Detection of County Economic Development Using LJ1-01 Nighttime Light Imagery: A Comparison with NPP-VIIRS Data
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Area
2.2. Data and Data Preprocessing
2.2.1. NPP-VIIRS Data
2.2.2. LJ1-01 Data
2.2.3. Standardization of Socioeconomic Parameters
2.3. Calculation of the County-Level Economic Index
- (1)
- Calculation of the AHP weight. The AHP decomposes the problem into different factors and combines them into different levels according to their mutual influence to form a multilevel analysis structure model; the relative importance of the lowest level relative to the highest level is determined according to the model. The main steps of the AHP are as follows:
- (a)
- Construction of the judgment matrix A of the AHP.The element aij of the judgment matrix A represents the importance of the i index relative to the j index, which is given by Santy’s 1–9 scale method [42], in which 1 indicates that the two indices are equally important, 3 indicates that the i–th index is more important than the j-th index and 9 indicates that the i-th index is significantly more important than the j-th index. The larger the number, the more important the i-th index is relative to the j-th index. By using the same scale to subjectively compare the indices with each other, the difficulty of the scoring caused by the different properties or other factors can be reduced to a larger extent, so as to improve the accuracy of the judgment.
- (b)
- Single-layer weight determination. The normalized eigenvector of matrix A is used as the weight vector W. wi is normalized to obtain the single-level weight of the indicator.
- (c)
- Consistency verification. Since the construction of the judgment matrix comes from subjective scoring, in order to avoid logical contradictions, it is necessary to verify the consistency of the judgment matrix. The AHP uses the CI as the consistency verification index and the CR as the consistency ratio. The calculation method is shown in Formulas (10) and (11), where λ is the largest eigenvalue of the matrix and RI represents the randomness index. The relationship between the RI and the order of judgment matrix is shown in Table 3. Generally, when the consistency ratio CR < 0.1, it is considered that the inconsistency of A is within the allowable range and that the consistency is verified.
- (d)
- AHP weight determination. The final weight of each index can be calculated by multiplying the second-level index weight by the corresponding first-level index weight obtained in Step (b).
- (2)
- Entropy weight calculation. The entropy is used to calculate the coefficient of variation for each index, which determines the indicator weight and obtains an objective comprehensive evaluation result. The main steps of the entropy-weight method are as follows:
- (e)
- Indicator assimilation.
- (f)
- Calculation of the entropy ei of each indicator.
- (g)
- Calculation of the coefficient of variation of each indicator gi.
- (h)
- Calculation of the weight of each indicator.
- (3)
- Calculation of the Entropy-AHP weight. Using Wentropy to modify WAHP, the result is normalized to obtain the final Wi.
- (4)
- Construction of the CEI of the study area. According to the Entropy-AHP weights and the dimensionless data in Section 2.2, linear weighting is used to sum these data. The CEI of each county in the study area is finally obtained according to Formula (19).
2.4. RF Regression Models
2.5. Spatial Analysis of the CEI
- (1)
- Moran’s I. Moran’s I is used to measure global spatial autocorrelation. It is a weighted correlation coefficient used to detect departures from spatial randomness, which can indicate spatial patterns. The calculation method is shown in Formula (22) [48], where xi and xj are the values at spatial point i and j, respectively; is the average value of all the points in the entire region; wij is the weight of the spatial neighborhood relationship; and n is the total number of all spatial statistical units in the study area. The range of Moran’s I is [–1,1]. A positive value means that the object is positively correlated in space, while a negative value means that it is negatively correlated. The statistical significance of Moran’s I can be evaluated by the Z-score after standard normalization.
- (2)
- LISA. Moran’s I can only measure the spatial correlation of the entire region; it cannot reflect the spatial clustering of each partition in the case of spatial heterogeneity. In 1995, American regional economist Anselin proposed the LISA (local indicators of spatial association) statistic to evaluate the existence of clusters in the spatial arrangement of a given variable [49]. This statistic detects local spatial association and can be used to identify local clusters (i.e., regions where adjacent areas have similar values) or spatial outliers (i.e., areas distinct from their neighbors). The calculation of the LISA statistics is shown in Formula (23), where xi, xj, and wij have the same meaning as in (22). LISA statistics decompose Moran’s I into contributions for each location. The sum of Ii for all observations is proportional to Moran’s I.
