Project proposals

These are just a few projects I'm interested in. Feel free to reach out if you have a different idea in mind even if it's not related to these topics.

15-minutes cities visualized

Keywords: spatial data analysis, accessibility, facility placement, visualisation, big data, Python, OSM data

Graph summaries of accessibility maps

The idea behind "15-minutes cities" is that within a short walk or bike ride people should have access to all necessary facilities that constitute the essence of urban living, such as parks, shops, cafes, schools, hospitals. Initiatives to transform cities according to this paradigm are currently being implemented across the world, in an attempt to make urban spaces more liveable, sustainable and community-oriented. However, a systematic understanding of the connection between urban form and accessibility is missing. Comparing accessibility across cities can be helpful in this direction - but often the measures being compared are either city-scale metrics or detailed point representations. In this project the student will create succinct representations of accessibility maps that allow comparison across cities, using characteristic functions defined on graph vertices with attributes. The graph summaries obtained can help identify patterns and similarities between cities and classify them based on their topology.

Keywords: spatial data analysis, accessibility, graph summaries, Python, OSM data

Spatiotemporal dependencies in wind energy production

The integration of wind power in the energy grid is dependent on accurate production forecasts. The power output curves between neighbouring wind farms are often correlated temporally and spatially, but currently, these spatiotemporal dependencies are under-utilised in prediction models. Graph neural networks allow for modelling these dependencies. In this project the student will implement a prediction model using a newly released Python library for temporal geometric graph neural networks in order to analyse dependencies across wind farms at different locations in Denmark.

Keywords: graph neural networks, energy data, timeseries analysis, Python

Algorithms for data driven cycling network expansion

As a response to increased traffic congestion and the need to reduce carbon emissions, cities consider ways to modernise, build and extend transit systems. Transit network design solutions can benefit from analysing the large amount of crowd-sourced location data available, which provides valuable insights into population mobility needs. Designing efficient metro lines, bicycle paths, or bus routes brings a number of conflicting constraints into play: from the user's perspective, an efficient transit network is easily accessible and time-efficient, while from the provider's side there is, amongst others, a limitation on the budget. In this project the student will implement a method which, taking into account the above constraints, expands a transit network based on GPS location data from people travelling inside a city.

Keywords: location data analysis, network design, network expansion, graph algorithms, Python, OSM data

Music genre embeddings

Musical genres are inherently ambiguous and difficult to define. Even more so is the task of establishing how genres relate to one another. Yet, genre is perhaps the most common and effective way of describing musical experience. The number of possible genre classifications (e.g. Spotify has over 4000 genre tags, LastFM over 500,000 tags) has made the idea of manually creating music taxonomies obsolete. The aim of this project is to create hyperbolic embeddings to learn a general music taxonomy based on the co-occurrence of genres. The student will create a new dataset based on the One million songs data and will compare the hyperbolic embeddings with a previous implementation.

Keywords: large data processing, scalable algorithms, music genres, hyperbolic embeddings, Python, Spotify data