Assessing the nonlinear impact of green space exposure on psychological stress perception using machine learning and street view images

Aug 5, 2026

Upload by Noah

Urban green space exposure is widely regarded as a nature-based approach to address urban challenges, yet the stress-relieving effects and underlying mechanisms remain insufficiently clarified. This study builds a psychological stress perception measurement scale and combines machine learning with extensive street view image data to estimate stress perception in central Shanghai. It predicts perceived stress using labeled volunteer scores and uses interpretable XGBoost to characterize the nonlinear dose–effect relationship.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Methods

Results

Discussion

TYPE Original Research PUBLISHED 18 September 2024 DOI 10. 3389/fpubh.2024.1402536 OPEN ACCESS EDITED BY Yuan Li, Shaanxi Normal University, China REVIEWED BY Abdullah Nidal Addas, King Abdulaziz University, Saudi Arabia Xin-Chen Hong, Fuzhou University, China *CORRESPONDENCE Yazhuo Zhang [zhangyazhuo@tju.edu.cn](zhangyazhuo@tju.edu.cn)[ ](zhangyazhuo@tju.edu.cn)Yike Hu [huyike11@tju.edu.cn](huyike11@tju.edu.cn) †These authors have contributed equally to this work and share ﬁrst authorship RECEIVED 17 March 2024 ACCEPTED 13 August 2024 PUBLISHED 18 September 2024 CITATION Zhang T, Wang L, Zhang Y, Hu Y and Zhang W (2024) Assessing the nonlinear impact of green space exposure on psychological stress perception using machine learning and street view images. Front. Public Health 12:1402536 . doi: 10.3389/fpubh.2024.1402536 COPYRIGHT © 2024 Zhang, Wang, Zhang, Hu and Zhang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Assessing the nonlinear impact of green space exposure on psychological stress perception using machine learning and street view images Tianlin Zhang1†, Lei Wang1†, Yazhuo Zhang2*, Yike Hu1* and Wenzheng Zhang1 1 School of Architecture, Tianjin University, Tianjin, China, 2 School of Civil Engineering, Tianjin University, Tianjin, China Introduction: Urban green space (GS) exposure is recognized as a nature-based strategy for addressing urban challenges. However, the stress relieving e􀀀ectsand mechanisms of GS exposure are yet to be fully explored. The development of machine learning and street view images o􀀀ers a method for large-scale measurement and precise empirical analysis. Methods: This study focuses on the central area of Shanghai, examining the complex e􀀀ects of GS exposure on psychological stress perception. By constructing a multidimensional psychological stress perception scale and integrating machine learning algorithms with extensive street view images data, we successfully developed a framework for measuring urban stress perception. Using the scores from the psychological stress perception scale provided by volunteers as labeled data, we predicted the psychological stress perception in Shanghai’s central urban area through the Support Vector Machine (SVM) algorithm. Additionally, this study employed the interpretable machine learning model eXtreme Gradient Boosting (XGBoost) algorithm to reveal the nonlinear relationship between GS exposure and residents’ psychological stress. Results: Results indicate that the GS exposure in central Shanghai is generally low, with signiﬁcant spatial heterogeneity. GS exposure has a positive impact on reducing residents’ psychological stress. However, this e􀀀ect has a threshold; when GS exposure exceeds 0.35, its impact on stress perception gradually diminishes. Discussion: We recommend combining the threshold of stress perception with GS exposure to identify urban spaces, thereby guiding precise strategies for enhancing GS. This research not only demonstrates the complex mitigating e􀀀ect of GS exposure on psychological stress perception but also emphasizes the importance of considering the “dose-e􀀀ect” of it in urban planning and construction. Based on open-source data, the framework and methods developed in this study have the potential to be applied in di􀀀erent urban environments, thus providing more comprehensive support for future urban planning. KEYWORDS urban greening, street view, human perception, health planning, sustainable environment Frontiersin Public Health 01 [frontiersin.org](frontiersin.org)

FAQs

How does the study measure psychological stress perception from urban green space exposure?

It constructs a multidimensional psychological stress perception scale, using volunteer-provided scale scores as labeled data for model training and prediction.

Which machine learning models are used, and what is each model’s role?

A Support Vector Machine (SVM) predicts psychological stress perception, while an interpretable XGBoost model is used to reveal the nonlinear relationship between green space exposure and stress.

What is the main nonlinear finding about green space exposure and stress perception?

Green space exposure in central Shanghai shows low overall levels with significant spatial heterogeneity, and it reduces psychological stress up to a threshold; beyond 0.35, the impact gradually diminishes.

Aug 5, 2026

Upload by Noah