Extraction Urban Clusters from Geospatial Data: A Case Study from Switzerland

by   Jingya Yan, et al.

Different techniques were developed to extract urban agglomerations from a big dataset. The urban agglomerations are used to understand the structure and growth of cities. However, the major challenge is to extract urban agglomerations from big data, which can reflect human activities. Community urban cluster refers to spatially clustered geographic events, such as human settlements or activities. It provides a powerful and innovative insight to analyze the structure and growth of the real city. In order to understand the shape and growth of urban agglomerations in Switzerland from spatial and temporal aspects, this work identifies urban clusters from nighttime light data and street network data. Nighttime light data record lights emitted from human settlements at night on the earth's surface. This work uses DMSP-OLS Nighttime light data to extract urban clusters from 1992 to 2013. The street is one of the most important factors to reflect human activities. Hence, urban clusters are also extracted from street network data to understand the structure of cities. Both of these data have a heavy-tailed distribution, which includes power laws as well as lognormal and exponential distributions. The head/tail breaks is a classification method to find the hierarchy of data with a heavy-tailed distribution. This work uses head/tail breaks classification to extract urban clusters of Switzerland. At last, the power law distribution of all the urban clusters was detected at the country level.


page 5

page 10

page 12

page 13


Local Betweenness Centrality Analysis of 30 European Cities

Urban morphology and socioeconomic aspects of cities have been explored ...

Urban Mosaic: Visual Exploration of Streetscapes Using Large-Scale Image Data

Urban planning is increasingly data driven, yet the challenge of designi...

Geometrical effects on mobility

In this paper we analyze the effect of randomly deleting streets of a sy...

Urban Visual Intelligence: Studying Cities with AI and Street-level Imagery

The visual dimension of cities has been a fundamental subject in urban s...

Classification of Urban Morphology with Deep Learning: Application on Urban Vitality

There is a prevailing trend to study urban morphology quantitatively tha...

A shape-based heuristic for the detection of urban block artifacts in street networks

Street networks are ubiquitous components of cities, guiding their devel...

Heavy-tailed kernels reveal a finer cluster structure in t-SNE visualisations

T-distributed stochastic neighbour embedding (t-SNE) is a widely used da...

Please sign up or login with your details

Forgot password? Click here to reset