Search

Creating a walkable environment is an essential step toward the 2030 Sustainable Development Goals. Nevertheless, not all people can enjoy a walkable environment, and neighborhoods with different socioeconomic status are found to vary greatly with walkability. Former studies have typically unraveled the relationship between neighborhood deprivation and walkability from a temporally static perspective and the produced estimations to a point-in-time snapshot were believed to incorporate great uncertainties. The ways in which neighborhood walkability changes over time in association with deprivation remain unclear. Using the case of the Hangzhou metropolitan area, we first measured the neighborhood walkability from 2016 to 2018 by calculating a set of revised walk scores. Further, we applied a machine learning algorithm, the kernel-based regularized least squares regression in particular, to unravel how neighborhood walkability changes in relation to deprivation over time. The results not only capture the nonlinearity in the relationship between neighborhood deprivation and walkability over time, but also highlight the marginal effects of each neighborhood deprivation indicator. Additionally, comparisons of the outputs between the machine learning algorithm and OLS regression illustrated that the machine learning approach did tell a different story and should contribute to remedying the contradictory conclusions in earlier studies. This paper is believed to renew the understanding of social inequalities in walkability by bringing the significance of temporal dynamics and structural interdependences to the fore. [ABSTRACT FROM AUTHOR]

Accurate prediction of urban residential rents is of great importance for landlords, tenants, and investors. However, existing rents prediction models face challenges in meeting practical demands due to their limited perspectives and inadequate prediction performance. The existing individual prediction models often lack satisfactory accuracy, while ensemble learning models that combine multiple individual models to improve prediction results often overlook the impact of spatial heterogeneity on residential rents. To address these issues, this paper proposes a novel prediction model called GERPM, which stands for Geographically Weighted Stacking Ensemble Learning-Based Urban Residential Rents Prediction Model. GERPM comprehensively analyzes the influencing factors of residential rents from multiple perspectives and leverages a geographically weighted stacking ensemble learning approach. The model combines multiple machine learning and deep learning models, optimizes parameters to achieve optimal predictions, and incorporates the geographically weighted regression (GWR) model to consider spatial heterogeneity. By combining the strengths of deep learning and machine learning models and taking into account geographical factors, GERPM aims to improve prediction accuracy and provide robust predictions for urban residential rents. The model is evaluated using housing data from Nanjing, a major city in China, and compared with representative individual prediction models, the equal weight combination model, and the ensemble learning model. The experimental results demonstrate that GERPM outperforms other models in terms of prediction performance. Furthermore, the model's effectiveness and robustness are validated by applying it to other major cities in China, such as Shanghai and Hangzhou. Overall, GERPM shows promising potential in accurately predicting urban residential rents and contributing to the advancement of the rental market. [ABSTRACT FROM AUTHOR]

Urban areas contribute to over 80% of carbon dioxide emissions, and considerable efforts are being undertaken to characterize spatiotemporal variations of CO2 (carbon dioxide) at a city, regional, and national level, aiming at providing pipelines for carbon mission reduction. The complex underlying surface composition of urban areas makes process-based and physiology-based models inadequate for simulating carbon flux in this context. In this study, long short-term memory (LSTM), support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were employed to develop and investigate their viability in estimating carbon flux at the ecosystem level. All the data used in our study were derived from the long-term chronosequence observations collected from the flux towers within urban complex underlying surface, along with meteorological reanalysis datasets. To assess the generalization ability of these models, the following statistical metrics were utilized: coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). Our analysis revealed that the RF model performed the best in simulating carbon flux over long time series, with the highest R2 values reaching up to 0.852, and exhibiting the smallest RMSE and MAE values at 0.293 μmol·m−2·s−1 and 0.157 μmol·m−2·s−1. As a result, the RF model was chosen for simulating carbon flux at spatial scale and assessing the impact of urban impervious surfaces in the simulation. The results showed that the RF model performs well in simulating carbon flux at the spatial scale. The input of impervious surface area index can improve the performance of the RF model in simulating carbon flux, with R2 values of 84.46% (with the impervious surface area index in) and 83.74% (without the impervious surface area index in). Furthermore, the carbon flux in Fengxian District, Shanghai, exhibited significant spatial heterogeneity: the CO2 flux in the western part of Fengxian District was less than in the eastern part, and the CO2 flux gradually increased from the west to the east. In addition, we creatively introduced the diurnal impervious surface area index based on the Kljun model, and clarified the influence of impervious surface on the spatiotemporal simulation of CO2 flux over the complex urban underlying surface. Based on these findings, we conclude that the RF models can be effectively applied for estimating carbon flux on the complex underlying urban surface. The results of our study reduce the uncertainty in modeling carbon cycling in terrestrial ecosystems, and make the variety of models for the carbon cycling of terrestrial ecosystems more diverse. [ABSTRACT FROM AUTHOR]

