Geospatial Systems - Carrow Morris-Wiltshire
In partnership with
Profile
Carrow Morris-Wiltshire
Biography
About Carrow
Carrow Morris-Wiltshire is a PhD candidate at the EPSRC Centre for Doctoral Training (CDT) in Geospatial Systems at Newcastle University. His research, conducted in partnership with the Defence Science and Technology Laboratory (Dstl), focuses on developing resilient Artificial Intelligence (AI) systems for real-time situational awareness in complex operational environments. The core challenge of his work is to transform incomplete and imperfect data from distributed sensor networks into reliable, actionable intelligence for critical decision support.
Carrow’s journey in geospatial systems began with an MEng in Civil and Structural Engineering from Newcastle University. Prior to his PhD, he gained valuable industry experience in sustainability consultancy, where he designed automated data processing pipelines for carbon reporting, reinforcing his interest in leveraging data science for real-world impact.
Currently, Carrow is developing novel deep learning architectures that are inherently robust to the data quality issues—such as sensor dropouts and network failures—that are common in real-world deployments. His methodology uses a hybrid Graph Neural Network (GNN) and Transformer architecture, trained with a masked auto-encoding objective. This approach forces the model to learn how to infer missing information from its spatial context, a critical capability for maintaining operational continuity with imperfect data.
Carrow’s research has been recognised at international conferences, including publications and talks at GISRUK 2024 and CUPUM 2025.
Furthering his expertise in this domain, Carrow was awarded an Enrichment Scheme placement at The Alan Turing Institute. He spends a portion of his research time working with the Environment and Sustainability team, contributing to their open-source DeepSensor project. This work focuses on developing probabilistic deep learning models for fusing sparse and heterogeneous sensor data, directly aligning with his goal of creating trustworthy AI that can quantify its own uncertainty.
As he progresses in his PhD, Carrow is focused on translating his research into practical applications for both urban management and defence, aiming to deliver AI systems that provide reliable decision support even when data is sparse and unreliable.
Research
Real-Time Prediction of Spatiotemporal Dynamics in the Built Environment: An AI and Internet of Things Approach.
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.
Publications
