Scholarlink

<p>Urban spatial dynamic modeling (SDM) has long been used to anticipate land-use change, urban expansion, and infrastructure demand. Yet, despite increasing&#xa0;methodological sophistication, most applications remain oriented toward reproducing spatial patterns rather than supporting sustainability transitions. This perspective argues that SDM is at a turning point and outlines how it can evolve to address climate neutrality, resilience, and equity in both growing and shrinking cities. Five interlinked development pathways are proposed: (i) hybrid AI–theory models balancing predictive accuracy and interpretability; (ii) human-centric accessibility frameworks grounded in time geography; (iii) network-based resilience approaches drawing on graph theory and space syntax; (iv) semantic place functions enabled by vision–language foundation models; and (v) scalable architectures applicable across diverse data and governance contexts. Together, these pathways reposition SDM from a forecasting tool to a transition-support instrument, aligning it with planning support systems and enabling more&#xa0;sustainable and just urban futures.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Urban spatial dynamic modeling in transition: Hybrid, human-centric, and scalable futures

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月14日

查看全文
  • Zipan Cai

摘要

Urban spatial dynamic modeling (SDM) has long been used to anticipate land-use change, urban expansion, and infrastructure demand. Yet, despite increasing methodological sophistication, most applications remain oriented toward reproducing spatial patterns rather than supporting sustainability transitions. This perspective argues that SDM is at a turning point and outlines how it can evolve to address climate neutrality, resilience, and equity in both growing and shrinking cities. Five interlinked development pathways are proposed: (i) hybrid AI–theory models balancing predictive accuracy and interpretability; (ii) human-centric accessibility frameworks grounded in time geography; (iii) network-based resilience approaches drawing on graph theory and space syntax; (iv) semantic place functions enabled by vision–language foundation models; and (v) scalable architectures applicable across diverse data and governance contexts. Together, these pathways reposition SDM from a forecasting tool to a transition-support instrument, aligning it with planning support systems and enabling more sustainable and just urban futures.