Weekly PhD Newsletter | SIGN UP NOW Weekly PhD Newsletter | SIGN UP NOW

Detecting the impacts of river plumes in coastal waters from satellite imagery using machine learning, NERC GW4+ DTP PhD studentship for 2023 Entry, PhD in Computer Science


   Department of Computer Science

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr Chunbo Luo, Dr Zeyu Fu  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

About the Partnership

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.

Project Background 

Rivers discharging into coastal seas form visible plumes. The impact of fluvial water, nutrients and pollutants carried by rivers to coastal regions is less easily observable due to the highly dynamic nature. Short-term river plume changes following episodic events such as heavy rain have the potential to negatively impact aquaculture, fishing, and recreational activities in and near estuaries. Conventional coastal water quality analysis is carried out in the laboratory using water samples collected sporadically when weather conditions allow. Autonomous monitoring methods including satellite observation complement this effort by looking at water quality through optical proxies such as turbidity and colour. By combining satellite imagery sources in the context of machine learning methods, we expect to be able to produce meaningful estimates of water quality conditions and downstream impacts on human activities.

Project Aims and Methods 

The overarching aim of this project is to use machine learning based satellite image processing techniques for detecting and tracking river plumes and to couple these observations to sparse in situ observation data of chemical and biological water quality. The developed methods will support early warning systems that directly inform the commercial (e.g., aquaculture) and recreational (e.g., diving, fishing, surfing) activities of potential risks in the event of strong storm runoff.

The project will seek to tackle the challenge by exploiting the new generation of medium and high-resolution satellite imagery (Sentinel-1 (radar), optical high resolution from Sentinel-2 MSI (optical) and Landsat 13/14 OLI, and medium-resolution optical imagery from Sentinel-3 OLCI) with advanced computing techniques. In particular, multi-modal learning/fusion will be investigated to make use of important complemental information captured from different data sources including satellite imageries and in-situ obversions. Convolutional neural networks/vision transformers-based autoencoders, as well as sub-pixel level endmember extraction methods, will be employed for semantic segmentation. In addition, transfer representation learning approaches will be studied to reduce the requirements of expensive annotation processes in remote sensing of river plumes.

The student will be encouraged to discuss the detailed research directions, to better match the interests and maximise the project outcomes.

Candidate requirements 

First degree on Computer Science, Mathematics or Engineering. Related knowledge and experience on remote sensing image processing will be particularly encouraged to apply.

Project partners

University of Exeter and PML create an ideal team with complimentary expertise for the proposed research. The student will have direct access to required satellite data and GPU clusters. The funded student will benefit from collaboration and opportunities through the IDSAI and Alan Turing Institute.

Training 

The student will be instructed to take training courses including machine learning, remote sensing, Aquatic optics, academic writing and project management.

For further information and to submit an application please visit - https://www.exeter.ac.uk/study/funding/award/?id=4590


Funding Notes

For eligible successful applicants, the studentship comprises: A stipend for 3.5 years (currently £17,668 p.a. for 2022-23) in line with UK Research and Innovation rates;
Payment of university tuition fees; A research budget of £11,000 for an international conference, lab, field and research expenses. A training budget of £3,250 for specialist training courses and expenses.

References

Background reading and references : Greb, S., Dekker, A. G., Binding, C., Bernard, S., Brockmann, C., DiGiacomo, P., ... & Wang, M. (2018). Earth observations in support of global water quality monitoring. International Ocean-Colour Coordinating Group.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs