Incorporating planning intelligence into deep learning: A planning support tool for street network design

TL;DR

This paper introduces a novel AI-powered planning support tool that integrates professional city planning knowledge with deep learning to generate realistic and context-aware street network designs, aiding both experts and lay users.

Contribution

It presents a new method combining deep neural networks with planning guidance for automated, context-aware street network generation.

Findings

Incorporating planning knowledge improves street configuration realism

The tool enables systematic comparison of different street network proposals

Model can be used by both professionals and lay users for city planning

Abstract

Deep learning applications in shaping ad hoc planning proposals are limited by the difficulty in integrating professional knowledge about cities with artificial intelligence. We propose a novel, complementary use of deep neural networks and planning guidance to automate street network generation that can be context-aware, example-based and user-guided. The model tests suggest that the incorporation of planning knowledge (e.g., road junctions and neighborhood types) in the model training leads to a more realistic prediction of street configurations. Furthermore, the new tool provides both professional and lay users an opportunity to systematically and intuitively explore benchmark proposals for comparisons and further evaluations.