This project will apply artificial intelligence methods for natural language processing and machine learning to extract ecological and biodiversity data from textual descriptions of the environments in which biological specimens were collected. Since the ‘Age of Discovery’ (global exploration by humans) centuries ago, wildlife populations have been in decline, with rapid acceleration in species loss in the last 50 years. This biodiversity loss is driven by human development and exploration of the landscape alongside the introduction of invasive non-native species. These anthropogenic activities are a key evolutionary force altering habitat and changing species interactions, meaning species must adapt to survive. In order to help understand these interactions and changes over space and time the project will exploit historic records of plants and animals, stretching back over 100 years. These species descriptions sometimes include descriptions of the environment in which the specimens were collected, and so may contain valuable information about the habitat of the given species at the time at which the specimen was collected. There are currently millions of such digital records of specimens in museums, herbaria and other agencies. Interpreting these descriptions with AI methods will allow us to assess changes in species-habitat associations in recent centuries and what impact increasing human pressures may have had, providing crucial data for maintaining biodiversity.
The project will be a collaboration between the School of Computer Science and Informatics and the School of Biosciences in Cardiff University, and Massey University in New Zealand. It will entail access to specimen collection records from various sources including the Natural History Museum and Kew Gardens in the UK, The Wyoming Herbarium, and Manaaki Whenua – Landcare New Zealand. Data from New Zealand for example has the potential to understand change in geographic distribution and the interactions with particular habitats of invasive species that have had a devastating effect on native wildlife populations, particularly of birds.
The project will involve:
- The use of deep learning methods to determine associations between natural language descriptions of habitat and standard land cover categories (from other data sources);
- Data mining and statistical methods to determine relationships between selected species and their habitats over time; and the interactions between invasive non-native species and affected native species;
- Testing hypotheses about the influence of particular non-native invasive species on individual native species.
- Creation of maps and space-time visualisations of habitat and species interactions.
Keywords: Ecology, biodiversity, invasive species, landcover, natural language processing, deep learning, geographical information systems.
Please address enquiries to Prof Chris Jones: jonescb2@cardiff.ac.uk
Entry Requirements
Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.
Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.
How to apply:
Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below
This project is accepting applications all year round, for self-funded candidates via https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/computer-science-and-informatics
In order to be considered candidates must submit the following information:
- Supporting statement
- CV
- In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
- Qualification certificates and Transcripts
- Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
- References x 2
- Proof of English language (if applicable)
If you have any questions or need more information, please contact COMSC-PGR@cardiff.ac.uk
Continue with Facebook