The spatiotemporal socio-demography of the Tokyo capital region: a data-driven explorative approach

In the coming decades, most of Asia’s population will reside in megacities, vast urban regions accommodating 10–30 million people. However, Asian megacities will be at the same time situated in the countries whose national population is projected to decline rapidly in the coming decades. Hence, for scholars and policymakers of Asian countries, understanding how the socio-demography of mature, post-growth, megacities will evolve within space and time is crucial to envision long-term and effective spatial governance. Prior studies have shown that varied migration patterns among socio-demographic groups lead to synchronized re-urbanization, post-suburbanization, and urban shrinkage in mature city regions. However, existing studies have limitations: they often exclude large Asian megacities, lack micro-scale analyses, and use predefined spatial typologies/divisions that obscure detailed patterns. To address these research gaps, this study investigated sub-municipal spatiotemporal patterns in Tokyo, the largest Asian megacity, using micro-scale job-household data and unsupervised machine learning clustering. The study revealed that Tokyo, like Euro-American cities, has experienced regional synchronization of (re)urbanization and (post)suburbanization within a complex landscape of shrinkage. However, the synchronized sub/urban growth is not uniform across localities within Tokyo. Complex migration flows seem to create disparities in demographic growth and decline, emphasizing the need for collaborative governance among localities within a megacity. The study contributes to a wider audience who are interested not only in the evolution of cities but also in an emerging application of machine learning to quantitative urban analyses.