Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier B.V.
Abstract
Cities in the developing world are expanding rapidly, and undergoing changes to their roads, buildings, vegetation,
and other land use characteristics. Timely data are needed to ensure that urban change enhances health, wellbeing
and sustainability. We present and evaluate a novel unsupervised deep clustering method to classify and characterise
the complex and multidimensional built and natural environments of cities into interpretable clusters using high resolution satellite images. We applied our approach to a high-resolution (0.3 m/pixel) satellite image of Accra,
Ghana, one of the fastest growing cities in sub-Saharan Africa, and contextualised the results with demographic and
environmental data that were not used for clustering. We show that clusters obtained solely from images capture dis tinct interpretable phenotyp orientation; length and arrangement of roads) environment, and population, either as a unique defining charac teristic (e.g., bodies of water or dense vegetation) or in combination (e.g., buildings surrounded by vegetation or
sparsely populated areas intermixed with roads). Clusters that were based on a single defining characteristic
were robust to the spatial scale of analysis and the choice of cluster number, whereas those based on a combina tion of characteristics changed based on scale and number of clusters. The results demonstrate that satellite data
and unsupervised deep learning provide a cost-effective, interpretable and scalable approach for real-time track ing of sustainable urban development, especially where traditional environmental and demographic data are
limited and infrequent.
Description
Research Article
Keywords
Urban environment, Built and natural environment, High-resolution satellite images, Clustering, Deep learning, Sub-Saharan Africa