Dataset List

Vol.|Area

No.07 Vol.11,2024
No.06 Vol.11,2024
No.05 Vol.11,2024
No.04 Vol.11,2024
No.03 Vol.11,2024
No.02 Vol.11,2024
No.01 Vol.11,2024
No.12 Vol.10,2023
No.11 Vol.10,2023
No.10 Vol.10,2023
No.09 Vol.10,2023
No.08 Vol.10,2023
No.07 Vol.10,2023
No.06 Vol.10,2023
No.05 Vol.10,2023
No.04 Vol.10,2023
No.03 Vol.10,2023
No.02 Vol.10,2023
No.01 Vol.10,2023
No.12 Vol.9,2022
No.11 Vol.9,2022
No.10 Vol.9,2022
No.09 Vol.9,2022
No.08 Vol.9,2022
No.07 Vol.9,2022
No.06 Vol.9,2022
No.05 Vol.9,2022
No.04 Vol.9,2022
No.03 Vol.9,2022
No.02 Vol.9,2022
No.01 Vol.9,2022
No.12 Vol.8,2021
No.11 Vol.8,2021
No.10 Vol.8,2021
No.09 Vol.8,2021
No.08 Vol.8,2021
No.07 Vol.8,2021
No.06 Vol.8,2021
No.05 Vol.8,2021
No.04 Vol.8,2021
No.03 Vol.8,2021
No.03 Vol.8,2021
No.02 Vol.8,2021
No.01 Vol.8,2021
No.09 Vol.7,2020
No.08 Vol.7,2020
No.07 Vol.7,2020
No.06 Vol.7,2020
No.05 Vol.7,2020
No.04 Vol.7,2020
No.03 Vol.7,2020
No.02 Vol.7,2020
No.01 Vol.7,2020
No.06 Vol.6,2019
No.05 Vol.6,2019
No.04 Vol.6,2019
No.03 Vol.6,2019
No.02 Vol.6,2019
No.01 Vol.6,2019
No.08 Vol.5,2018
No.07 Vol.5,2018
No.06 Vol.5,2018
No.05 Vol.5,2018
No.04 Vol.5,2018
No.03 Vol.5,2018
No.02 Vol.5,2018
No.01 Vol.5,2018
No.04 Vol.4,2017
No.03 Vol.4,2017
No.02 Vol.4,2017
No.01 Vol.4,2017
No.09 Vol.3,2016
No.08 Vol.3,2016
No.07 Vol.3,2016
No.06 Vol.3,2016
No.05 Vol.3,2016
No.04 Vol.3,2016
No.03 Vol.3,2016
No.02 Vol.3,2016
No.01 Vol.3,2016
No.02 Vol.2,2015
No.01 Vol.2,2015
No.02 Vol.1,2014
No.01 Vol.1,2014
China
Asia
Oceanic region
African
European
North American
South American
Arctic
Global Scale
Data Details

Dataset of Nonlinear and Spatially Heterogeneous Relationship between Environmental Factors and Violent Crime in Beijing (2014-2019)


ZHANG Yanji1ZHU Chunwu2
1 School of Humanities and Social Sciences，Fuzhou University，Fuzhou 350108，China2 Department of Landscape Architecture and Urban Planning，Texas A & M University，College Station 77840，TX，USA

DOI:10.3974/geodb.2024.07.01.V1

Published:Jul. 2024

Visitors：140       Data Files Downloaded：8      
Data Downloaded：84.18 MB      Citations：

Key Words：

nonlinear relationship,spatial heterogeneity,Gradient Boosting Decision Tree,SHAP interpreter

Abstract：

Based on the information from Beijing Court, Baidu Map, NPP-VIIRS data, the authors used Gradient Boosting Decision Tree (GBDT) algorithm and SHapley Additive exPlanation (SHAP) interpreter with machine learning to systematically reveal the nonlinear and spatially heterogeneous relationships between 48 built and social environmental factors on violent crime. Finally, the dataset of nonlinear and spatially heterogeneous relationship between environmental factors and violent crime in Beijing (2014-2019) was obtained. The dataset includes: (1) boundary of the study area; (2) The relationship between various environmental factors and violent crime count; (3) robust regression analysis results of the impact of environmental factors on violent crime; (4) cluster data of the factors contributing to violent crime. The dataset is archived in .xlsx and .shp formats, and consists of 16 data files with data size of 12.2 MB (compressed into one file with 10.5 MB). The research paper based on the dataset will be published at Acta Geographica Sinica, Vol. 79, 2024.

Foundation Item：

National Social Science Foundation of China (21CSH006)

Data Citation：

ZHANG Yanji, ZHU Chunwu. Dataset of Nonlinear and Spatially Heterogeneous Relationship between Environmental Factors and Violent Crime in Beijing (2014-2019)[J/DB/OL]. Digital Journal of Global Change Data Repository, 2024. https://doi.org/10.3974/geodb.2024.07.01.V1.

References：


     [1] Chen, J., Liu, L., Xiao, L., et al. Integrative analysis of spatial heterogeneity and over dispersion of crime with a geographically weighted negative binomial model [J]. International Journal of Geo-Information, 2020, 9(1): 60.
     [2] Wheeler, D. C., Waller, L. A. Comparing spatially varying coefficient models: A case study examining violent crime rates and their relationships to alcohol outlets and illegal drug arrests [J]. Journal of Geographical Systems, 2009, 11(1): 1-22.
     [3] Zhang, X., Liu, L., Lan, M., et al. Interpretable machine learning models for crime prediction [J]. Computers, Environment and Urban Systems, 2022, 94: 101789.
     [4] Xie, H., Liu, L., Yue, H. Modeling the effect of streetscape environment on crime using street view images and interpretable machine-learning technique [J]. International Journal of Environmental Research and Public Health, 2022, 19(21): 13833.
     [5] Chen, Q. Machine Learning and Python Applications [M]. Beijing: Higher Education Press, 2021.
     [6] Carvalho, D. V., Pereira, E. M., Cardoso, J. S. Machine learning interpretability: A survey on methods and metrics [J]. Electronics, 2019, 8(8): 832.
     [7] Rummens, A., Hardyns, W., Pauwels, L. The use of predictive analysis in spatiotemporal crime forecasting: Building and testing a model in an urban context [J]. Applied Geography, 2017, 86: 255-261.
     [8] Liu, L., Liu, W. J., Liao, W. W., et al. Comparison of random forest algorithm and space-time kernel density mapping for crime hotspot prediction [J]. Progress in Geography, 2018, 37(6): 761-771.
     [9] Lundberg, S. M., Erion, G. G., Lee, S. I. Consistent individualized feature attribution for tree ensembles [J]. arXiv, 2018: 1802.03888. DOI: 10.48550/arXiv.1802.03888.
     [10] https://www.bjcourt.gov.cn.
     [11] https://eogdata.mines.edu/products/vnl/.
     [12] https://ditu.baidu.com/.
     

Data Product:

ID Data Name Data Size Operation
1 Environ&CrimesBJ.rar 10774.76KB
Co-Sponsors
Superintend