Machine Learning Modeling of Vitality Characteristics in Historical Preservation Zones with Multi-Source Data
Abstract
:1. Introduction
1.1. Background
1.2. Literature Review
1.2.1. The Definition of Urban Vitality
1.2.2. The Measurement of Urban Vitality
1.2.3. The Influencing Factors and Mechanism of Urban Vitality
1.2.4. Research Gap
2. Materials
2.1. Study Area
2.2. Framework
2.3. Data Source
3. Methods
3.1. Calculation of the Vitality of HPZs (Response Variables)
3.1.1. Physical Space Vitality (PSV)
3.1.2. Cyberspace Vitality (CSV)
3.1.3. Sentiment Degree (SENT)
3.2. Calculation of Influence Factors (Feature Variables)
3.2.1. Calculation of Morphological Indicators
3.2.2. Calculating Functional Indicators
3.2.3. Calculating Road Traffic Indicators
3.2.4. Calculating Visual Indicators
3.3. Regression Analysis
3.3.1. Multivariate Statistical Correlation Analysis
3.3.2. Random Forest Modeling
3.3.3. Feature Importance
4. Results and Discussion
4.1. Results of Variable Correlation
- The physical space vitality (PSV) is negatively related to the density of road intersections density (ID), the number of shopping and consumption places (P_S), the number of catering places (P_C), and the sky view ratio (R_SV); however, it is positively related to the proportion of buildings (R_BU) in the field of vision. In the historical preservation zones (HPZs) with tourism as the main business form, pedestrians prefer the slow-moving system of the ancient city to enjoy their journeys. The denser the road intersections in the zones, the more complicated the road traffic, which is not conducive to people’s staying and entertainment. The number of places for shopping and entertainment is usually the means for commercial districts to attract people. However, due to the restrictions of urban morphology and protection policies, there are generally not many shopping and entertainment places within HPZs. Therefore, they show the opposite trend to the physical space vitality, indicating the difference between HPZs and commercial districts. As for the visual environment, due to the small street scale in the ancient city, the higher the sky view ratio, the higher the width, and the lower the comfort scale. Relatively speaking, the higher the proportion of buildings, the more comfortable the surrounding feeling, which could attract more pedestrian flow. Due to the limitations of the Baidu heat map data, we could not identify the groups who are the real pedestrians, therefore the conclusion maybe biased; however, from the perspective of volume of crowd, it also provides beneficial ideas;
- The sentiment degree of the crowd (SENT) has a negative correlation with the number of public infrastructures (P_I) and road impedance (ACC), by comparison, and a positive correlation with the ratio of pavements (R_P) in the field of vision. The smaller the impedance of the road means, the better the accessibility of the block, meaning that it is more convenient for the pedestrian to reach. The reason the number of public infrastructures is negatively correlated with the sentiment degree of the crowd, contrary to empirical experience, may be caused by the improper layout of public facilities in historical preservation zones (HPZs) at present. The higher the proportion of pavements in the field of vision means a better slow-moving system which is more friendly to pedestrians;
- The cyberspace vitality (CSV) is positively related to the number of entertainment and leisure facilities (P_E), shopping and consumption places (P_S), and caterings places (P_C), while it is negatively related to the average building height (H_M) and floor area ratio (FAR). Among them, the correlation between cyberspace vitality and the number of entertainment and shopping places shows the opposite direction compared to the physical space vitality. We can also deduce that the cyberspace vitality is different from the physical vitality. This is because Sina Weibo is more focused on the young generations; therefore, the historical preservation zones (HPZs) that attract young people to “check-in” are intended to have more “youngster-targeted” business forms, which are closely related to the booming cyber-star economy. The higher floor area ratio and average building height indicate a more enclosed space, with which it is relatively difficult to attract a crowd’s attention.
4.2. Results of Overall Model Performance
4.3. Analysis on Influencing Factors of Vitality Characteristics
- In model_1, the density of the road intersections density (ID) has the most significant impact on the physical space vitality, which may be because more dense intersections mean heavier traffic. Combined with the analysis results in Section 4.1, it reveals that the area with an excessive density of road intersections will have a certain obstacle to attracting offline pedestrian flow. The number of shopping and consumption places (P_S) and road impedance (ACC) are the other factors that have an impact. Combined with the analysis results in 4.1, it is known that these two factors have a negative impact on the vitality of physical space. However, the number of hotel facilities (P_H), the number of public infrastructures (P_I), and the floor area ratio (FAR) have little impact on the physical space vitality;
- According to the importance ranking of features, in model_2, road impedance (ACC) and the number of public infrastructures (P_I) have the greatest impact on the crowd’s sentiment. Combined with the results in Figure 5 of Section 4.1, these two factors negatively affect the population’s sentiment. Secondly, the sky view ratio (R_SV), the number of pedestrians (R_PE), the standard deviation of building height (H_SD), and the average building height (H_M) also have a positive impact on crowd satisfaction. Other factors, especially the number of hotels (P_H) and the number of educational facilities (P_EF), are less critical in the model;
- According to the ranking of the feature importance of model_3, the factors that have a greater impact on the vitality of cyberspace are the number of catering places (P_C) and entertainment facilities (P_E), which have a positive effect on the vitality of cyberspace. Factors such as road impedance (ACC), the number of attractions (P_A), and green looking ratio (R_GL) are also important in the model. However, the number of hotels (P_H), the road intersection density (ID), and the number of public infrastructures (P_I) are of little importance.
