An unsupervised approach to Geographical Knowledge Discovery using street level and street network images
This work addresses the need for unsupervised approaches in geography and urban analytics, offering an interpretable method for predicting urban characteristics like street quality, though it is incremental in nature.
The paper tackles the problem of geographic knowledge discovery from urban images using unsupervised learning, proposing ConvPCA to extract interpretable visual latent components from street-level and street-network images, achieving similar accuracy to less interpretable methods.
Recent researches have shown the increasing use of machine learn-ing methods in geography and urban analytics, primarily to extract features and patterns from spatial and temporal data using a supervised approach. Researches integrating geographical processes in machine learning models and the use of unsupervised approacheson geographical data for knowledge discovery had been sparse. This research contributes to the ladder, where we show how latent variables learned from unsupervised learning methods on urbanimages can be used for geographic knowledge discovery. In particular, we propose a simple approach called Convolutional-PCA(ConvPCA) which are applied on both street level and street network images to find a set of uncorrelated and ordered visual latentcomponents. The approach allows for meaningful explanations using a combination of geographical and generative visualisations to explore the latent space, and to show how the learned representation can be used to predict urban characteristics such as streetquality and street network attributes. The research also finds that the visual components from the ConvPCA model achieves similaraccuracy when compared to less interpretable dimension reduction techniques.