Residential green and blue spaces may be therapeutic for the mental health. However, solid evidence on the linkage between exposure to green and blue spaces and mental health among the elderly in non-Western countries is scarce and limited to exposure metrics based on remote sensing images (i.e., land cover and vegetation indices). Such overhead-view measures may fail to capture how people perceive the environment on the site. This study aimed to compare streetscape metrics derived from street view images with satellite-derived ones for the assessment of green and blue space; and to examine associations between exposure to green and blue spaces as well as geriatric depression in Beijing, China. Questionnaire data on 1190 participants aged 60 or above were analyzed cross-sectionally. Depressive symptoms were assessed through the shortened Geriatric Depression Scale (GDS-15). Streetscape green and blue spaces were extracted from Tencent Street View data by a fully convolutional neural network. Indicators derived from street view images were compared with a satellite-based normalized difference vegetation index (NDVI), a normalized difference water index (NDWI), and those derived from GlobeLand30 land cover data on a neighborhood level. Multilevel regressions with neighborhood-level random effects were fitted to assess correlations between GDS-15 scores and these green and blue spaces exposure metrics. The average cumulative GDS-15 score was 3.4 (i.e., no depressive symptoms). Metrics of green and blue space derived from street view images were not correlated with satellite-based ones. While NDVI was highly correlated with GlobeLand30 green space, NDWI was moderately correlated with GlobeLand30 blue space. Multilevel regressions showed that both street view green and blue spaces were inversely associated with GDS-15 scores and achieved the highest model goodness-of-fit. No significant associations were found with NDVI, NDWI, and GlobeLand30 green and blue space. Our results passed robustness tests. Our findings provide support that street view green and blue spaces are protective against depression for the elderly in China, yet longitudinal confirmation to infer causality is necessary. Street view and satellite-derived green and blue space measures represent different aspects of natural environments. Both street view data and deep learning are valuable tools for automated environmental exposure assessments for health-related studies.

Though global-coverage urban perception datasets have been recently created using machine learning, their efficacy in accurately assessing local urban perceptions for other countries and regions remains a problem. Here we describe a human-machine adversarial scoring framework using a methodology that incorporates deep learning and iterative feedback with recommendation scores, which allows for the rapid and cost-effective assessment of the local urban perceptions for Chinese cities. Using the state-of-the-art Fully Convolutional Network (FCN) and Random Forest (RF) algorithms, the proposed method provides perception estimations with errors less than 10%. The driving factor analysis from both the visual and urban functional aspects demonstrated its feasibility in facilitating local urban perception derivations. With high-throughput and high-accuracy scorings, the proposed human-machine adversarial framework offers an affordable and rapid solution for urban planners and researchers to conduct local urban perception assessments.

Urban land use information plays an important role in urban management, government policy-making, and population activity monitoring. However, the accurate classification of urban functional zones is challenging due to the complexity of urban systems. Many studies have focused on urban land use classification by considering features that are extracted from either high spatial resolution (HSR) remote sensing images or social media data, but few studies consider both features due to the lack of available models. In our study, we propose a novel scene classification framework to identify dominant urban land use type at the level of traffic analysis zone by integrating probabilistic topic models and support vector machine. A land use word dictionary inside the framework was built by fusing natural–physical features from HSR images and socioeconomic semantic features from multisource social media data. In addition to comparing with manual interpretation data, we designed several experiments to test the land use classification accuracy of our proposed model with different combinations of previously acquired semantic features. The classification results (overall accuracy = 0.865, Kappa = 0.828) demonstrate the effectiveness of our strategy that blends features extracted from multisource geospatial data as semantic features to train the classification model. This method can be applied to help urban planners analyze fine urban structures and monitor urban land use changes, and additional data from multiple sources will be blended into this proposed framework in the future.