Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 6, 2026Scientific ReportsOpen Access

A hybrid multi-agent and genetic algorithm framework for multi-objective spatial allocation in urban regeneration

View Full Paper
Ask AI
Bookmark
Share

Authors

QZQiong ZhangJCJianzhi ChenSLShengfeng Liu

Discussion

Loading...

Member takes

Overview

Simulation study demonstrates improved land use and stakeholder satisfaction in urban renewal, indicating that coupled agent-based genetic algorithms enhance planning feasibility.

Key Points

  • To develop and evaluate IMAGO, an integrated framework coupling multi-agent systems with multi-objective genetic algorithms for spatial allocation in complex urban regeneration.
  • Coupled a multi-agent system representing public authorities, developers, and residents with a multi-objective genetic algorithm.
  • Integrated parcel-level geospatial data, socioeconomic indicators, ecological limits, and dynamic stakeholder negotiations into the spatial optimization cycle in Wuhan's core urban zone.
  • IMAGO outperformed conventional planning approaches across key metrics, achieving land-use diversity of 0.842 ± 0.025, park service coverage of 0.683 ± 0.020, inhabitant satisfaction of 0.756 ± 0.022, and developer return on investment of 1.842 ± 0.045.
  • The generated layouts successfully converted obsolete industrial areas into mixed-use neighborhoods, reassigned peripheral zones to ecological buffers, and unified fragmented green spaces.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a9d1e7228139818eab2154chttps://doi.org/10.1038/s41598-026-60992-y
View Full Paper
Ask AI
Bookmark
Share