Senior Research Associate in Data-Driven Weather and Climate Modelling (Fixed Term)

University of Cambridge; Hartford; On-site; GBP 35,000 - 50,000; Full time

Job summary

A prestigious research university is seeking a scientist with expertise in data science, computer science, and earth sciences for a one-year research position. The role involves developing research projects, managing budgets, and contributing to educational programs. Candidates should have a PhD and relevant research experience in numerical weather prediction and strong publication records.

Qualifications

• Research experience in data-driven techniques in numerical weather prediction or climate forecasting.
• Evidence of high-quality research outputs.
• Strong track record in relevant research areas.

Responsibilities

• Define and conduct individual and collaborative research objectives.
• Manage research budgets and assess outcomes.
• Secure funding and contribute to teaching programs.

Skills

Research experience in numerical weather prediction

Expertise in data-driven techniques

Collaboration potential

Education

PhD in a relevant area

Job description

Overview

Recent advances in machine learning have opened up a variety of data-driven modelling techniques within science which are showing unprecedented abilities to replace traditional models with fast approximations. Numerical Weather Prediction (NWP) is one such area in which machine learning based models are showing comparable skill compared with traditional techniques, but at significantly reduced computational cost. Furthermore, data-driven techniques can cover entire forecasting pipelines, in some cases obviating the need for state estimation and operating directly on observations. Further work is needed to develop models which can be used effectively in operational contexts, integrating with a variety of observations across different scales, and being used to accurately predict extremes, seasonal variability, localised forecasts, and more. There also remains a gap between weather and climate modelling in this space; further work is needed to understand whether and how the techniques that work well for machine-learned NWP can be applied to longer timescales for climate predictions. These are the broad areas of interest for the present position based in the Institute of Computing for Climate Science.

About ICCS

The institute is a joint venture between the Department of Applied Mathematics and Theoretical Physics, the Department of Computer Science and Technology, and University Information Services, thanks to various sources of philanthropic funding and grant funding. ICCS aims to support advancements in weather and climate modelling through a multi-disciplinary approach, drawing on earth sciences, mathematics, statistics, software engineering, computer science, and machine learning.

Position

This position offers a unique opportunity for an outstanding scientist with expertise in working across the interfaces between data science, computer science, machine learning and earth sciences to carry out foundational research. The fellow will be based in DAMTP and affiliated with Queens College. This is a one-year appointment in the first instance that includes research expenses support, allowing the SRA to apply for other sources of funding as principal investigator. As part of the University of Cambridge, ICCS has a significant education and training component, through the commitment towards sharing its scientific insights openly and broadly, and will contribute strongly to Cambridge Zero, the University\'s climate change initiative, that is identifying routes to the creation of a sustainable, zero-carbon future for all.

Duties

Duties include defining, developing and conducting individual and collaborative research objectives, proposals and projects and managing research budgets. You are responsible for the investigation and delivery of your own research programmes, and assessing, interpreting and evaluating the outcomes. You are expected to extend and apply knowledge, contribute to publications, present, and communicate complex ideas to those with limited knowledge. You need to be able to identify sources of funding, help secure funds and develop links with external contacts. You may be expected to contribute towards teaching programmes, supervise postgraduate research students, mentor colleagues and carry out appraisals.

Essential requirements

Essential requirements for the role(s) of SRA include, Click the \'Apply\' button below to register an account with our recruitment system (if you have not already) and apply online. Please indicate the contact details of three academic referees on the online application form and upload a full CV, publications list, a description of your recent research, current research and future research interests (not to exceed two pages). Please ensure that at least one of your referees is contactable at any time during the selection process, and is made aware that they will be contacted by the HR Office Administrator to request that they upload a reference for you to our Web Recruitment System.

If you have any questions regarding the role or the application process, please contact: Colm-cille P. Caulfield ( ) Dominic Orchard ( ) If you have any queries regarding the application process, please contact .

The University actively supports equality, diversity and inclusion and encourages applications from all sections of society. We particularly welcome applications from women and/or candidates from a BME background for this vacancy as they are currently under-represented at this level in our Department. The University has a responsibility to ensure that all employees are eligible to live and work in the UK.

Further information

Qualifications

• PhD in a relevant area of earth sciences but drawing on techniques from machine learning, mathematics, statistics, or data science;
• Research experience and expertise in data-driven techniques in numerical weather prediction and/or climate forecasting;
• Normally at least three years\' research experience (obtained in either academic or industrial settings);
• A strong track record in one or more relevant research areas;
• Evidence of high-quality research outputs;
• Evidence of potential for collaborations.