Mapping the Character of Geographic Places [Self Funded Students Only]

Historically maps were often designed to engage the reader and to communicate some particular aspects of the places portrayed, including the appearance of landscape and of individual buildings. The internet has been of great value in making maps readily available, but while the main web mapping resources can be effective for purposes of navigation, their value in helping to communicate the nature of places is often very limited indeed. This contrasts with the diversity of local manual map making in which municipalities promote their locality and its landmarks to visitors with engaging and visually attractive maps.

With current geographical information systems it is possible to portray a wide range of aspects of place relating for example to cultural and retail activities and affordances, safety and crime levels, visitors’ perceptions, architectural styles, air quality, conviviality, ethnic profile, historical and literary associations, and natural features. Equally the power of graphic communication and computer vision provides the possibility of automatic creation of very engaging visualisations.

The aim of the project is to develop automated mapping techniques that are effective in communicating the local characteristics of places on multiple dimensions. To achieve this aim we will:

-  Create a taxonomy of place characteristics to classify locations at the level of buildings, streets and neighbourhoods.

- Apply user studies to propose graphic design elements and map styling methods with the potential to communicate different characteristics of place.

-   Develop machine learning methods to classify geographic locations according to various attributes or characteristics identified in the place taxonomy. We will use a mix of unsupervised machine learning methods that identify distinguishing characteristics of places given the multiple data sources, based on digital maps of physical and socio-economic phenomena, and on social media sources such as Wikipedia/DBpedia, Twitter and Flickr. There will also be human subject studies in which people introduce their own categories. Supervised deep learning methods will also be used to create classifiers that exploit the multiple data sources to attach appropriate labels or categories.

- Develop automated deep generative methods that apply the proposed graphic design ideas to create maps representing the distinctive place characteristics of selected geographic locations.

-  Conduct human-subject evaluations of the effectiveness of maps generated by the automated mapping techniques with regard to their communication of particular characteristics of place.

 The supervision team bring skills in computer cartography and geographical information systems, computer vision and machine learning.

Please address enquiries to Prof. Yukun Lai, [Email Address Removed]

Keywords: Artificial Intelligence / Machine Learning / Natural Language Processing / Computer Vision / Social Media / Geography / Cartography / Geospatial Computing

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. 

This application is open to students worldwide. 

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 [Email Address Removed]