5. Conclusions
- (1)
- In terms of research methods and workflow, this paper proposed a framework which combines multi-source data and machine learning technology and integrates with other advanced digital analytical approaches such as CV, NLP, and GIS for the construction of vitality indexes. This could provide a new perspective for urban vitality research and other quantitative research on relevant topics;
- (2)
- As for the performance of models, all Random Forest models proposed in this research have a good fitting ability to the data distribution: the R2 of model 1(physical space vitality) is 0.86, the R2 of model 2(sentiment degree) is 0.85, and the R2 of model 3 is 0.76 (cyberspace vitality), and the RMSE of each model is less than 0.5. All three models established in this study have good performance in explaining variables and generalization, which can be further applied to the large-scale measurement in the other HPZs of Beijing, suggesting more rapid and informative results;
- (3)
- For the influencing factors of vitality, we have summarized the following findings:
- The density of road intersections has the most significant impact on physical space vitality, which is negatively related to the vitality. The density of shopping and consumption places and road impedance are the other factors that negatively impact the vitality of a physical space;
- The factors that have the greatest impact on the sentiment of the crowd are road impedance and the number of public infrastructures, which cause multiple negative effects on the satisfaction of the population;
- The number of catering places and entertainment facilities are the most critical factors that significantly affect a cyberspace’s vitality.
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
Appendix A
Model Types | Physical Space Vitality (R2) | Sentiment Degree (R2) | Cyber Space Vitality (R2) |
---|---|---|---|
Random Forest | 0.86 | 0.85 | 0.76 |
Fine regression Tree | 0.61 | 0.64 | 0.39 |
Linear regression | 0.58 | 0.59 | 0.54 |
Robust linear regression | 0.68 | 0.50 | 0.53 |
Linear SVM | 0.53 | 0.51 | 0.53 |
Gaussian SVM | 0.56 | 0.09 | 0.15 |
Kernel Approximation regression | 0.76 | 0.78 | 0.73 |
Boost tree | 0.72 | 0.80 | 0.67 |
Bagged tree | 0.78 | 0.76 | 0.69 |
Shallow neural network | 0.70 | 0.83 | 0.66 |
2-layer neural network | 0.62 | 0.85 | 0.44 |
Appendix B
References
- Li, M.; Liu, J.; Lin, Y.; Xiao, L.; Zhou, J. Revitalising historic districts: Identifying built environment predictors for street vibrancy based on urban sensor data. Cities 2021, 117, 103305. [Google Scholar] [CrossRef]
- Wang, J. Exploring the Approaches of Adaptive Conservation, Reconstruction and Revitalization of Historic Districts A Case Study of Gunanjie Street in Dingshu, Yixing. Archit. J. 2021, 5, 1–7. [Google Scholar] [CrossRef]
- Whitehand, J.W.R.; Gu, K. Conserving urban landscape heritage: A geographical approach. Procedia-Soc. Behav. Sci. 2010, 2, 6948–6953. [Google Scholar] [CrossRef] [Green Version]
- Whitehand, J.W.R.; Gu, K.; Whitehand, S.M.; Zhang, J. Urban morphology and conservation in China. Cities 2011, 28, 171–185. [Google Scholar] [CrossRef]
- Yong, H.; Sun, Y. Review on Historical District Preservation and Renovation Practice. Planner 2015, 31, 98–104. [Google Scholar]
- Zheng, L.J.; Yang, C. Public Participation in the Dynamic Conservation of Historic Districts. City Plan. Rev. 2005, 7, 63–65. [Google Scholar]
- Yu, D.; Huang, Z.; Wang, C. On Dynamic Protection Planning of Urban Historical Blocks: A Case Study of China First Automobile Works Historical Area. Urban Stud. 2011, 18, 79–83. [Google Scholar]
- Jiang, T.; Dai, J.; Ju, D. Exploration on the implementation method of historic conservation area from street renewal to urban block renewal: The example of Dongzhimennei Avenue in Beijing. Urban Issues 2022, 9, 24–34. [Google Scholar] [CrossRef]
