Assessing multiscale visual appearance characteristics of neighbourhoods using geographically weighted principal component analysis in Shenzhen, China

Wu, Chao; Peng, Ningyezi; Ma, Xiangyuan; Li, Sheng; Rao, Jinmeng

doi:10.1016/j.compenvurbsys.2020.101547

Cited by 42 publications

(23 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the existence of constant and local parameters, the locally weighted least squares method is no longer applicable to the calibration of mixed GWR. Therefore, two common methods were proposed to calibrate the mixed GWR, namely, the backfitting algorithm and two‐step estimation method, as noted in previous studies (Mei et al., 2004 , 2006 ; Wu et al., 2019 ; Wu, Peng, Ma, Li, & Rao, 2020 ; Yu et al., 2020 ). For the calibration of GWR, the selection of the optimal bandwidth is important.…”

Section: Methodsmentioning

confidence: 99%

Analyzing COVID‐19 Using Multisource Data: An Integrated Approach of Visualization, Spatial Regression, and Machine Learning

Zhou

Liu

et al. 2021

GeoHealth

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Analyzing COVID‐19 Using Multisource Data: An Integrated Approach of Visualization, Spatial Regression, and Machine Learning

Zhou

Liu

et al. 2021

GeoHealth

Self Cite

View full text Add to dashboard Cite

show abstract

“…This paper collected data on 12,137 housing units in a total of 3186 gated commercial communities. A 1 km buffer zone was constructed to designate the neighbourhood of a residential area [42,43], and all of the location-related characteristics of communities were thus aggregated within a 1 km buffer. The study area, Shenzhen, and the locations of the communities are shown in Figure 2.…”

Section: Data Collectionmentioning

confidence: 99%

Understanding the Effects of Influential Factors on Housing Prices by Combining Extreme Gradient Boosting and a Hedonic Price Model (XGBoost-HPM)

Jiang²,

Ke³

et al. 2021

Land

Self Cite

View full text Add to dashboard Cite

The characteristics of housing and location conditions are the main drivers of spatial differences in housing prices, which is a topic attracting high interest in both real estate and geography research. One of the most popular models, the hedonic price model (HPM), has limitations in identifying nonlinear relationships and distinguishing the importance of influential factors. Therefore, extreme gradient boosting (XGBoost), a popular machine learning technology, and the HPM were combined to analyse the comprehensive effects of influential factors on housing prices. XGBoost was employed to identify the importance order of factors and HPM was adopted to reveal the value of the original non-market priced influential factors. The results showed that combining the two models can lead to good performance and increase understanding of the spatial variations in housing prices. Our work found that (1) the five most important variables for Shenzhen housing prices were distance to city centre, green view index, population density, property management fee and economic level; (2) space quality at the human scale had important effects on housing prices; and (3) some traditional factors, especially variables related to education, should be modified according to the development of the real estate market. The results showed that the demonstrated multisource geo-tagged data fusion framework, which integrated XGBoost and HPM, is practical and supports a comprehensive understanding of the relationships between housing prices and influential factors. The findings in this article provide essential implications for informing equitable housing policies and designing liveable neighbourhoods.

show abstract

“…Based on a comprehensive analysis of the multiscale spatiotemporal characteristics of traditional villages in China, this article summarizes and proposes the basic principles and countermeasures for the coordinated development of traditional villages. 1) Focusing on the coordinated development of traditional villages on a small scale and classifying traditional villages with common features to protect them from multilevel perspectives is important [66]. For example, the special opinion of Zhejiang that divided traditional villages into "ancient architectural villages", "natural ecological villages", "folk villages" and other types can be implemented in other provinces.…”

Section: Discussionmentioning

confidence: 99%

Identifying the Spatiotemporal Patterns of Traditional Villages in China: A Multiscale Perspective

Chen

Zhou

et al. 2020

Land

Self Cite

View full text Add to dashboard Cite

Traditional villages are important carriers of traditional cultural heritage, and they have strong historical, cultural, aesthetic and tourism value for all countries and the international community. In China, the number of traditional villages is currently decreasing each year, and the precious material and non-material heritage is at risk of disappearing in the process of urbanization. A comprehensive understanding of the spatiotemporal patterns of traditional villages on multiple scales has important significance in protecting traditional culture, revitalizing traditional villages and achieving sustainable urbanization. Therefore, the spatiotemporal characteristics of traditional villages at the city, province, and geographic zone scales are explored by a series of Geographic Information System(GIS)-based methods in this article. Specifically, the analysis units are multi-scale, the applied methods are multi-variate, and the identified patterns are multi-perspective. The results demonstrate that the distribution of traditional villages in China is unbalanced over space and time. Moreover, the different spatiotemporal distributions of traditional villages are sensitive to scales. These findings clarify differences in the corresponding geographic and environmental factors, the level of economic development and local policy support. We further suggest that exploring the effective and suitable modes of protection and rural development is necessary. The results of this article revealing the unbalanced spatiotemporal distribution of traditional villages can provide valuable suggestions and insights into alleviating regional inequality in China.

show abstract

Assessing multiscale visual appearance characteristics of neighbourhoods using geographically weighted principal component analysis in Shenzhen, China

Cited by 42 publications

References 65 publications

Analyzing COVID‐19 Using Multisource Data: An Integrated Approach of Visualization, Spatial Regression, and Machine Learning

Analyzing COVID‐19 Using Multisource Data: An Integrated Approach of Visualization, Spatial Regression, and Machine Learning

Understanding the Effects of Influential Factors on Housing Prices by Combining Extreme Gradient Boosting and a Hedonic Price Model (XGBoost-HPM)

Identifying the Spatiotemporal Patterns of Traditional Villages in China: A Multiscale Perspective

Contact Info

Product

Resources

About