Using deep learning to examine street view green and blue spaces and their associations with geriatric depression in Beijing, China

Helbich, Marco; Yao, Yao; Liu, Ye; Zhang, Jinbao; Liu, Penghua

doi:10.1016/j.envint.2019.02.013

Cited by 425 publications

(263 citation statements)

References 76 publications

(147 reference statements)

Supporting

Mentioning

241

Contrasting

Unclassified

Order By: Relevance

“…To extract streetscape greenery objects (e.g., plants and trees), a supervised machine learning approach based on semantic image segmentation techniques was implemented [31]. More precisely, we used a fully convolutional neural network for semantic image segmentation (FCN-8s) [38] together with the online ADE20K dataset of annotated images for training purposes [45].…”

Section: Greenery Datamentioning

confidence: 99%

“…A preliminary study carried out in Beijing, China, showed that streetscape greenery derived from street view data was inversely 1 As a multi-dimensional construct, mental wellbeing constitutes positive states of psychological, life satisfaction, as well as emotional health [63]. correlated with depressive symptoms among elderly people, while this was not the case for NDVI [31]. This suggests that streetscape greenery is particularly vital in dense Chinese inner cities, where larger areas of greenery are often absent.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Urban greenery and mental wellbeing in adults: Cross-sectional mediation analyses on multiple pathways across different greenery measures

Wang

Helbich

Yao

et al. 2019

Environmental Research

Self Cite

193

101

View full text Add to dashboard Cite

Background: Multiple mechanisms have been proposed to explain how greenery in the vicinity of people's homes enhances their mental health and wellbeing. Mediation studies, however, focus on a limited number of mechanisms and rely on remotely sensed greenery measures, which do not accurately capture how neighborhood greenery is perceived on the ground.Objective: To examine: 1) how streetscape and remote sensing-based greenery affect people's mental wellbeing; 2) whether and, if so, to what extent the associations are mediated by physical activity, stress, air quality and noise, and social cohesion; and 3) whether differences in the mediation across the streetscape greenery and NDVI exposure metrics occurred. Methods:We used a population sample from 2016 of 1,029 adult residents of the metropolis of Guangzhou, China. Mental wellbeing was quantified by the World Health Organization Well-Being Index (WHO-5). Two objective greenery measures were extracted at the neighborhood level: 1) streetscape greenery from street view data via a convolutional neural network, and 2) the normalized difference vegetation index (NDVI) from Landsat 8 remote sensing images. Single and multiple mediation analyses with multilevel regressions were conducted.Results: Streetscape and NDVI greenery were weakly and positively, but not significantly, correlated. Our regression results revealed that streetscape greenery and NDVI were, individually and jointly, positively associated with mental wellbeing. Significant partial mediators for the streetscape greenery were physical activity, stress, air quality and noise, and social cohesion; together, they explained 62% of the association.For NDVI, only physical activity and social cohesion were significant partial mediators, accounting for 22% of the association. Conclusions: Mental health and wellbeing and both streetscape and satellite-derived greenery seem to be both directly correlated and indirectly mediated. Our findings signify that both greenery measures capture different aspects of natural environments and may contribute to people's wellbeing by means of different mechanisms. 3 Keywords Green space; street view data; deep learning; mediation; mental wellbeing; China Highlights  Mechanisms underlying mental health and wellbeing benefits of greenery are not well established.  Streetscape greenery from street view images and a remote sensing-based vegetation index (NDVI) served as exposure measure. Higher mental wellbeing was correlated with more greenery, independently of the measure. Substantial proportions of greenery-wellbeing associations were explained by mediators; for streetscape greenery, mediation was higher. Different pathways seem to be at play across both greenery measures.

show abstract

Section: Greenery Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Urban greenery and mental wellbeing in adults: Cross-sectional mediation analyses on multiple pathways across different greenery measures