- Wu, J.; Lu, Y.; Gao, H.; Wang, M. Cultivating historical heritage area vitality using urban morphology approach based on big data and machine learning. Comput. Environ. Urban Syst. 2022, 91, 101716. [Google Scholar] [CrossRef]
- Zhou, X.P.; Tang, J.Y. A Study on Commercial Development Pattern and Planning Method of Historic District: Taking Jinli, Kuanzhai Lane and Wneshu District as Example. Urban Plan. Forum 2009, 5, 107–113. [Google Scholar]
- Mao, Z.; Chen, X.; Xiang, Z.; Chen, Y. Research on the Measurement and Influencing Factors of Street Vigour in Historic Districts: A Case Study of Wenming Street Historic District in Kunming. South Archit. 2021, 4, 48–55. [Google Scholar]
- Throsby, D. Investment in urban heritage conservation in developing countries: Concepts, methods and data. City Cult. Soc. 2016, 7, 81–86. [Google Scholar] [CrossRef]
- Chen, Y.; Lei, C. Evolution of the Conservation Problems and Planning Strategies of Pingjiang Historic and Cultural Area: Mechanism Simulation Analysis Based on System Dynamics. Urban Plan. 2022, 46, 84–95. [Google Scholar]
- Wang, J. Problems and solutions in the protection of historical urban areas. Front. Arch. Res. 2012, 1, 40–43. [Google Scholar] [CrossRef] [Green Version]
- Zhong, X. Vigorous Renaissance of Historic Precincts: A Case Study of Furong Historic Precinct in Jinan. Mod. Urban Res. 2011, 26, 44–48. [Google Scholar]
- Lu, X.; Xiao, Y.; Li, M. The Eco-Sustainable Planning and Revitalisation of Historic and Cultural Blocks: A Case Study of Jiang’an South District Renovation in Wuhan. World Archit. 2022, 8, 51–56. [Google Scholar] [CrossRef]
- Wang, M.; Yang, X.; Peng, M.; Yan, X. Tourism Aesthetic Fatigue: Performance Characteristics, Formation Mechanism and Mitigation Measures. Tour. Trib. 2022, 37, 109–117. [Google Scholar] [CrossRef]
- Shang, Q. Underground Space: A View for the Conservation of Beijing Old City. Procedia Eng. 2016, 165, 265–276. [Google Scholar] [CrossRef]
- Zhang, L.; Wang, Y.; Xu, Y.; Li, L. The Improvement Approach of the Historic District’s Evacuation Direction Sign Based on Fuzzy Control. Archit. J. 2017, S2, 40–44. [Google Scholar]
- Xu, M.; Wu, S.; Xu, J. Research on the Renovated Hotels in Historic Districts and Their Contribution to the Vitality of Historic and Cultural Districts, Qingdao. Planners 2019, 35, 43–50. [Google Scholar]
- Wu, Y.; Deng, Y. Study of the Residential Rehabilitation-orient mode for the Historical Districts: Taking Xiaohezhijie Historical District in Hangzhou China and Honmachi District in Takahashi Japan as Examples. Urban Stud. 2016, 23, 51–57+2. [Google Scholar]
- Huang, B.; Zhou, Y.; Li, Z.; Song, Y.; Cai, J.; Tu, W. Evaluating and characterising urban vibrancy using spatial big data: Shanghai as a case study. Environ. Plan. B Urban Anal. City Sci. 2020, 47, 1543–1559. [Google Scholar] [CrossRef]
- Xiao, L.; Lo, S.; Liu, J.; Zhou, J.; Li, Q. Nonlinear and synergistic effects of TOD on urban vibrancy: Applying local explanations for gradient boosting decision tree. Sustain. Cities Soc. 2021, 72, 103063. [Google Scholar] [CrossRef]
- Jacobs, J. The Death and Life of American Cities; Vintage Book Company: New York, NY, USA, 1961. [Google Scholar]
- Gehl, J. Life between Buildings: Using Public Space; Koch, J., Translator; Van Nostrand Reinhold: New York, NY, USA, 1987. [Google Scholar]
- Montgomery, J. Making a city: Urbanity, vitality and urban design. J. Urban Des. 1998, 3, 93–1166. [Google Scholar] [CrossRef]
- Moreno, C.; Allam, Z.; Chabaud, D.; Gall, C.; Pratlong, F. Introducing the “15-Minute City”: Sustainability, Resilience and Place Identity in Future Post-Pandemic Cities. Smart Cities 2021, 4, 93–111. [Google Scholar] [CrossRef]
- Guo, X.; Yang, Y.; Cheng, Z.; Wu, Q.; Li, C.; Lo, T.; Chen, F. Spatial social interaction: An explanatory framework of urban space vitality and its preliminary verification. Cities 2022, 121, 103487. [Google Scholar] [CrossRef]
- Mouratidis, K.; Poortinga, W. Built environment, urban vitality and social cohesion: Do vibrant neighbourhoods foster strong communities? Landsc. Urban Plan. 2020, 204, 103951. [Google Scholar] [CrossRef]
