Geospatial Systems - Carrow Morris-Wiltshire
In partnership with
G.19a, Cassie Building, Newcastle University, NE1 7RU
I embarked on my journey with the Geospatial Systems CDT in September 2022, following the completion of an MEng in Civil and Structural Engineering at Newcastle University in June 2022. In the months that followed, I immersed myself in the world of sustainability consultancy, joining a team focussed on carbon reporting for the real estate sector. My responsibilities included designing and implementing automated data processing pipelines to enhance reporting workflows.
It was during my master’s program and this stint in industry that my passion for data science, systems engineering, and the concept of ‘smart cities’ flourished. As part of my MEng dissertation, I conducted a spatial analysis of ‘walkability’ in Newcastle upon Tyne, leveraging Python to dissect and visualize complex geospatial data. It was shortly after expressing my intent to pursue a second master’s in data science that I serendipitously discovered the Geospatial Systems CDT.
What sets the CDT apart is its unique intersection of academia and industry. This program seamlessly combines my penchant for independent research with the invaluable guidance of academic and industry professionals. With a 3+1 program structure, I have the opportunity to complete a fully funded 1-year MRes in data science, followed by a 3-year PhD, supported by the tools and resources essential for honing both my technical and professional skills.
While my long-term career goals remain fluid, they are grounded in an unwavering commitment to continuous learning and the pursuit of novel experiences. I am certain that my academic journey will be enriched by the fascinating people and opportunities I encounter, shaping my path toward meaningful contributions in the world of geospatial systems and smart cities.
Real-Time Simulation of Urban Systems Using Deep Learning
My research aims to address some of the complex challenges inherent in modelling urban systems, which exhibit non-deterministic and non-linear behaviour’s. It highlights the limitations of existing solutions, particularly agent-based models (ABMs), due to the absence of robust validation methods, and inability to handle real-time data. My project will take employ a hybrid deep-learning model to create an ’emulator’ of an ABM, bridging the gap between theoretical models and real data. By leveraging existing centralised repositories of real-time urban data, the research aims to predict the spatio-temporal dynamics of urban agents. This approach has the potential to move us closer to the creation of an ‘urban digital twin,’ offering insights into the behaviour of complex urban systems and non-independent sensors’ spatio-temporal dependencies, allowing for more effective response to developing events, like overcrowding or flooding.