3. Results
3.1. Mapping of the CEI in the Study Area
3.2. Model Results and Accuracy
3.3. Spatial Analysis of the CEI
4. Discussion
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
Appendix A
Notation | Explanation |
---|---|
DN | The light radiation value |
i,j | The i-th or j-th index |
A | The judgment matrix of AHP |
aij | Scalar, representing matrix elements |
W | The weight vector |
CI | The consistency verification index in AHP |
CR | The consistency ratio in AHP |
RI | The randomness index in AHP |
Pij | The dimensionless value |
ei | The entropy value |
gi | The coefficient of variation |
Xi | Scalar, representing the corresponding index value |
xi | Scalar, representing the corresponding value at spatial point i |
Scalar, representing the corresponding average value | |
R2 | The determinate coefficients |
MAE | The mean absolute error |
I | The value of Moran’s I |
Ii | The value of LISA statistic |
Data Type | Data Name | Data Source | Instruction |
---|---|---|---|
Nighttime Light Data | NPP-VIIRS NTL data | The Observation Group, Payne Institute for Public Policy (https://eogdata.mines.edu/download_dnb_composites.html) | 48 phases of monthly composite data from 2015 to 2018 and 2 phases of annual NTL data from 2015 to 2016. The data needs to eliminate background noise. |
LJ1-01 NTL data | High-Resolution Earth Observation System of the Hubei Data and Application Center (http://www.hbeos.org.cn/) | The Chinese 2018 synthetic LJ1-01 NTL data have been adjusted based on ground control points. The data needs absolute radiation correction. | |
Socioeconomic Statistical Data | The Statistical Yearbook of 2019 | The provincial statistical bureaus (http://tjj.hubei.gov.cn/, http://tjj.hunan.gov.cn/, http://tjj.jiangxi.gov.cn/) | 15 socioeconomic parameters such as county GDP, County fiscal revenue, Per capita disposable income, Urbanization rates, etc., were selected from the four perspectives of economic conditions, people’s livelihood, social development and public resources. |
The 2018 National Economic And Social Development Statistical Bulletins published by each county | |||
Basic Geographic Information Data | The administrative boundary | The Resource And Environment Data Cloud Platform of the Chinese Academy of Sciences (http://www.resdc.cn/Default.aspx) | All the basic geographic data were re-projected to the Albers equal-area projection coordinate system and resampled at 1000 m × 1000 m. |
DEM | |||
Farmland production potential data | |||
Monthly average precipitation data | The National Earth System Science Data Center, National Science and Technology Infrastructure of China (http://www.geodata.cn) | ||
Monthly average temperature data |
References
- Hölker, F.; Wolter, C.; Perkin, E.K.; Tockner, K. Light pollution as a biodiversity threat. Trends Ecol. Evol. 2010, 25, 681–682. [Google Scholar] [CrossRef] [PubMed]
- Green, J.; Perkins, C.; Steinbach, R.; Edwards, P. Reduced street lighting at night and health: A rapid appraisal of public views in England and Wales. Health Place 2015, 34, 171–180. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Li, X.; Xu, H.M. Potential of NPP/VIIRS nighttime light imagery for modeling the regional economy of China. Remote Sens. 2013, 5, 3057–3081. [Google Scholar] [CrossRef] [Green Version]
- Doll, C.N.H.; Muller, J.P.; Morley, J.G. Mapping regional economic activity from night-time light satellite imagery. Ecol. Econ. 2006, 57, 75–92. [Google Scholar] [CrossRef]
