding in the registration form.

If you have any further questions about the workshop, please write to the ICCS Operations Team at iccs@maths.cam.ac.uk.

 

Date: 
Monday, 25 March, 2024 - 09:00 to Wednesday, 27 March, 2024 - 13:00
Contact name: 
ICCS Team
Contact email: 
Contact phone: 
01223764060
Event location: 
Centre for Mathematical Sciences, Wilberforce Rd, Cambridge CB3 0WA

About Us

Computational modelling is key to climate science. But models are becoming increasingly complex as we seek to understand our world in more depth and model it at higher fidelity. The Institute of Computing for Climate Science studies and supports the role of software engineering, computer science, artificial intelligence, and data science within climate science.

The institute comprises a collaboration between Cambridge Zero, the Departments of Applied Mathematics and Theoretical Physics (host department of the institute), Computer Science and Technology, and University Information Services at the University of Cambridge.

Read more