Mask System for Standardizing Workflow of Population Density Random Forest Model with Shijiazhuang Data Validating
WEN Peizhang1SU Zhaowen1LIU Jinsong*1,2YAO Haifang3LI Lingling1
1 School of Geographical Sciences，Hebei Normal University，Shijiazhuang 050024，China2 Hebei Technology Innovation Center for Remote Sensing Identification of Environmental Change，Hebei Key Laboratory of Environmental Change and Ecological Construction，Geographic Experiment Teaching Demonstration Center of Hebei Province，Shijiazhuang 050024，China3 College of Home Economics，Hebei Normal University，Shijiazhuang 050024，China
DOI:10.3974/geodb.2025.05.08.V1
Published:May 2025
Visitors：120 Data Files Downloaded：3
Data Downloaded：3.78 MB Citations：
Key Words：
mask,population density,random forest model,Shijiazhuang
Abstract：
The mask serves as an auxiliary technique for constructing the population density random forest model. The authors took Shijiazhuang City, Hebei Province as the case study area and developed a comprehensive mask system. This dataset was created based on fundamental geographic parameters (left-bottom coordinates, projection, etc.) of Shijiazhuang’s 2020 administrative boundary data. Using the Create Fishnet tool in ArcGIS 10.2, a hectare vector grid (100 m×100 m grid) covering the entire area of Shijiazhuang was constructed. Building upon the administrative boundary and hectare grid data, all categories of masks were sequentially generated through spatial operations including select by location, polygon to raster, and random sampling. The dataset includes control masks (including research area mask, zonal mask, calculative mask, zonal calculative mask, and total sampling frame mask), sampling-related masks (including zonal sampling frame mask and zonal sampling mask), dasymetric mapping masks (including county masks, township masks), and testing masks (including reliability testing mask, validity testing mask, and boundary testing mask). The dataset has a 100 m spatial resolution, archived in GeoTIFF format (.tif). It consists of 67 data files with data size of 39 MB (compressed into 1 file with 1.25 MB). The research paper based on the dataset was published in Acta Geographica Sinica, Vol. 80, No. 6, 2025.
Foundation Item：
National Natural Science Foundation of China (42071167, 40871073); Ministry of Science and Technology of P. R. China (2019QZKK0406); Natural Science Foundation of Hebei Province (D2007000272); Hebei Normal University (L2024ZD07)
Data Citation：
WEN Peizhang, SU Zhaowen, LIU Jinsong*, YAO Haifang, LI Lingling. Mask System for Standardizing Workflow of Population Density Random Forest Model with Shijiazhuang Data Validating[J/DB/OL]. Digital Journal of Global Change Data Repository, 2025. https://doi.org/10.3974/geodb.2025.05.08.V1.
References：
[1] Leyk, S., Gaughan, A. E., Adamo, S. B., et al. The spatial allocation of population: a review of large-scale gridded population data products and their fitness for use [J]. Earth System Science Data, 2019, 11(3): 1385-1409.
[2] Wardrop, N. A., Jochem, W. C., Bird, T. J., et al. Spatially disaggregated population estimates in the absence of national population and housing census data [J]. PNAS, 2018, 115(14): 3529-3537.
[3] Liu, Y., Yang, X. J., Liu, J. S. Experimental study on optimization of population density models based on random forest [J]. Journal of Global Change Data & Discovery, 2020, 4(4): 402-416.
[4] Feng, X. T. Social Research Methods. 5th ed. [M]. Beijing: China Renmin University Press, 2018: 75-76.
[5] Li, L. L., Liu, J. S., Li, Z., et al. Experimental study of population density using an optimized random forest model [J]. Acta Geographica Sinica, 2023, 78(5): 1304-1320.
[6] Li, L. L., Liu, J. S., Li, Z., et al. Experimental study of population density using an optimized random forest model [J]. Journal of Geographical Sciences, 2024, 34(8): 1636-1656.
[7] Shen, H. F., Zhong, Y. F., Wang, Y., et al. ENVI Remote Sensing Image Processing Method [M]. Wuhan: Wuhan University Press, 2009: 165-170.
[8] Liu, J. S. The geographical meaning about the modifiable areal unit problem in the population density scaling [D]. Shijiazhuang: Hebei Normal University, 2009.
[9] Zheng, D., Ou, Y., Zhou, C. H. Understanding of and thinking over geographical regionalization methodology [J]. Acta Geographica Sinica, 2008, 63(6): 563-573.
[10] Wen, P. Z., Su, Z. W., Liu, J. S., et al. Mask system for standardizing the modeling workflow of the population density random forest model [J]. Acta Geographica Sinica, 2025, 80(6): 1556-1571.
Data Product:
| ID |
Data Name |
Data Size |
Operation |
| 1 |
SJZ_Masksystem_2020.rar |
1290.33KB |
|