PhD Studentship: Animal health in marine ecosystems: machine learning and data science to discover structure in unstructured data - March 2019

A great deal of data has been collected on marine animal health in the UK, including wild marine mammals and farmed salmon, but this material often exists in formats that are not amenable to large-scale analysis. These materials represent a wealth of untapped data for conducting population-based investigations of marine animal health. We are seeking a student to develop and apply approaches for deducing the structure of data from unstructured or loosely structured documents, and for augmenting this with data from other sources (e.g., photographs or digital images), to generate useful, context-specific knowledge regarding the health and welfare of marine animals.

The experimental approach will involve the application of machine learning, text mining/natural language processing (NLP), signal/image processing, and artificial intelligence to address problems in context detection and automated data extraction. The suitability of the approaches developed will be evaluated based on their ability to provide useful information from veterinary records for the investigation of spatial and temporal trends in disease and mortality in farmed salmon and in wild marine mammals.

Contact: deepayan.bhowmik@stir.ac.uk. More details: Link. Deadline: 5pm 3rd March 2019.