EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Park Development, Potential Measurement, and Site Selection Study Based on Interpretable Machine Learning—A Case Study of Shenzhen City, China

Haihong Li, Li He

ISPRS International Journal of Geo-Information · 24.04.2025 · 14 (5) · 184

DOI: 10.3390/ijgi14050184 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 24.04.2025. Verfasst von Haihong Li und 1 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hubei Province: Study on Simulation Forecasting and Application of Expansion Mode of Mono-city Cluster Based on Spatial Interacti…, Jingzhou Think Tank Project: Study on Rural Revitalisation Planning Strategies for Jingzhou Suburban Integration Villages in the Context of Co-Creation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scientific site selection for urban parks is an important way to increase urban resilience and safeguard people’s well-being. Aiming at the lack of systematic consideration in the traditional park siting research, this study utilizes geographically weighted regression to explore the various characteristic factors affecting the spatial distribution of parks, and based on this, combines the random forest model and the interpretable model to accurately assess the potential of parks on urban land in Shenzhen and provide the basis for site selection. The study indicates that: ① Shenzhen’s parks exhibit complex differentiation characteristics in terms of natural landscape elements and the intensity of economic activities; ② The geographically weighted random forest (GWRF) model has better learning and generalization capabilities compared to the random forest (RF) model, and the average accuracy of the GWRF model is improved by 0.04 compared to the traditional RF model; ③ The park’s development potential is divided according to the results of the GWRF model, with 52.01% denoted as the potential incubation zone, 21.15% the potential accumulation zone, 8.25% the potential growth zone, and 18.59% the potential core zone; ④ Through interpretability analysis, it is identified that vegetation coverage, the density of tourist attractions or points of interest (POI), slope, elevation, and nighttime light intensity are the most significant factors affecting park development potential, while the distance to roads and the distance to bodies of water are the least influential factors. The research systematically explores a quantitative evaluation framework for the development potential of Shenzhen’s parks, opening new theoretical pathways and practical paradigms for the sustainable development planning of Shenzhen under the “Park City” concept.

Förderung

  • Natural Science Foundation of Hubei Province: Study on Simulation Forecasting and Application of Expansion Mode of Mono-city Cluster Based on Spatial Interacti…
  • Jingzhou Think Tank Project: Study on Rural Revitalisation Planning Strategies for Jingzhou Suburban Integration Villages in the Context of Co-Creation

Zitieren

APA

Li, H., & He, L. (2025). Park Development, Potential Measurement, and Site Selection Study Based on Interpretable Machine Learning—A Case Study of Shenzhen City, China. ISPRS International Journal of Geo-Information, 14(5), 184. https://doi.org/10.3390/ijgi14050184

Vancouver

Li H, He L. Park Development, Potential Measurement, and Site Selection Study Based on Interpretable Machine Learning—A Case Study of Shenzhen City, China. ISPRS International Journal of Geo-Information. 2025;14(5):184. doi:10.3390/ijgi14050184

BibTeX
@article{Li2025,
  author = {Li, Haihong and He, Li},
  title = {Park Development, Potential Measurement, and Site Selection Study Based on Interpretable Machine Learning—A Case Study of Shenzhen City, China},
  journal = {ISPRS International Journal of Geo-Information},
  year = {2025},
  volume = {14},
  number = {5},
  pages = {184},
  doi = {10.3390/ijgi14050184}
}
Kostenlos starten →