Dr David Moffat, Plymouth Marine Laboratory
Professor Alex Nimmo-Smith, SoBMS, University of Plymouth
Dr Dena Bazazian, School of Engineering, Computing, and Mathematics. University of Plymouth
Predicting how ocean life will respond to pressures from increasing human use and climate change is the basis for science-informed decision-making. It requires development of models that enable forecasting of possible outcomes in ‘what if’ scenarios. Such models demand large un-bias biological ‘training’ datasets, which are difficult and expensive to collect and analyse using current human-reliant methods. Greater automation in collection and analysis of observations is needed to deliver sufficiently large datasets to significantly enhance our predictive modelling capability. In this respect Artificial Intelligence (AI) is a potentially powerful tool. This studentship will develop next generation marine biological observing capability by combining vision-enabled smart autonomous platforms with state-of-the-art machine learning.
The student will collect new image-based observation data from Plymouth Sound National Marine Park using the University (and potentially PML’s) small AUVs. They will explore image enhancement methods to improve the quality and consistency of imagery, before annotating these data, providing both baseline observations for the NMP and a high-quality human-annotated image dataset for use in training AI algorithms to identify and quantify coastal benthic animals. The student will train deep-learning algorithms to identify coastal benthic marine taxa from AUV imagery, and trial real-time automated biological monitoring in coastal environments.
The student will have a unique opportunity to expand their outlook into a highly multi-disciplinary domain. They will interact with ecologists, computer scientists, and engineers, developing a wide network beyond the supervisory team. Depending on their background the student may receive training in ecology and taxonomy, artificial intelligence and deep-learning, marine optics, R and Python programming. The student will spend periods of time at PML and thus will benefit from interaction with 2 institutions.
A degree in either an ecological field, computer science field, or other highly numerate field e.g. mathematics, engineering etc is required. We recognise that candidates are unlikely to have both ecological and computer science skills. Thus, we are looking for someone with a strong programming background and a demonstrable capacity to learn new skills and adapt their knowledge to new situations.