CN 11-5366/S     ISSN 1673-1530
"Landscape Architecture is more than a journal."
LI K, MAO Y P, LI Y J. Impact of Subjective and Objective Green Space Characteristics on Mental Health Benefits: An Explainable Machine Learning Approach[J]. Landscape Architecture, 2025, 32(7): 1-9.
Citation: LI K, MAO Y P, LI Y J. Impact of Subjective and Objective Green Space Characteristics on Mental Health Benefits: An Explainable Machine Learning Approach[J]. Landscape Architecture, 2025, 32(7): 1-9.

Impact of Subjective and Objective Green Space Characteristics on Mental Health Benefits: An Explainable Machine Learning Approach

  • Objective Against the backdrop of high-density urban development, residents’ mental health problems have become increasingly severe. Access to urban green spaces is widely regarded as an important approach to improving residents’ mental health. Exploring the impact of green space characteristics on mental health benefits can provide a theoretical basis for urban green space planning and design from the perspective of healthy city. This research aims to clarify the internal relationships between objective and subjective green space characteristics and different mental health benefits (emotional restoration, cognitive enhancement, and stress relief) through explainable machine learning models.
    Methods A mental health perception restoration experiment was carried out in two green spaces (Yanziji Park and Xiamafang Park) in Nanjing, with 56 participants engaged in two-hour free activities in the green spaces. During this period, GPS trajectories, data on objective green space characteristics, data on perception assessment of subjective green space characteristics, and data on self-assessment of mental health benefits were collected. Objective green space characteristics include the Normalized Difference Vegetation Index (NDVI), green view index, canopy density, actual noise dB (A), and spatial attractiveness, which are measured by remote sensing, semantic segmentation, and acoustic instruments. Subjective green space characteristics, such as perceived greenness, perceived noise, and perceived attractiveness, are evaluated by means of a 5-point Likert scale questionnaire. Mental health benefits are divided into the three types of emotional restoration, cognitive enhancement, and stress relief, and are assessed using the Restorative Outcomes Scale (ROS). To analyze and clarify the relationships between objective and subjective green space characteristics and different types of mental health benefits, the research adopts the Light Gradient Boosting Machine (LightGBM) model, combined with SHapley Additive exPlanations (SHAP) to measure and explain the importance of green space characteristics for mental health benefits. Based on the SHAP values, the non-linear relationships between them are further clarified.
    Results Through the analysis of 3 types of mental health benefits and 5 models, the LightGBM model outperforms other algorithms (such as Random Forest and XGBoost) in terms of prediction accuracy (R2: 0.523 – 0.642), with its robustness in capturing complex feature interactions being verified. The SHAP value analysis shows that subjective green space characteristics have a stronger relative impact on mental health outcomes than objective indicators. Specifically, perceived attractiveness is the most important contributing factor, followed by perceived greenness and perceived noise. Notably, the positive impact of perceived greenness on mental health is greater than that of objective indicators such as green visibility and NDVI. In addition, in terms of noise, excessive actual noise could inhibit cognitive enhancement and stress relief. However, moderate perceived noise could promote emotional restoration and stress relief. For example, when the actual noise exceeds 53.88 decibels in the cognitive enhancement model and 52.73 decibels in the stress relief model, negative effects would occur. While in the emotional restoration model, when the perceived noise is within a certain range (less than 2.58 points), it is beneficial for emotional restoration.
    Conclusion The results of this research provide empirical evidence for the internal relationship between urban green spaces and residents’ mental health. Firstly, this research constructs an indicator system covering both objective and subjective characteristics. By combining field measurements, questionnaire surveys, and advanced machine learning algorithms, the research explores the impact of green space characteristics on emotional restoration, cognitive enhancement, and stress relief. Secondly, subjective green space characteristics play a prominent role in influencing mental health benefits. The combined influence of perceived attractiveness and perceived greenness is the most significant. The results of non-linear regression show that actual noise has an inhibitory effect on cognitive enhancement and stress relief, while moderate perceived noise can promote emotional restoration and stress relief. Finally, this research provides a direction for further exploring the in-depth association mechanism between green spaces and mental health, and also offers data support for urban green space planning and design aimed at promoting residents’ mental health.
  • loading

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return