Dr Nicolas Pugeault, Department of Computer Science, College of Engineering, Mathematics and Physical Sciences, University of Exeter
Dr James Clark, Plymouth Marine Laboratory
Mrs Elaine Fileman, Plymouth Marine Laboratory
Mrs Claire Widdicombe, Plymouth Marine Laboratory
Location: University of Exeter, Streatham Campus, Exeter EX4 4QJ
This project is one of a number that are in competition for funding from the NERC GW4+ Doctoral Training Partnership (GW4+ DTP). The GW4+ DTP consists of the GW4 Alliance of research-intensive universities: the University of Bath, University of Bristol, Cardiff University and the University of Exeter plus five unique and prestigious Research Organisation partners: British Antarctic Survey, British Geological Survey, Centre for Ecology & Hydrology, the Natural History Museum and Plymouth Marine Laboratory. The partnership aims to provide a broad training in the Earth, Environmental and Life sciences, designed to train tomorrow’s leaders in scientific research, business, technology and policy-making. For further details about the programme please see http://nercgw4plus.ac.uk/
For eligible successful applicants, the studentships comprises:
- An stipend for 3.5 years (currently £15,009 p.a. for 2019/20) 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.
- Travel and accommodation is covered for all compulsory DTP cohort events.
- No course fees for courses run by the DTP
We are currently advertising projects for a total of 10 studentships at the University of Exeter
Enumeration and classification of plankton from environmental samples is key to determining ecosystem function and their role in the marine food web. Traditional enumeration methods using microscopy are often slow and laborious. The availability of automated imaging microscopy platforms such as FlowCam has revolutionized the way plankton can be detected within their natural environment such that there is now a requirement for automated classification techniques to deal with the enormous volume of digital data produced. The aim of this project is to use state-of-the-art machine learning and pattern recognition approaches, such as deep learning, to analyse plankton shapes and develop automated algorithms for plankton identification and quantification. The project is a collaboration between the University of Exeter’s Institute for Data Science and AI and the Plymouth Marine Laboratory (PML), a charity undertaking pioneering marine research to further our understanding of the dynamic and complex marine environment and inform knowledge-based solutions to the challenges our oceans face.
Project Aims and Methods
The aims of this project will be as follows:
Explore the applicability and scalability of deep learning approaches for plankton identification from Flowcam imaging. The quantity of plankton species as well as the variety of appearances within each species makes this problem an especially challenging one for machine learning.
Develop an approach for large-scale plankton identification and quantification from microscopy images containing multiple targets.
Develop a comprehensive dataset and benchmark for plankton classification for the research community.
The project will make use of state-of-the-art machine learning approaches, including Deep Neural Networks and Generative Adversarial Models to analyse the microscopy images. Note that this project offers a large flexibility in its aims and methods used and that both partners would expect the doctoral student to take the lead and propose further development as the project progresses and new developments arise in the literature.
References / Background reading list
- Ellen, J. S., Graff, C. A. and Ohman, M. D. (2019), “Improving plankton image classification using context metadata”, Limnology and Oceanography: Methods.
- Wang, C., Zheng, X., Guo, C., Yu, Z., Yu, J., Zheng, H. and Zheng, B. (2018), “Transferred parallel convolutional neural network for large imbalanced plankton database classification”, in 2018 OCEANS-MTS/IEEE Kobe Techno-Oceans (OTO), IEEE, pp. 1–5.
- Lin, T.-Y., Goyal, P., Girshick, R., He, K. and Dollar, P. (2017), “Focal loss for dense object detection”, in Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988.
- Orenstein, E. C. and Beijbom, O. (2017), “Transfer learning and deep feature extraction for planktonic image data sets”, in 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, pp. 1082–1088.