Assessing Greenspace Attractiveness with ChatGPT, Claude, and Gemini: Do AI Models Reflect Human Perceptions?

TL;DR

This study evaluates how well multimodal large language models can assess greenspace attractiveness compared to human perceptions, revealing strengths in formal spaces and limitations in informal spaces, emphasizing the need for human oversight.

Contribution

It demonstrates the potential and limitations of AI models in assessing greenspace attractiveness, highlighting the importance of human judgment and context in urban planning.

Findings

High agreement between AI and humans for attractive formal greenspaces

Low alignment for informal spaces and unattractive formal spaces

Models focus on aesthetic features, underrepresenting safety and infrastructure

Abstract

Understanding greenspace attractiveness is essential for designing livable and inclusive urban environments, yet existing assessment approaches often overlook informal or transient spaces and remain too resource intensive to capture subjective perceptions at scale. This study examines the ability of multimodal large language models (MLLMs), ChatGPT GPT-4o, Claude 3.5 Haiku, and Gemini 2.0 Flash, to assess greenspace attractiveness similarly to humans using Google Street View imagery. We compared model outputs with responses from a geo-questionnaire of residents in Lodz, Poland, across both formal (for example, parks and managed greenspaces) and informal (for example, meadows and wastelands) greenspaces. Survey respondents and models indicated whether each greenspace was attractive or unattractive and provided up to three free text explanations. Analyses examined how often their attractiveness judgments aligned and compared their explanations after classifying them into shared reasoning categories. Results show high AI human agreement for attractive formal greenspaces and unattractive informal spaces, but low alignment for attractive informal and unattractive formal greenspaces. Models consistently emphasized aesthetic and design oriented features, underrepresenting safety, functional infrastructure, and locally embedded qualities valued by survey respondents. While these findings highlight the potential for scalable pre-assessment, they also underscore the need for human oversight and complementary participatory approaches. We conclude that MLLMs can support, but not replace, context sensitive greenspace evaluation in planning practice.