- Mu, B.; Liu, C.; Mu, T.; Xu, X.; Tian, G.; Zhang, Y.; Kim, G. Spatiotemporal fluctuations in urban park spatial vitality determined by on-site observation and behavior mapping: A case study of three parks in Zhengzhou City, China. Urban For. Urban Green. 2021, 64, 127246. [Google Scholar] [CrossRef]
- Meng, Y.; Xing, H. Exploring the relationship between landscape characteristics and urban vibrancy: A case study using morphology and review data. Cities 2019, 95, 102389. [Google Scholar] [CrossRef]
- Wu, C.; Ye, X.; Ren, F.; Du, Q. Check-in behaviour and spatio-temporal vibrancy: An exploratory analysis in Shenzhen, China. Cities 2018, 77, 104–116. [Google Scholar] [CrossRef]
- Dong, X.; Lian, Y. A review of social media-based public opinion analyses: Challenges and recommendations. Technol. Soc. 2021, 67, 101724. [Google Scholar] [CrossRef]
- Li, F.; Li, F.; Li, S.; Long, Y. Deciphering the recreational use of urban parks: Experiments using multi-source big data for all Chinese cities. Sci. Total Environ. 2020, 701, 134896. [Google Scholar] [CrossRef] [PubMed]
- Jin, X.; Long, Y.; Sun, W.; Lu, Y.; Yang, X.; Tang, J. Evaluating cities’ vitality and identifying ghost cities in China with emerging geographical data. Cities 2017, 63, 98–109. [Google Scholar] [CrossRef]
- Wu, J.; Ta, N.; Song, Y.; Lin, J.; Chai, Y. Urban form breeds neighborhood vibrancy: A case study using a GPS-based activity survey in suburban Beijing. Cities 2018, 74, 100–108. [Google Scholar] [CrossRef]
- Zhang, L.; Zhang, R.; Yin, B. The impact of the built-up environment of streets on pedestrian activities in the historical area. Alex. Eng. J. 2021, 60, 285–300. [Google Scholar] [CrossRef]
- Lan, F.; Gong, X.; Da, H.; Wen, H. How do population inflow and social infrastructure affect urban vitality? Evidence from 35 large- and medium-sized cities in China. Cities 2020, 100, 102454. [Google Scholar] [CrossRef]
- Tu, W.; Zhu, T.; Xia, J.; Zhou, Y.; Lai, Y.; Jiang, J.; Li, Q. Portraying the spatial dynamics of urban vibrancy using multisource urban big data. Comput. Environ. Urban Syst. 2010, 80, 101428. [Google Scholar] [CrossRef]
- García-Palomares, J.C.; Salas-Olmedo, M.H.; Moya-Gómez, B.; Condeço-Melhorado, A.; Gutiérrez, J. City dynamics through Twitter: Relationships between land use and spatiotemporal demographics. Cities 2018, 72, 310–319. [Google Scholar] [CrossRef]
- Zong, W.; Zhang, J. Use of smartphone applications and its impacts on urban life: A survey and random forest analysis in Japan. Sustain. Cities Soc. 2019, 49, 101589. [Google Scholar] [CrossRef]
- Blanford, J.I.; Huang, Z.; Savelyev, A.; MacEachren, A.M. Geo-Located Tweets. Enhancing Mobility Maps and Capturing Cross-Border Movement. PLoS ONE 2015, 10, e0129202. [Google Scholar] [CrossRef]
- Wu, Z.; Ye, Z. Research on Urban Spatial Structure Based on Baidu Heat Map: A Case Study on the Central City of Shanghai. City Plan. Rev. 2016, 4, 33–40. [Google Scholar]
- Liu, L.; Liu, Z. The Recognition of CAZ in Shanghai Based on Evaluated POI. In Big Data Support of Urban Planning and Management; Springer: Cham, Switzerland, 2018; pp. 99–112. [Google Scholar]
- Long, Y.; Mao, M.; Mao, Q.; Shen, Z.; Zhang, Y. Fine-Scale Urban Modeling and Its Opportunities in the “Big Data” Era: Methods, Dataand Em-Pirical Studies. Hum. Geogr. 2014, 29, 7–13. [Google Scholar]
- Yue, W.; Chen, Y.; Zhang, Q.; Liu, Y. Spatial Explicit Assessment of Urban Vitality Using Multi-Source Data: A Case of Shanghai, China. Sustainability 2019, 11, 638. [Google Scholar] [CrossRef] [Green Version]
- Wang, X.; Zhang, Y.; Yu, D.; Qi, J.; Li, S. Investigating the spatiotemporal pattern of urban vibrancy and its determinants: Spatial big data analyses in Beijing, China. Land Use Policy 2022, 119, 106162. [Google Scholar] [CrossRef]
- Sung, H.; Lee, S. Residential built environment and walking activity: Empirical evidence of Jane Jacobs’ urban vitality. Transp. Res. Part D Transp. Environ. 2015, 41, 318–329. [Google Scholar] [CrossRef]