Urban parks not only enhance urban ecology but also play a crucial role in providing cultural ecosystem services (CESs) for the well-being of urban residents. Both artificial and natural landscape factors within parks contribute significantly to the supply of cultural ecosystem services. To explore public perceptions of landscape factors and CESs, this study focused on 25 urban parks in Hangzhou. Social media data uploaded by park visitors from 2018 to 2023 were collected to establish a corresponding CES indicator framework. Combining computer vision with text mining, we assessed the preferences and correlations between visitor-perceived CESs and park landscape factors. The results indicated that the majority of park visitors perceive CESs (80.00%) with overall satisfaction higher than importance. Among them, aesthetic experiences and recreation showed both high satisfaction and importance. In shared social media photos, arbors (19.01%), herbaceous flowers (8.99%), and groves (8.22%) were frequently presented as landscape factors. The study revealed close correlations between user gender, landscape factors, and perceived CES categories, with females contributing more to the perception of both. There were internal correlations within CES categories, with spiritual services, aesthetic experiences, and recreation showing the most significant associations. Different landscape factors impacted CES categories to varying degrees, and biological landscapes formed by plant and animal factors were considered to provide more CESs. These findings are significant for enhancing the quality of ecological services and biodiversity in parks. [ABSTRACT FROM AUTHOR]

Using traditional tea frost hazard risk assessment results as sample data, the four indicators of minimum temperature, altitude, tea planting area, and tea yield were selected to consider the risk of hazard-causing factors, the exposure of hazard-bearing bodies, and the vulnerability of hazard-bearing bodies. The random forest algorithm was used to construct the frost hazard risk assessment model of Hangzhou tea, and hazard risk assessment was carried out on tea with different cold resistances in Hangzhou. The model's accuracy reached 93% after training, and the interpretation reached more than 0.937. According to the risk assessment results of tea with different cold resistance, the high-risk areas of weak cold resistance tea were the most, followed by medium cold resistance and the least strong cold resistance. Compared with the traditional method, the prediction result of the random forest model has a deviation of only 1.57%. Using the random forest model to replace the artificial setting of the weight factor in the traditional method has the advantages of simple operation, high time efficiency, and high result accuracy. The prediction results have been verified by the existing hazard data. The model conforms to the actual situation and has certain guiding for local agricultural production and early warning of hazards. [ABSTRACT FROM AUTHOR]

Under the background of stock planning, improving the quality of urban public space has become an important work of urban planning, design, and construction management. An accurate diagnosis of the spatial quality of streets and the effective implementation of street renewal planning play important roles in the high-quality development of urban spatial environments. However, traditional planning design and study methods, typically based on questionnaires, interviews, and on-site research, are inefficient and make it difficult to objectively and comprehensively grasp the overall construction characteristics and problems of urban street space in a large area, thus making it challenging to meet the needs of practical planning. Therefore, based on street view images, this study combined machine learning with an artificial audit to put forward a methodological framework for diagnosing the quality issues of street space. The Gongshu District of Hangzhou, China, was selected as a case study, and the diagnosis of quality problems for streets at different grades was achieved. The diagnosis results showed the current situation and problems of the selected area. Simultaneously, a series of targeted strategies for street spatial update planning was proposed to solve these problems. This diagnostic method, based on a combination of subjective and objective approaches, can be conducive to the precise and comprehensive identification of urban public spatial problems, which is expected to become an effective tool to assist in urban renewal and other planning decisions. [ABSTRACT FROM AUTHOR]