A5086368010- Urban Transport and Accessibility
- Impact of Light on Environment and Health
- Air Quality Monitoring and Forecasting
- Human Mobility and Location-Based Analysis
- Urban Green Space and Health
- Urban Design and Spatial Analysis
- Noise Effects and Management
- Air Quality and Health Impacts
- Land Use and Ecosystem Services
- Remote-Sensing Image Classification
Turing Institute
2025
MRC Centre for Environment and Health
2023
Imperial College London
2021-2023
Principles of dense, mixed-use environments and pedestrianisation are influential in urban planning practice worldwide. A key outcome espoused by these principles is generating "urban vitality", the continuous use street sidewalk infrastructure throughout day, to promote safety, economic viability attractiveness city neighbourhoods. Vitality hypothesised arise from a nearby mixture primary uses, short blocks, density buildings population diversity age condition surrounding buildings. To...
Advances in computer vision, driven by deep learning, allows for the inference of environmental pollution and its potential sources from images. The spatial temporal generalisability image-based models is crucial their real-world application, but currently understudied, particularly low-income countries where infrastructure measuring complex patterns limited modelling may therefore provide most utility. We employed convolutional neural networks (CNNs) two complementary classification models,...
The interactions of individuals with city neighbourhoods is determined, in part, by the perceived quality urban environments. Perceived neighbourhood a core component vitality, influencing social cohesion, sense community, safety, activity and mental health residents. Large-scale assessment perceptions was pioneered Place Pulse projects. Researchers demonstrated efficacy crowd-sourcing perception ratings image pairs across 56 cities training model to predict from street-view images....
Advances in computer vision, driven by deep learning, allows for the inference of environmental pollution and its potential sources from images. The spatial temporal generalisability image-based models is crucial their real-world application, but currently understudied, particularly low-income countries where infrastructure measuring complex patterns air noise limited modelling may therefore provide most utility. We employed convolutional neural networks (CNNs) two complementary...
BACKGROUND AND AIM: Cities in the developing world are expanding rapidly and undergoing changes to their roads, housing other buildings, vegetation, land use characteristics. Timely data needed ensure that urban change enhance health, wellbeing sustainability. METHODS: We characterise, as mutually exclusive clusters, complex, multidimensional, built natural environments cities with high-resolution satellite images unsupervised deep clustering. apply our approach Accra, Ghana, one of fastest...
BACKGROUND AND AIM: There are limited data on human activity and the environment needed to inform policies target infrastructures improve health wellbeing of residents in cities sub-Saharan Africa, world's fastest urbanising region. METHODS: We collected a bespoke dataset 2.10 million images Accra, Ghana, captured at five-minute internals over ~15 months 145 representative locations. retrained convolutional neural network using manually labelled subset identify people (including street...