- Zhang, A.; Li, W.; Wu, J.; Lin, J.; Chu, J.; Xia, C. How can the urban landscape affect urban vitality at the street block level? A case study of 15 metropolises in China. Environ. Plan. B Urban Anal. City Sci. 2021, 48, 1245–1262. [Google Scholar] [CrossRef]
- Li, X.; Li, Y.; Jia, T.; Zhou, L.; Hijazi, I.H. The six dimensions of built environment on urban vitality: Fusion evidence from multi-source data. Cities 2022, 121, 103482. [Google Scholar] [CrossRef]
- Huang, D.; Liu, Z.; Zhao, X.; Zhao, P. Emerging polycentric megacity in China: An examination of employment subcenters and their influence on population distribution in Beijing. Cities 2017, 69, 36–45. [Google Scholar] [CrossRef]
- Koohsari, M.J.; Kaczynski, A.T.; Mcormack, G.R.; Sugiyama, T. Using Space Syntax to Assess the Built Environment for Physical Activity: Applications to Research on Parks and Public Open Spaces. Leis. Sci. 2014, 36, 206–216. [Google Scholar] [CrossRef]
- Liu, S.; Lai, S.-Q.; Liu, C.; Jiang, L. What influenced the vitality of the waterfront open space? A case study of Huangpu River in Shanghai, China. Cities 2021, 114, 103197. [Google Scholar] [CrossRef]
- Allam, Z.; Nieuwenhuijsen, M.; Chabaud, D.; Moreno, C. The 15-minute city offers a new framework for sustainability, liveability, and health. Lancet Planet. Health 2022, 6, e181–e183. [Google Scholar] [CrossRef]
- Allam, Z.; Bibri, S.E.; Chabaud, D.; Moreno, C. The ‘15-Minute City’ concept can shape a net-zero urban future. Humanit. Soc. Sci. Commun. 2022, 9, 126. [Google Scholar] [CrossRef]
- Niu, Y.; Mi, X.; Wang, Z. Vitality evaluation of the waterfront space in the ancient city of Suzhou. Front. Arch. Res. 2021, 10, 729–740. [Google Scholar] [CrossRef]
- Liang, Y.; D’Uva, D.; Scandiffio, A.; Rolando, A. The more walkable, the more livable?—Can urban attractiveness improve urban vitality? Transp. Res. Procedia 2022, 60, 322–329. [Google Scholar] [CrossRef]
- Wu, W.; Dang, Y.; Zhao, K. Spatial Characteristics of Urban Vitality based on Multi-dimensional Perception. J. Geo-Inf. Sci. 2022, 24, 1867–1882. [Google Scholar] [CrossRef]
- Wu, Y.; Wang, L.; Fan, L.; Yang, M.; Zhang, Y.; Feng, Y. Comparison of the spatiotemporal mobility patterns among typical subgroups of the actual population with mobile phone data: A case study of Beijing. Cities 2020, 100, 102670. [Google Scholar] [CrossRef]
- Yang, J.; Cao, J.; Zhou, Y. Elaborating non-linear associations and synergies of subway access and land uses with urban vitality in Shenzhen. Transp. Res. Part A Policy Pract. 2021, 144, 74–88. [Google Scholar] [CrossRef]
- Chen, Z.; Dong, B.; Pei, Q.; Zhang, Z. The impacts of urban vitality and urban density on innovation: Evidence from China’s Greater Bay Area. Habitat Int. 2022, 119, 102490. [Google Scholar] [CrossRef]
- Yang, C.; Lv, C. Study on Slow-Traffic Vitality Impact Factors of Urban Waterfront Based on GWR Model: Taking Typical Waterfront Blocks along Huangpu River as Examples. J. Hum. Settl. West China 2022, 37, 55–62. [Google Scholar] [CrossRef]
- Wu, F.; Chen, M. Research on Hot Trends and Case Studies of the Vitality of Foreign Public Spaces Using Citespace in the Past 15 Years. Urban Stud. 2021, 28, 6–12. [Google Scholar]
- Mushkani, R.A.; Ono, H. The role of land use and vitality in fostering gender equality in urban public parks: The case of Kabul city, Afghanistan. Habitat Int. 2021, 118, 102462. [Google Scholar] [CrossRef]
- Niu, T.; Qing, L.; Han, L.; Long, Y.; Hou, J.; Li, L.; Tang, W.; Teng, Q. Small public space vitality analysis and evaluation based on human trajectory modeling using video data. Build. Environ. 2022, 225, 109563. [Google Scholar] [CrossRef]
- Gómez-Varo, I.; Delclòs-Alió, X.; Miralles-Guasch, C. Jane Jacobs reloaded: A contemporary operationalisation of urban vitality in a district in Barcelona. Cities 2022, 123, 103565. [Google Scholar] [CrossRef]