Wang

Helbich

Yao

et al. 2019

Environmental Research

Self Cite

193

101

View full text Add to dashboard Cite

show abstract

“…of depression is therefore a key public health concern especially for older people (Helbich et al, 2019;Niles & O'Donovan, 2019;Wang, Liu, et al, 2019b;Wang, Lu, et al, 2019c). Compared to young people, older people spend more time in their neighbourhoods due to retirement and functional restriction Wang, Feng, Xue, Liu, & Wu, 2019a;Wiles et al, 2009;Wiles, Leibing, Guberman, Reeve, & Allen, 2012) and neighbourhood environment may play an important role in their daily life.…”

mentioning

confidence: 99%

Relationship between neighbourhood social participation and depression among older adults: A longitudinal study in China

Wang

Feng

Liu

et al. 2019

Health Soc Care Community

Self Cite

View full text Add to dashboard Cite

Previous research has found a negative linkage between neighbourhood social participation and depressive symptoms in Western countries, but the cross‐sectional design of these studies limits the ability to infer causality. Little attention has been paid to socio‐psychological pathways linking neighbourhood social participation to depressive symptoms among older adults in China. This study aimed to examine the impact of neighbourhood social participation on depressive symptoms among older adults in China. It also further explored the mediating roles of physical activity, social contact among neighbours, and contact with own children in the relationship between social participation and depressive symptoms. Data obtained through three waves (2011, 2013, and 2015) of the China Health and Retirement Longitudinal Study were used. The sample consisted of 10,105 individuals aged 60 and above and 24,623 person‐year records captured during these three waves. Depressive symptoms were assessed using the Center for Epidemiology Studies of Depression scale. Results showed that respondents' depression decreased with an increasing level of neighbourhood social participation, more time spent on physical activities, and a higher frequency of contact with neighbours and with own children. These factors were found to partly mediate the relationship between neighbourhood social participation and depression. The negative relationships between social contact and depression and contact with own children and depression were both strengthened by neighbourhood social participation. In conclusion, physical activity, social contact among neighbours and contact with own children are mechanisms through which neighbourhood social participation lowers the risk of depression among older adults in China.

show abstract

“…Current studies have utilized different big geodata to assess street networks from different perspectives [16][17][18]. For instance, Long and Liu [19] evaluated street greenery by proposing an automatic method to detect greenery from street view images.…”

Section: Introductionmentioning

confidence: 99%

Urban Function as a New Perspective for Adaptive Street Quality Assessment

Liu

et al. 2020

Sustainability

View full text Add to dashboard Cite

Street networks are considered to be one significant component of urban structures that serve various urban functions. Assessing the quality of each street is important for managing natural and public resources, organizing urban morphologies and improving city vitality. While current research focuses on particular street assessment indices, such as accessibility and connectivity, they ignore biases in street assessment caused by differences in urban functions. To address this issue, an adaptive approach to assessing street quality from the perspective of the variation in urban functions is proposed. First, an adaptive urban function detection model is established, with street-level element segmenting using PSPNet and semantic urban function extraction using LDA topic modelling. On this basis, an urban function-driven street quality assessment is proposed to adaptively evaluate multilevel urban streets. Taking Tianhe District in Guangzhou, Guangdong Province, as the study area, experiments using street view images and points of interest (POIs) are applied to validate the proposed approach. The experiment results in a model for adaptive urban function detection with an overall accuracy of 64.3%, showing that streets with different urban functions, including traffic, commercial, and residential functions, can be assessed. The experimental results can facilitate urban function organization and urban land-use planning.

show abstract

Using deep learning to examine street view green and blue spaces and their associations with geriatric depression in Beijing, China

Cited by 425 publications

References 76 publications

Urban greenery and mental wellbeing in adults: Cross-sectional mediation analyses on multiple pathways across different greenery measures

Urban greenery and mental wellbeing in adults: Cross-sectional mediation analyses on multiple pathways across different greenery measures

Relationship between neighbourhood social participation and depression among older adults: A longitudinal study in China

Urban Function as a New Perspective for Adaptive Street Quality Assessment

Contact Info

Product

Resources

About