- Elvidge, C.D.; Baugh, K.E.; Kihn, E.A.; Kroehl, H.W.; Davis, E.R.; Davis, C.W. Relation between satellite observed visible-near infrared emissions, population, economic activity and electric electricity consumption. Int. J. Remote Sens. 1997, 18, 1373–1379. [Google Scholar] [CrossRef]
- Ou, J.; Liu, X.; Liu, P.; Liu, X.; Liu, X. Evaluation of Luojia 1-01 nighttime light imagery for impervious surface detection: A comparison with NPP-VIIRS nighttime light data. Int. J. Appl. Earth Obs. Geoinf. 2019, 81, 1–12. [Google Scholar] [CrossRef]
- Elvidge, C.D.; Baugh, K.E.; Zhizhin, M.; Hsu, F.C. Why VIIRS data are superior to DMSP for mapping nighttime lights. Proc. Asia Pac. Adv. Netw. 2013, 35. [Google Scholar] [CrossRef] [Green Version]
- Shi, K.; Yu, B.; Huang, Y.; Hu, Y.; Yin, B.; Chen, Z.; Chen, L.; Wu, J. Evaluating the ability of NPP-VIIRS nighttime light data to estimate the gross domestic product and the electric power consumption of china at multiple scales: A comparison with DMSPOLS data. Remote Sens. 2014, 6, 1705–1724. [Google Scholar] [CrossRef] [Green Version]
- Zhang, Q.; Wang, P.; Chen, H.; Huang, Q.; Jiang, H.; Zhang, Z.; Zhang, Y.; Luo, X.; Sun, S. A novel method for urban area extraction from VIIRS DNB and MODIS NDVI data: A case study of Chinese cities. Int. J. Remote Sens. 2017, 38, 6094–6109. [Google Scholar] [CrossRef]
- Yu, B.; Tang, M.; Wu, Q.; Yang, C.; Deng, S.; Shi, K.; Peng, C.; Wu, J.; Chen, Z. Urban built-up area extraction from log-transformed NPP-VIIRS nighttime light composite data. IEEE Geosci. Remote Sens. 2018, 15, 1279–1283. [Google Scholar] [CrossRef]
- Wei, J.; He, G.; Liu, H. Modelling regional socio-economic parameters based on comparison of NPP/VIIRS and DMSP/OLS nighttime light imagery. Remote Sens. Inf. 2016, 4, 28–34. [Google Scholar]
- Jiang, W.; He, G.; Long, T.; Guo, H.; Yin, R.; Leng, W.; Liu, H.; Wang, G. Potentiality of using Luojia 1-01 nighttime light imagery to investigate artificial light pollution. Sensors 2018, 18, 2900. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Li, X.; Zhao, L.; Li, D.; Xu, H. Mapping urban extent using Luojia 1-01 nighttime light imagery. Sensors 2018, 18, 3665. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Zhang, G.; Wang, J.; Jiang, Y.; Zhou, P.; Zhao, Y.; Xu, Y. On-orbit geometric calibration and validation of luojia 1-01 night-light satellite. Remote Sens. 2019, 11, 264. [Google Scholar] [CrossRef] [Green Version]
- Li, X.; Li, X.; Li, D.; He, X.; Jendryke, M. A preliminary investigation of Luojia-1 night-time light imagery. Remote Sens. Lett. 2019, 10, 526–535. [Google Scholar] [CrossRef]
- Zhang, G.; Guo, X.; Li, D.; Jiang, B. Evaluating the Potential of LJ1-01 Nighttime Light Data for Modeling Socio-Economic Parameters. Sensors 2019, 19, 1465. [Google Scholar] [CrossRef] [Green Version]
- Gao, Y.H.; Wang, M.C. Analysis of county economic divergence and spatial-character of provincial border-regions: The case of ganzhou city. Econ. Geogr. 2011, 31, 736–740. [Google Scholar]
- Shao, L.C.; Qiao, J.J.; Wang, Y.X. County economic space structure and evolution characteristics in Henan Province. Areal Res. Dev. 2016, 35, 64–69. [Google Scholar]
- Zhong, Y.; Lu, Y. County-level economic disparities in the red-triangle economic zone. Econ. Geogr. 2010, 30, 568–573. [Google Scholar]