- Wang, F.; Yan, L.; Xiong, X.; Wu, B. A Study on Tourist Cognition of Urban Memory in Historic Sites: A Case Study of Alley Nanluogu Historic Site in Beijing. Acta Geogr. Sin. 2012, 67, 545–556. [Google Scholar]
- Chen, L.; Zhang, W. The Change and Reconstruction of Local Culture in Response to Urban Renewal and Globalization: A Case Study of Shichahai Historic District. Prog. Geogr. 2010, 29, 649–656. [Google Scholar]
- Zhang, Y.; Yang, C.; Qi, L. Study on the Assessment of Street Vitality and Influencing Factors in the Historic District—A Case Study of Shichahai Historic District. Chin. Landsc. Archit. 2019, 35, 106–111. [Google Scholar]
- González Martínez, P. Authenticity as a challenge in the transformation of Beijing’s urban heritage: The commercial gentrification of the Guozijian historic area. Cities 2016, 59, 48–56. [Google Scholar] [CrossRef] [Green Version]
- Shin, H.B. Urban conservation and revalorisation of dilapidated historic quarters: The case of Nanluoguxiang in Beijing. Cities 2010, 27, S43–S54. [Google Scholar] [CrossRef]
- Deng, Y.; Mao, Q. Study on the Formation and Scale of Block of Beijing Inner City Based on Qianlong map. Urban Plan. 2003, 10, 58–65. [Google Scholar]
- Rigatti, S.J. Random forest. J. Insur. Med. 2017, 47, 31–39. [Google Scholar] [CrossRef] [Green Version]
- Hu, W.; Shen, S.; Yang, F.; Bao, Z. Research on the Evaluation and Influencing Factors of the Vitality of Historical and Cultural Districts based on Multi-source Big Data. Chin. Overseas Archit. 2021, 9, 96–101. [Google Scholar] [CrossRef]
- Long, Y.; Huang, C. Does block size matter? The impact of urban design on economic vitality for Chinese cities. Environ. Plan. B Urban Anal. City Sci. 2019, 46, 406–422. [Google Scholar] [CrossRef] [Green Version]
- Liu, S.; Ge, J.; Bai, M.; Yao, M.; He, L.; Chen, M. Toward classification-based sustainable revitalisation: Assessing the vitality of traditional villages. Land Use Policy 2022, 116, 106060. [Google Scholar] [CrossRef]
- Koroteev, M.V. BERT: A Review of Applications in Natural Language Processing and Understanding. arXiv 2021, arXiv:2103.11943. [Google Scholar]
- Huang, C.; Gong, P.; Ding, R.; Qu, S.; Yang, X. Comprehensive Analysis of the Vitality of Urban Central Activities Zone Based on Multi-Source Data. In Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Virtual Conference, 29 March–1 April 2021; pp. 549–558. [Google Scholar] [CrossRef]
- Li, Y.; Yabuki, N.; Fukuda, T. Exploring the association between street built environment and street vitality using deep learning methods. Sustain. Cities Soc. 2022, 79, 103656. [Google Scholar] [CrossRef]
- He, Q.; He, W.; Song, Y.; Wu, J.; Yin, C.; Mou, Y. The impact of urban growth patterns on urban vitality in newly built-up areas based on an association rules analysis using geographical ‘big data’. Land Use Policy 2018, 78, 726–738. [Google Scholar] [CrossRef]
- Zhang, F.; Zhou, B.; Liu, L.; Liu, Y.; Fung, H.H.; Lin, H.; Ratti, C. Measuring human perceptions of a large-scale urban region using machine learning. Landsc. Urban Plan. 2018, 180, 148–160. [Google Scholar] [CrossRef]
- Qiu, W.; Zhang, Z.; Liu, X.; Li, W.; Li, X.; Xu, X.; Huang, X. Subjective or objective measures of street environment, which are more effective in explaining housing prices? Landsc. Urban Plan. 2022, 221, 104358. [Google Scholar] [CrossRef]
- Ma, X.; Ma, C.; Wu, C.; Xi, Y.; Yang, R.; Peng, N.; Zhang, C.; Ren, F. Measuring human perceptions of streetscapes to better inform urban renewal: A perspective of scene semantic parsing. Cities 2021, 110, 103086. [Google Scholar] [CrossRef]
- Lu, Y. Using Google Street View to investigate the association between street greenery and physical activity. Landsc. Urban Plan. 2019, 191, 103435. [Google Scholar] [CrossRef]
- Zhang, F.; Zu, J.; Hu, M.; Zhu, D.; Kang, Y.; Gao, S.; Zhang, Y.; Huang, Z. Uncovering inconspicuous places using social media check-ins and street view images. Comput. Environ. Urban Syst. 2020, 81, 101478. [Google Scholar] [CrossRef]
