A Scene–Object–Economy Framework for Identifying and Validating Urban–Rural Fringe Using Multisource Geospatial Big Data

Abstract

Rapid urbanization has led to the emergence of urban–rural fringes, complex transitional zones that challenge traditional urban–rural dichotomies. While these areas play a crucial role in urban development, their precise identification remains a significant challenge. Existing methods often rely on single-dimensional metrics or administrative boundaries, failing to capture the multi-faceted nature of these zones. This study introduces a novel “Scene–Object–Economy” (SOE) framework to address these limitations and enhance the precision of urban–rural fringe identification. Our approach integrates multisource geospatial big data, including remote sensing imagery, nightlight data, buildings, and Points of Interest (POI), leveraging machine learning techniques. The SOE framework constructs feature from three dimensions: scene (image features), object (buildings), and economy (POIs). This multidimensional methodology allows for a more comprehensive and nuanced mapping of urban–rural fringes, overcoming the constraints of traditional methods. The study demonstrates the effectiveness of the SOE framework in accurately delineating urban–rural fringes through multidimensional validation. Our results reveal distinct spatial patterns and characteristics of these transitional zones, providing valuable insights for urban planners and policymakers. Furthermore, the integration of dynamic population data as a separate layer of analysis offers a unique perspective on population distribution patterns within the identified fringes. This research contributes to the field by offering a more robust and objective approach to urban–rural fringe identification, laying the groundwork for improved urban management and sustainable development strategies. The SOE framework presents a promising tool for future studies in urban spatial analysis and planning.

Keywords

• urban–rural fringe
• remote sensing
• machine learning
• urbanization
• geospatial big data