OUR CHANGING OCEANS: artificial intelligence (AI) and the marine carbon cycle, NERC GW4+ DTP, PhD in Geography Ref: 3328

About the award

Supervisors

Lead Supervisor

Dr Ute Schuster, Department of Geography, College of Life and Environmental Sciences, University of Exeter

Additional Supervisors

Dr Jacqueline Christmas, Department of Computer Science, College of Engineering, Mathematics and Physical Sciences, University of Exeter

Location: University of Exeter, Streatham Campus, Exeter EX4 4QJ

Main Information

This project is one of a number that are in competition for funding from the NERC Great Western Four+ Doctoral Training Partnership (GW4+ DTP).  The GW4+ DTP consists of the Great Western Four alliance of the University of Bath, University of Bristol, Cardiff University and the University of Exeter plus five Research Organisation partners:  British Antarctic Survey, British Geological Survey, Centre for Ecology and Hydrology, the Natural History Museum and Plymouth Marine Laboratory.  The partnership aims to provide a broad training in earth and environmental sciences, designed to train tomorrow’s leaders in earth and environmental science. For further details about the programme please see http://nercgw4plus.ac.uk/

For eligible successful applicants, the studentships comprises:

  • An index-linked stipend for 3.5 years (currently £14,777 p.a. for 2018/19);
  • Payment of university tuition fees;
  • A research budget of £11,000 for an international conference, lab, field and research expenses;
  • A training budget of £4,000 for specialist training courses and expenses.

Up to 30 fully-funded studentships will be available across the partnership.

Eligibility
Students from EU countries who do not meet the residency requirements may still be eligible for a fees-only award but no stipend.  Applicants who are classed as International for tuition fee purposes are not eligible for funding.

Project details

Human activity is changing the environment of our planet, including the carbon cycle.  The carbon dioxide (CO2) content of the atmosphere is increasing, leading to changes in the terrestrial and marine carbon cycles (Le Quéré et al., 2017).

Knowledge of the ocean uptake of CO2, with a high degree of confidence, is crucial in determining the current state of the carbon cycle in the marine environment, as well as improving the certainty in results from predictive models (Intergovernmental Panel on Climate Change, 2013).

Additionally, the biogeochemical drivers of variability of the air-to-sea CO2 exchange need to be understood, from regional to global spatial scales, and from monthly to inter-annual time scales.

Artificial intelligence techniques, particularly in machine learning, will help us to estimate the degree of uncertainty in the observed data, and in the models’ predictions.

Project Aims and Methods

1) Collect observations.  We have established a time-series of ocean surface CO2 measurements, made on board commercial vessels, between the UK and Caribbean, as part of an international effort to collect such high quality data, which is publically available through the Surface Ocean CO2 Atlas (SOCAT, 2018). Within this project we will continue the collection of these measurements, the data quality control and the contribution to the global dataset in SOCAT.

We’ll be using these in situ observations, together with data from Earth Observations and Reanalyses, in statistical machine learning and AI models to improve our understanding of the marine carbon cycle and the biogeochemical drivers of its variability, and the air-sea CO2 flux:

2) Develop dynamic marine biogeochemical regimes.  Observations are, by their nature, sparse in time and space; mapping techniques are therefore required to produce spatially complete fields at regular time intervals. A number of ocean divisions have been used for this (including Longhurst, 2007; Landschützer et al., 2014; Fay and McKinley, 2014; Watson et al., 2009; Reygondeau et al., 2013), but these are either static in space and time, contain unrealistically straight boundaries, or are computationally expensive to produce. We’ll be using statistical machine learning and AI methods to develop a new observation-based, time-changing (dynamic) division of ocean biogeochemical regimes, that are biogeochemically realistic and do not require extensive computational power.

3) Improve air-sea CO2 flux estimates.  This will enable us to produce improved regional to global air-sea CO2 fluxes, at monthly through inter-annual time scales. We will rigorously test the uncertainties of our flux estimates, and perform validations and comparisons with published results and model outputs (e.g. CMIP6 results; Eyring et al., 2016).

The supervisors are happy to discuss the project’s details to suit a candidate.

