Computer Science: Fully Funded EPSRCDTP Ph.D. Scholarship: AI-Based Crop Detection Using Spectral Remote Sensing Images
The availability of free satellite images at medium/high spatial resolution has enabled potential solutions to challenge dynamic land use and land cover mapping problems. This project is about developing new AI techniques for crop detection and mapping.
Crop detection is the first step in AI-based time series analyses, which aim to provide basic information for many socio-economic applications. Examples are crop control and yield estimation, change monitoring, supply chain and food security, and climate change policies such as crop rotation, insurance, and fertilization services.
The lack of ground truth data is a major problem for crop detection. This is the case for most time series analyses of historical data. On the other hand, crop-specific variations in visual and chemical properties over a year are realized through spectral satellite images. Therefore, this project focuses on developing AI techniques that efficiently use spectral bands for crop detection.
This is achieved based on (1) an unsupervised framework for time series analysis and identification of effective spectral bands for crop detection; For this purpose, crop fingerprints and other vegetation indices are used to identify critical wavelengths. (2) A supervised framework for developing a novel spectral attention model using visual transformers prediction strategies.
Candidates will normally have an undergraduate degree at 2.1 level in data science, computer science, mathematics, industrial engineering or a closely related discipline plus a recognized master’s degree with merit (or non-UK equivalent as defined by Swansea University ) Must have.
Duolingo English Test
Certify your English proficiency with the Duolingo English Test! The DET is a convenient, fast, and affordable online English test accepted by over 4,000 universities around the world.
This scholarship covers the full cost of UK tuition fees and an annual stipend of £17,668.
Additional research expenses will also be available.
Please visit our website for more information.