- Wang, R.; Yuan, Y.; Liu, Y.; Zhang, J.; Liu, P.; Lu, Y.; Yao, Y. Using street view data and machine learning to assess how perception of neighborhood safety influences urban residents’ mental health. Health Place 2019, 59, 102186. [Google Scholar] [CrossRef] [PubMed]
- Zhou, H.; He, S.; Cai, Y.; Wang, M.; Su, S. Social inequalities in neighborhood visual walkability: Using street view imagery and deep learning technologies to facilitate healthy city planning. Sustain. Cities Soc. 2019, 50, 101605. [Google Scholar] [CrossRef]
- Larkin, A.; Gu, X.; Chen, L.; Hystad, P. Predicting perceptions of the built environment using GIS, satellite and street view image approaches. Landsc. Urban Plan. 2021, 216, 104257. [Google Scholar] [CrossRef] [PubMed]
- Yang, J.; Rong, H.; Kang, Y.; Zhang, F.; Chegut, A. The financial impact of street-level greenery on New York commercial buildings. Landsc. Urban Plan. 2021, 214, 104162. [Google Scholar] [CrossRef]
- Biau, G.; Scornet, E. A random forest guided tour. TEST 2016, 25, 197–227. [Google Scholar] [CrossRef] [Green Version]
- Ho, T.K. Random decision forests. In Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada, 14–16 August 1995; Volume 1, pp. 278–282. [Google Scholar] [CrossRef]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Green Version]
- Li, X.; Li, L.; Wang, X.; Lin, Q.; Wu, D.; Dong, Y.; Han, S. Visual quality evaluation model of an urban river landscape based on random forest. Ecol. Indic. 2021, 133, 108381. [Google Scholar] [CrossRef]
- Yang, L.; Ao, Y.; Ke, J.; Lu, Y.; Liang, Y. To walk or not to walk? Examining non-linear effects of streetscape greenery on walking propensity of older adults. J. Transp. Geogr. 2021, 94, 103099. [Google Scholar] [CrossRef]
- Belgiu, M.; Drăguţ, L. Random Forest in remote sensing: A review of applications and future directions. ISPRS J. Photogramm. Remote Sens. 2016, 114, 24–31. [Google Scholar] [CrossRef]
- Belgiu, M.; Drăguţ, L. Comparing supervised and unsupervised multiresolution segmentation approaches for extracting buildings from very high-resolution imagery. ISPRS J. Photogramm. Remote Sens. 2014, 96, 67–75. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 2011, 12, 2825–2830. [Google Scholar]
- Nembrini, S.; König, I.R.; Wright, M.N. The revival of the Gini importance? Bioinformatics 2018, 34, 3711–3718. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Cheng, L.; Chen, X.; De Vos, J.; Lai, X.; Witlox, F. Applying a random forest method approach to model travel mode choice behavior. Travel Behav. Soc. 2019, 14, 1–10. [Google Scholar] [CrossRef]
- Qiu, W.; Li, W.; Liu, X.; Huang, X. Subjectively Measured Streetscape Perceptions to Inform Urban Design Strategies for Shanghai. ISPRS Int. J. Geo-Inf. 2021, 10, 493. [Google Scholar] [CrossRef]
Class | Variable | Symbol | Data Source | Description |
---|---|---|---|---|
Response | Physical space vitality | PSV | Baidu | Fine-grained raster heat maps depicting timely crowd assembling. |
Cyberspace vitality | CSV | Sina Weibo | The Check_in number of Weibo posts can represent the popularity of the HPZs. | |
Sentiment degree | SENT | Sina Weibo | The content of Weibo texts containing the sentiment of people. | |
Feature_ morphological indicators | Average of building height | H_M | Baidu | It is acknowledged that urban morphology influences the popularity of HPZs in some way, based on Jacobs’ theory. Morphology related indicators are calculated in the Geographic Information System. |
Standard deviation of building height | H_SD | Baidu | ||
Building density | BD | Baidu | ||
Floor Area Ratio | FAR | Baidu | ||
Feature_ functional indicators | Number of hotels | P_H | Baidu | The distribution of functional facilities is important in evaluating the current use of HPZs, and they greatly affect the vitality. Baidu POI data were collected to build possible influencing factors. |
Number of places of entertainment | P_E | Baidu | ||
Number of tourist attractions | P_A | Baidu | ||
Number of stores and shopping malls | P_S | Baidu | ||