Training

Due to the interdisciplinary nature of this project, a training plan will be developed according to the background and expertise of the successful candidate.  This will include health & safety for laboratory and field work, applying best practices and standard operating procedure in obtaining high quality observations, effective communication for international, interdisciplinary research, AI techniques, statistical analyses, and high quality scientific writing.
NERCNERC

Fig.1 Map of the northern hemisphere with a long-term mean estimation of the sea-to-air flux of CO2 in units [mol m-2 year-1]. Fig.2 Photo of one commercial ship that is part of the international effort to gather high quality CO2 data. 

 

References / Background reading list

Eyring et al. (2016) Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization. GMD, 9, 1937-1958, doi:10.5194/gmd-9-1937-2016

Fay and McKinley (2014) Global open-ocean biomes: mean and temporal variability. ESSD, 6, 273-284, doi:10.5194/essd-6-273-2014

Intergovernmental Panel on Climate Change (2013) The Physical Science Basis. http://www.ipcc.ch/report/ar5/wg1/ 

Landschützer et al. (2014) Recent variability of the global ocean carbon sink. GBC, 28, 927-949, doi:10.1002/2014GB004853

Longhurst (2007) Ecological Geography of the Sea. Academic Press, London.

Le Quéré et al. (2017) Global Carbon Budget 2017. ESSD, 10, 405-448, doi.org/10.5194/essd-10-405-2018

Reygondeau et al. (2013) Dynamic biogeochemical provinces in the global ocean. GBC, 27, 1-13, doi:10.1002/gbc.20089

SOCAT (2018) https://www.socat.info/

Watson et al. (2009) Tracking the variable North Atlantic Sink for atmospheric CO2. Science, 326, 1391, doi:10.1126/science.1177394

 

Entry requirements

Applicants should have obtained, or be about to obtain, a First or Upper Second Class UK Honours degree, or the equivalent qualifications gained outside the UK.   Applicants with a Lower Second Class degree will be considered if they also have Master’s degree.  Applicants with a minimum of Upper Second Class degree and significant relevant non-academic experience are encouraged to apply.

Candidate Requirements
The candidate may be a computer or data science graduate (or equivalent) with interests in, and some knowledge of, the marine carbon cycle, or a geography or environmental science or natural science graduate (or equivalent), with knowledge and interests in AI, computer science and mathematics.

All applicants would need to meet our English language requirements by the start of the  project http://www.exeter.ac.uk/postgraduate/apply/english/.

 

How to apply

In the application process you will be asked to upload several documents.  Please note our preferred format is PDF, each file named with your surname and the name of the document, eg. “Smith – CV.pdf”, “Smith – Cover Letter.pdf”, “Smith – Transcript.pdf”.

  • CV
  • Letter of application outlining your academic interests, prior research experience and reasons for wishing to undertake the project.
  • Transcript(s) giving full details of subjects studied and grades/marks obtained.  This should be an interim transcript if you are still studying.
  • If you are not a national of a majority English-speaking country you will need to submit evidence of your current proficiency in English.
  • Two References (applicants are recommended to have a third academic referee, if the two academic referees are within the same department/school).

Reference information
You will be asked to name two referees as part of the application process.  It is your responsibility to ensure that your two referees email their references to pgrenquiries@exeter.ac.uk, as we will not make requests for references directly; you must arrange for them to be submitted by 7 January 2019

References should be submitted to us directly in the form of a letter. Referees must email their references to us from their institutional email accounts. We cannot accept references from personal/private email accounts, unless it is a scanned document on institutional headed paper and signed by the referee.

All application documents must be submitted in English. Certified translated copies of academic qualifications must also be provided.

The closing date for applications is midnight on 7 January 2019.  Interviews will be held between 4 and 15 February 2019.

If you have any general enquiries about the application process please email pgrenquiries@exeter.ac.uk.  Project-specific queries should be directed to the supervisor.


Data Sharing
During the application process, the University may need to make certain disclosures of your personal data to third parties to be able to administer your application, carry out interviews and select candidates.  These are not limited to, but may include disclosures to:

  • the selection panel and/or management board or equivalent of the relevant programme, which is likely to include staff from one or more other HEIs;
  • administrative staff at one or more other HEIs participating in the relevant programme.

Such disclosures will always be kept to the minimum amount of personal data required for the specific purpose. Your sensitive personal data (relating to disability and race/ethnicity) will not be disclosed without your explicit consent.

Summary

Application deadline:7th January 2019
Value:£14,777 per annum for 2018-19
Duration of award:per year
Contact: PGR Enquiries pgrenquiries@exeter.ac.uk