Site Selection of Elderly Care Facilities Based on Multi-Source Spatial Big Data and Integrated Learning
This study explores a method to improve the site selection for elderly care facilities in an aging region, using Hefei City, China, as the study area. It combines topographic conditions, population distribution, economic development status, and other multi-source spatial big data at a 500 m grid sca...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/13/12/451 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850049254308970496 |
|---|---|
| author | Yin Zhang Junhong Zhu Fangyi Li Yingjie Wang |
| author_facet | Yin Zhang Junhong Zhu Fangyi Li Yingjie Wang |
| author_sort | Yin Zhang |
| collection | DOAJ |
| description | This study explores a method to improve the site selection for elderly care facilities in an aging region, using Hefei City, China, as the study area. It combines topographic conditions, population distribution, economic development status, and other multi-source spatial big data at a 500 m grid scale; constructs a prediction model for the suitability of sites for elderly care facilities based on integrated learning; and carries out a comprehensive evaluation and feature importance analysis. Finally, it uses trained random forest (RF) and gradient boosting decision tree (GBDT) models to predict preliminary site selection results for elderly care facilities. A second screening that compares three degrees of population aging is conducted to obtain the final site selection results. The results show the following: (1) The comprehensive evaluation indexes of the two integrated learning models, RF and GBDT, are above or below 80% as needed, which is better than the four single learning models. (2) The prediction results of the RF and GBDT models have 87.9% and 78.4% fit to existing elderly facilities, respectively, which indicates that the methods are reasonable and reliable. (3) The results of both the RF and GBDT models indicate that the closest distance to healthcare facilities and the size of the population distribution are the two most important factors affecting the location of elderly care facilities. (4) The results of the preliminary site selection show an overall spatial distribution of higher suitability in the main urban area and lower suitability in the suburban counties. The secondary screening finds that priority needs to be given to the periphery of the main urban area and to Lujiang County and other surrounding townships that have a more serious degree of aging as soon as possible in the site selection of new elderly care facilities. |
| format | Article |
| id | doaj-art-552dd9e1b61340a89e39f2d8fcdc6b0f |
| institution | DOAJ |
| issn | 2220-9964 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj-art-552dd9e1b61340a89e39f2d8fcdc6b0f2025-08-20T02:53:44ZengMDPI AGISPRS International Journal of Geo-Information2220-99642024-12-01131245110.3390/ijgi13120451Site Selection of Elderly Care Facilities Based on Multi-Source Spatial Big Data and Integrated LearningYin Zhang0Junhong Zhu1Fangyi Li2Yingjie Wang3School of Management, Hefei University of Technology, Hefei 230009, ChinaSchool of Management, Hefei University of Technology, Hefei 230009, ChinaSchool of Management, Hefei University of Technology, Hefei 230009, ChinaSchool of Management, Hefei University of Technology, Hefei 230009, ChinaThis study explores a method to improve the site selection for elderly care facilities in an aging region, using Hefei City, China, as the study area. It combines topographic conditions, population distribution, economic development status, and other multi-source spatial big data at a 500 m grid scale; constructs a prediction model for the suitability of sites for elderly care facilities based on integrated learning; and carries out a comprehensive evaluation and feature importance analysis. Finally, it uses trained random forest (RF) and gradient boosting decision tree (GBDT) models to predict preliminary site selection results for elderly care facilities. A second screening that compares three degrees of population aging is conducted to obtain the final site selection results. The results show the following: (1) The comprehensive evaluation indexes of the two integrated learning models, RF and GBDT, are above or below 80% as needed, which is better than the four single learning models. (2) The prediction results of the RF and GBDT models have 87.9% and 78.4% fit to existing elderly facilities, respectively, which indicates that the methods are reasonable and reliable. (3) The results of both the RF and GBDT models indicate that the closest distance to healthcare facilities and the size of the population distribution are the two most important factors affecting the location of elderly care facilities. (4) The results of the preliminary site selection show an overall spatial distribution of higher suitability in the main urban area and lower suitability in the suburban counties. The secondary screening finds that priority needs to be given to the periphery of the main urban area and to Lujiang County and other surrounding townships that have a more serious degree of aging as soon as possible in the site selection of new elderly care facilities.https://www.mdpi.com/2220-9964/13/12/451population agingmulti-source spatial big dataintegrated learningelderly care facilitiessite selectionHefei City |
| spellingShingle | Yin Zhang Junhong Zhu Fangyi Li Yingjie Wang Site Selection of Elderly Care Facilities Based on Multi-Source Spatial Big Data and Integrated Learning ISPRS International Journal of Geo-Information population aging multi-source spatial big data integrated learning elderly care facilities site selection Hefei City |
| title | Site Selection of Elderly Care Facilities Based on Multi-Source Spatial Big Data and Integrated Learning |
| title_full | Site Selection of Elderly Care Facilities Based on Multi-Source Spatial Big Data and Integrated Learning |
| title_fullStr | Site Selection of Elderly Care Facilities Based on Multi-Source Spatial Big Data and Integrated Learning |
| title_full_unstemmed | Site Selection of Elderly Care Facilities Based on Multi-Source Spatial Big Data and Integrated Learning |
| title_short | Site Selection of Elderly Care Facilities Based on Multi-Source Spatial Big Data and Integrated Learning |
| title_sort | site selection of elderly care facilities based on multi source spatial big data and integrated learning |
| topic | population aging multi-source spatial big data integrated learning elderly care facilities site selection Hefei City |
| url | https://www.mdpi.com/2220-9964/13/12/451 |
| work_keys_str_mv | AT yinzhang siteselectionofelderlycarefacilitiesbasedonmultisourcespatialbigdataandintegratedlearning AT junhongzhu siteselectionofelderlycarefacilitiesbasedonmultisourcespatialbigdataandintegratedlearning AT fangyili siteselectionofelderlycarefacilitiesbasedonmultisourcespatialbigdataandintegratedlearning AT yingjiewang siteselectionofelderlycarefacilitiesbasedonmultisourcespatialbigdataandintegratedlearning |