Number of infrastructures | P_I | Baidu | ||
Number of catering | P_C | Baidu | ||
Number of education facilities | P_EF | Baidu | ||
Feature_ traffic indicators | Walking accessibility | ACC | Baidu | Road traffic features may be related to regional vitality and population satisfaction. |
Street length | SL | Baidu | ||
Intersection density | ID | Baidu | ||
Feature_ visual indicators | Green Looking Ratio | R_GL | Baidu | The physical environment in the street will affect people’s visual perception and then affect vitality. These indicators were calculated using the Deeplab v3+ deep learning network to semantically segregate Baidu street view images. |
Sky View Ratio | R_SV | Baidu | ||
Road Ratio | R_R | Baidu | ||
Bicyclist Ratio | R_BI | Baidu | ||
Building Ratio | R_BU | Baidu | ||
Pavement Ratio | R_P | Baidu | ||
Sign Ratio | R_S | Baidu | ||
Car Ratio | R_C | Baidu | ||
Pedestrian Ratio | R_PE | Baidu |
HCAs | Sample Data of Weibo Content (in Chinese, Translated by Authors, Accessed on 19 June 2022) | Output Value | Sentiment Class |
---|---|---|---|
Shichahai | In the novel I like, the man and woman have a date in Shichahai, so there is a lot of romantic imagination. Although I didn’t see the uncle pulling the rickshaw in the story, the old man who told the story on the roadside is also very interesting. | 0.96 | Positive sample |
South Luogu Lane | Finally arrived in South Luogu Lane, Zhang’s Sichuan cuisine is affordable and delicious, and the hall is packed; the first bite of Wenyu cheese is amazing, but eating more will make you tired; the boy in the bar sings very well. | 0.98 | Positive sample |
Jingshan | Couldn’t find the way up the mountain. The people behind me accidentally ironed three holes in my new clothes when dropping his cigarette ashes. I was almost in tears, and I didn’t get a single apology. I went to Jingshan to see the sunset. It was a fine sunny day. But, in the afternoon, it suddenly began to rain. I’m so tired. | 0.05 | Negative sample |
Donghuamen Street | From Donghuamen to Beihai, the streets are full of motor vehicles that occupy the road illegally, resulting in a main road becoming a parking lot.There are many cars waiting for passengers. These private cars do not follow the rules to make money, causing congestion, so the road traffic in Beijing is getting more and more chaotic! How can road managers turn a blind eye to this? | 0.29 | Negative sample |
Xi Si | Where is the oldest hutong in Beijing? Many people who live in the east and west of the city will say “Brick Tower Hutong”. When you walk into this old hutong on Xisi South Street, you can clearly see the gates of each courtyard, and in each courtyard, you can hear the chatter and greetings of neighbors, attracting curious young people and foreign tourists. | 0.81 | Positive sample |
Morphological Indicators | Acronyms | Unit | Equation |
---|---|---|---|
Average of building height | m | ||
Standard deviation of building height | m | ||
Building density | % | ||
Floor area ratio |
MODEL_NAME | R2 | RMSE | MAE |
---|---|---|---|
1_physical space vitality (PSV) | 0.86 | 0.37 | 0.28 |
2_sentiment degree (SENT) | 0.85 | 0.43 | 0.21 |
3_cyber space vitality (CSV) | 0.76 | 0.49 | 0.36 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Huang, X.; Gong, P.; Wang, S.; White, M.; Zhang, B. Machine Learning Modeling of Vitality Characteristics in Historical Preservation Zones with Multi-Source Data. Buildings 2022, 12, 1978. https://doi.org/10.3390/buildings12111978
Huang X, Gong P, Wang S, White M, Zhang B. Machine Learning Modeling of Vitality Characteristics in Historical Preservation Zones with Multi-Source Data. Buildings. 2022; 12(11):1978. https://doi.org/10.3390/buildings12111978
Chicago/Turabian StyleHuang, Xiaoran, Pixin Gong, Siyan Wang, Marcus White, and Bo Zhang. 2022. "Machine Learning Modeling of Vitality Characteristics in Historical Preservation Zones with Multi-Source Data" Buildings 12, no. 11: 1978. https://doi.org/10.3390/buildings12111978