College of Science & Engineering

The Geospatial Data Science research group sits at the intersection between data science and geospatial data. We explore, analyse, model, and infer from geospatial data to design, develop and provide more intelligent and useful location-based services to make smarter, faster, fairer decisions for inclusive societies. 

The Geospatial Data Science Research Group works towards the process of making sense from geospatial data. We use a wide range of geospatial data, including data from state-of-the-art sensors and 'new forms of data' such as crowdsourced and social media data, and develop and implement novel models that can handle data challenges such as uncertainty, bias, missingness, or privacy concerns associated with them to have a better understanding of society, cities and citizens.

Self-funded projects

+++

Indicative Data Science: Extracting 3D Models of Cities from Unavailability and Degradation of Global Navigation Satellite Systems (GNSS)

This project will implement a crowdsourcing-based approach to create accurate 3D models from the free to use and globally available data of Global Navigation Satellite Systems (GNSS).

The effects of urban features, such as buildings and trees, on GNSS signals, i.e. signal blockage and obstruction, and attenuation, will help to recognise the shape, size, and materials of urban features, through the application of statistical, machine learning (ML) and artificial intelligence (AI) techniques.

The use of freely accessible raw GNSS data, which can be accessed on any current Android device, will enable the production of up to date 3D models at no or low cost, of particular value in developing regions where these models are not currently available.

GNSS

GNSS is the most widely used positioning technique because of free-to-use, privacy-preserving, and globally available signals. However, GNSS signals can be blocked, reflected and/or attenuated by objects, e.g. trees, buildings, walls and windows. While blockage, attenuation and reflection of GNSS signals are common in urban canyons and indoors, making the positioning unreliable, inaccurate or impossible, the affected received signals can act as an indicator of the structure of the surrounding environments.

This means, for example, if the signals are blocked or attenuated, then the size and shape of the obstacles or the type of media/material the signals have gone through or been reflected by can be understood. This needs the precise locations of satellites, and the receiver, and also predicted signal strength level at each location and time.

The crowdsource-based framework, i.e. a mobile app for data capture and a web mapping application for upload of GNSS raw data, will allow the project to have well-distributed data both in space and time. This will ultimately lead to higher quality (more spatially and temporally accurate, complete, precise) 3D models.

However due to the complexity of data, as neither the receiving mobile devices nor the broadcasting satellites are fixed, some novel data mining techniques, based on already existing statistical, ML, and AI techniques, need to be developed during this fellowship. They will handle the high volume, the velocity of change, and the complexity of the spatio-temporal GNSS raw data with high levels of veracity. The spatio-temporal patterns will be used for creating and updating the 3D models of cities at a high level of detail (LoDs), i.e. approximating the façade and the building materials, e.g. windows, from which the signals are reflected or have gone through. The 3D models will feed into 3D-mapping aided GNSS positioning (and integrated with other signals e.g. WiFi) which can ultimately provide more continuous and accurate GNSS positioning in urban canyons and indoors.

---

+++

Developing methods embracing challenges of new forms of data

We develop theoretical and applied solutions to the challenges of 'new forms of data' such as missingness and biases. Our Indicative Data Science project looks at developing solutions based on the mindset that considers the bias, missingness, or low quality as a useful source of data to make inference about the underlying reasons for the missingness and bias.

In the era of big data, open data, social media, and crowdsourced data when 'we are drowning in data', gaps and unavailability, representativeness, and bias issues associated with them may indicate some hidden problems or reasons of biases and missingness. These novel solutions allow us to understand the data, society, and cities better.  

---

+++

Colouring Glasgow

Colouring Glasgow is a knowledge exchange platform that provides open statistical data about the city's buildings and the dynamic behaviour of the stock. We're working to collate, collect, generate, verify over fifty types of data and to visualise many of these datasets.

Our information comes from many different sources. As we are unable to vouch for data accuracy, we are experimenting with how to present data sources, how data are edited over time, and how to ask for data verification, to help you to check reliability and judge how suitable the data are for your intended use. Your help in checking and adding data is very much appreciated.

---

+++

Intelligent Navigation Services

This extremely multi-disciplinary research theme looks at different aspects of navigation including positioning and localisation, path finding and routing algorithms, sense of direction, human computer interaction, cognitive navigation, intelligent mobility, and artificial intelligence.

---

+++

Sensor fusion and Signals of Opportunity

We look at different positioning signals and state-of-the-art sensor data to understand the mobility and movement of people in a non-intrusive way, model occupancy of buildings and energy consumption, better urban planning and use of space, and more recently for contact tracing and social distancing purposes.

---