- Liao, Y.; Zhou, F.M.; Tang, Y.F. The empirical study on the change of County Economy Disparity in Hunan. Econ. Geogr. 2014, 34, 35–41. [Google Scholar]
- Yu, B.; Shi, K.; Hu, Y.; Huang, C.; Chen, Z.; Wu, J. Poverty evaluation using NPP-VIIRS nighttime light composite data at the county level in China. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017, 8, 1217–1229. [Google Scholar] [CrossRef]
- Zhao, M.; Cheng, W.; Zhou, C.; Li, M.; Wang, N.; Liu, Q. GDP spatialization and economic differences in south china based on NPP-VIIRS nighttime light imagery. Remote Sens. 2017, 9, 673. [Google Scholar] [CrossRef] [Green Version]
- Li, C.; Yang, W.; Tang, Q. Detection of Multidimensional Poverty Using Luojia 1-01 Nighttime Light Imagery. J. Indian Soc. Remote Sens. 2020. [Google Scholar] [CrossRef]
- Xu, Y.; Knudby, A.; Ho, H.C. Estimating daily maximum air temperature from MODIS in British Columbia, Canada. Int. J. Remote Sens. 2014, 35, 8108–8121. [Google Scholar] [CrossRef]
- Abdel-Rahman, E.; Ahmed, F.; Ismail, R. Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO-1 hyperion hyperspectral data. Int. J. Remote Sens. 2013, 34, 712–728. [Google Scholar] [CrossRef]
- Tramontana, G.; Ichii, K.; Camps-Valls, G.; Tomelleri, E.; Papale, D. Uncertainty analysis of gross primary production upscaling using random forests, remote sensing and eddy covariance data. Remote Sens. Environ. 2015, 168, 360–373. [Google Scholar] [CrossRef]
- Xu, Y.; Knudby, A.; Coˆte’-Lussier, C. Mapping ambient light at night using field observations and high-resolution remote sensing imagery for studies of urban environments. Build. Environ. 2018, 145, 104–114. [Google Scholar] [CrossRef]
- Armitage, D.; Ober, H.K. A comparison of supervised learning techniques in the classification of bat echolocation calls. Ecol. Inform. 2010, 5, 465–473. [Google Scholar] [CrossRef]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Green Version]
- Ismail, R.; Mutanga, O. A comparison of regression tree ensembles: Predicting sirex noctilio induced water stress in Pinus patula Forests of Kwazulu-Natal, South Africa. Int. J. Appl. Earth Obs. 2010, 12, S45–S51. [Google Scholar] [CrossRef]
- Chen, Z.; Yu, B.; Ta, N.; Shi, K.; Yang, C.; Wang, C.; Zhao, X.; Deng, S.; Wu, J. Delineating seasonal relationships between Suomi NPP-VIIRS nighttime light and human activity across Shanghai, China. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019, 1–9. [Google Scholar] [CrossRef]
- Ye, T.; Zhao, N.; Yang, X.; Ouyang, Z.; Liu, X.; Chen, Q.; Hu, K.; Yue, W.; Qi, J.; Li, Z. Improved population mapping for China using remotely sensed and points-of-interest data within a random forests model. Sci. Total Environ. 2019, 658, 936–946. [Google Scholar] [CrossRef] [PubMed]
- Li, X.; Wang, T.; Zhang, G.; Jiang, B.; Jia, P.; Zhang, Z.; Zhao, Y. Planar Block Adjustment for China’s Land Regions with LuoJia1-01 Nighttime Light Imagery. Remote Sens. 2019, 11, 2097. [Google Scholar] [CrossRef] [Green Version]
- De Miguel, A.S.; Kyba, C.C.M.; Zamorano, J.; Gallego, J.; Gaston, K.J. The nature of the diffuse light near cities detected in nighttime satellite imagery. Sci. Rep. 2020, 10, 7829. [Google Scholar] [CrossRef] [PubMed]
- Chen, Z.; Yu, B.; Hu, Y. Estimating house vacancy rate in metropolitan areas using NPP-VIIRS nighttime light composite data. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 2015, 8, 2188–2197. [Google Scholar] [CrossRef]
