Bi-directional Mapping of Morphology Metrics and 3D City Blocks for Enhanced Characterization and Generation of Urban Form

2024-12-20

arXiv.org

AI Summary

In urban morphology, the absence of bidirectional mapping between morphological metrics and three-dimensional (3D) urban blocks leads to a disconnection between performance evaluation and complex morphological generation. Method: This paper introduces the first reversible mapping framework: (1) representing 3D urban blocks with high fidelity via multi-scale morphological metrics—encoded by neural networks and refined through unsupervised clustering—and (2) enabling metric-driven synthesis of diverse, realistic urban blocks. A quantitative method for evaluating metric effectiveness is proposed and applied to 14,248 blocks in New York City to identify an optimal metric subset. Results: The selected metrics significantly improve representation accuracy and generative diversity. This work bridges a critical gap between sustainability-oriented performance assessment and computational morphological generation, enabling performance-driven, closed-loop optimization in urban design.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Urban morphology, examining city spatial configurations, links urban design to sustainability. Morphology metrics play a fundamental role in performance-driven computational urban design (CUD) which integrates urban form generation, performance evaluation and optimization. However, a critical gap remains between performance evaluation and complex urban form generation, caused by the disconnection between morphology metrics and urban form, particularly in metric-to-form workflows. It prevents the application of optimized metrics to generate improved urban form with enhanced urban performance. Formulating morphology metrics that not only effectively characterize complex urban forms but also enable the reconstruction of diverse forms is of significant importance. This paper highlights the importance of establishing a bi-directional mapping between morphology metrics and complex urban form to enable the integration of urban form generation with performance evaluation. We present an approach that can 1) formulate morphology metrics to both characterize urban forms and in reverse, retrieve diverse similar 3D urban forms, and 2) evaluate the effectiveness of morphology metrics in representing 3D urban form characteristics of blocks by comparison. We demonstrate the methodology with 3D urban models of New York City, covering 14,248 blocks. We use neural networks and information retrieval for morphology metric encoding, urban form clustering and morphology metric evaluation. We identified an effective set of morphology metrics for characterizing block-scale urban forms through comparison. The proposed methodology tightly couples complex urban forms with morphology metrics, hence it can enable a seamless and bidirectional relationship between urban form generation and optimization in performance-driven urban design towards sustainable urban design and planning.

Problem

• Bridging the gap between morphology metrics and urban form generation
• Establishing bi-directional mapping for performance-driven urban design
• Enhancing urban sustainability through optimized form-metric integration

Innovation

• Bi-directional mapping of metrics and 3D forms
• Neural networks for morphology metric encoding
• Information retrieval for urban form clustering