1x PhD Studentship in Computer Vision - AI-driven Geographic Data Integration

3.5 year PhD studentship

Geographic Information Systems (GIS) have seen a major shift thanks to recent strides in aerial and satellite data technologies, covering acquisition, sharing, and interpretation. However, challenges in data quality and compatibility persist, necessitating manual corrections that are both time-consuming and limit scalability. Despite the availability of numerous algorithms and tools designed for geographic data integration, existing approaches remain computationally intensive and do not reach the generalisation capabilities obtained from recent AI advances.

Key Objectives:

• Develop robust algorithms for raster-to-vector alignment and/or label correction in geographic datasets.
• Explore unsupervised learning and foundation models to reduce user intervention and improve data quality.
• Achieve measurable objectives related to reducing alignment errors, enhancing geo-localization accuracy, and improving data trustworthiness.
• Assess the effectiveness of developed tools through real-world case studies focusing on environmental monitoring and disaster emergency response tasks.

Supervisor Bio

Jefersson A. dos Santos is an Assistant Professor (Lecturer) in Computer Vision at the University of Sheffield. More info: www.sheffield.ac.uk/dcs/people/academic/jefersson-alex-dos-santos

About the School/Research Group

The successful candidate will join the Computer Vision group in the School of Computer Science. You will have access to state-of-the-art facilities, extensive resources, AI-focused community (shef-ai.github.io) and a collaborative research ecosystem, incl. partnerships with several leading research groups both in the UK and abroad.

99 percent of our research is rated in the highest two categories in the REF 2021, meaning it is classed as world-leading or internationally excellent.

Candidate Requirements

• Minimum 2.1 undergraduate honours degree or Master’s degree with Merit in a relevant discipline (such as Computer Science, Mathematics or others related to the PhD topic).
• If English is not your first language, you must have an IELTS score of 6.5 overall, with no less than 6.0 in each component.
• Self-motivation and enthusiasm for conducting AI research, with a dedication to supporting high-quality work.
• Proficient in Python programming and familiar with deep learning frameworks such as PyTorch and TensorFlow.
• Preferred experience includes presenting or preparing scientific manuscripts for journals or conferences.

How to apply

To apply for a PhD studentship, applications must be made directly to the University of Sheffield using the Postgraduate Online Application Form. Make sure you name Dr Jefersson A. dos Santos as your proposed supervisor(s).

Information on what documents are required and a link to the application form can be found here - https://www.sheffield.ac.uk/postgraduate/phd/apply/applying

Your research proposal should:

• Be no longer than 2 A4 pages + unlimited references
• Outline your reasons for applying for this studentship
• Explain how you would approach the research, including details of your skills and experience in the topic area

Informal enquiries including a letter of interest, an up-to-date CV and transcripts should be directed to j.santos@sheffield.ac.uk. Please add quote [PHD-GEOD4I] in the email subject line.

Funding Notes

The PhD studentship will cover standard UK home tuition fees and provide a tax-free stipend at the standard UK Research Council rate (currently £19,237 for the 2024/25 academic year) for 3.5 years. International students are eligible to apply but you must have the means to self-fund the difference between the UK and overseas tuition fees. Further information on International fees can be found here: www.sheffield.ac.uk/new-students/tuition-fees/fees-lookup.

However, international students meeting specific criteria (such as a strong background in the topic or previous experience in related research projects) may be eligible for a full scholarship.

Advert information