Sort by
Refine Your Search
-
develop AI- and deep learning–based computer vision tools to automatically identify and quantify intertidal organisms. Beyond computer vision, it will leverage machine learning for large-scale, data-driven
-
-landslides, orographic rainfall effects and extremes), using the volcanic island of Tenerife as a case study. Some work has been done (e.g. on Hawaii), but knickpoint geometry and using state-of-the-art
-
designed to meet multiple needs in marine biodiversity monitoring. The project aims to develop embedded novel deep learning and computer vision algorithms to extend the system’s capabilities to classify
-
. Analysis of images will investigate the efficacy of manual digital approaches (e.g., Dot Dot Goose) and the development of a marine litter characterisation and quantification algorithm for automated analysis
-
, the project accelerates trait data acquisition by applying computer vision to herbarium specimens and field photos, as well as large language models to extract complementary information from literature and
-
by detecting and predicting threats such as pests, diseases, and environmental stress in line with the UK Plant Biosecurity Strategy. The project harnesses computer vision, deep learning, and large
-
University. How to Apply: All applications should be made online via the above ‘Apply’ button. Under programme name, select ‘School of Social Sciences and Humanities’. Please quote the advertised reference
-
: Applicants should have, or expect to achieve, at least a 2:1 honours degree (or equivalent) in Geography, Environmental Science, Computer Science, or Engineering. A relevant master’s degree and/or experience
-
the above 'Apply' button. Under programme name, select ‘School of Social Sciences and Humanities’. Please quote the advertised reference number, ‘FCDT-26-LU2’, in your application. This PhD is being
-
University. How to Apply: All applications should be made via the 'Apply' button above. Under programme name, select Department of Geography and Environment. Please quote the advertised reference number: FCDT