- Hu, W.; Liu, C.; Zhan, Q. Synthetic method and comparison verification of NPP-VIIRS annual nighttime lighting data in China. J. Guilin. Univ. Technol. 2020, 1–10. [Google Scholar]
- Zhou, Y.; Chen, Y.; Liu, Y. Generation and verfication of NPP-VIIRS annual nighttime light data. Remote Sens. Inf. 2019, 34, 62–68. [Google Scholar]
- Elvidge, C.D.; Cinzano, P.; Pettit, D.R.; Arvesen, J.; Sutton, P.; Small, C. Overview of the Nightsat mission concept. In Proceedings of the 2007 Urban Remote Sensing Joint Event, Paris, France, 11–13 April 2007; pp. 1–5. [Google Scholar] [CrossRef]
- Su, Z.Q.; Zhong, X.; Zhang, G.; Li, Y.J.; He, X.J.; Wang, Q.; Wei, Z.; He, C.L.; Li, D.R. High sensitive night-time light imaging camera design and in-orbit test of Luojia1-01 satellite. Sensors 2019, 19, 797. [Google Scholar] [CrossRef] [Green Version]
- Du, T.; Xie, X.J.; Liang, H.M. County Economy Comprehensive Evaluation and Spatial Analysis in Chongqing City Based on Entropy Weight-TOPSIS and GIS. Econ. Geogr. 2014, 34, 40–47. [Google Scholar]
- Liu, Y.; Pan, Y.C.; Chen, Y.F. The Temporal and Spatial Change of Economic Development at County Level in Shandong Province. Econ. Geogr. 2012, 32, 43–48. [Google Scholar]
- Saaty, T.L. A scaling method for priorities on hierarchical structures. J. Math. Psychol. 1977, 15, 234–281. [Google Scholar] [CrossRef]
- Li, G.; Cai, Z.; Liu, X.; Liu, J.; Su, S. A comparison of machine learning approaches for identifying high-poverty counties: Robust features of DMSP/OLS night-time light imagery. Int. J. Remote. Sens. 2019, 40, 5716–5736. [Google Scholar] [CrossRef]
- Ham, J.; Chen, Y.; Crawford, M.M.; Ghosh, J. Investigation of the random forest framework for classification of hyperspectral data. IEEE Trans. Geosci. Remote Sens. 2005, 43, 492–501. [Google Scholar] [CrossRef] [Green Version]
- Tobler, W. A computer movie simulating urban growth in the Detroit region. Econ. Geogr. 1970, 46, 234–240. [Google Scholar] [CrossRef]
- Michael, F. Goodchild. The Application of Advanced Information Technology in Assessing Environmental Impacts; Soil Society of America: Madison, WI, USA, 1996. [Google Scholar] [CrossRef]
- Corwin, D.L.; Loague, K. Application of GIS to the Modeling of Non-point Source Pollutants in the Vadose Zone. Soil. Sci. Soc. Am. J. 1996, 25, 403–411. [Google Scholar]
- Haining, R.P. Spatial Data Analysis: Theory and Practice; Cambridge University Press: Cambridge, UK, 2003. [Google Scholar] [CrossRef]
- Anselin, L. Local indicators of spatial association-lisa. Geogr. Anal. 1995, 27, 93–115. [Google Scholar] [CrossRef]
- Walton, J.T. Subpixel urban land cover estimation: Comparing cubist, random forests and support vector regression. Photogramm. Eng. Remote Sens. 2008, 74, 1213–1222. [Google Scholar] [CrossRef] [Green Version]
- Bennett, M.M.; Smith, L.C. Advances in using multitemporal night-time lights satellite imagery to detect, estimate, and monitor socioeconomic dynamics. Remote Sens. Environ. 2017, 192, 176–197. [Google Scholar] [CrossRef]
- Elvidge, C.D.; Tuttle, B.T.; Sutton, P.S.; Baugh, K.E.; Howard, A.T.; Milesi, C.; Bhaduri, B.L.; Nemani, R. Global distribution and density of constructed impervious surfaces. Sensors 2007, 7, 1962–1979. [Google Scholar] [CrossRef]
DMSP-OLS | NPP-VIIRS | LJ1-01 | |
---|---|---|---|
Time Span | 1992–2013 | November 2011–present | June 2018–March 2019 |
Swath | ~3000 km | ~3000 km | ~250 km |
Spectrum | 0.5–0.9 μm | 0.5–0.9 μm | 0.46–0.98 μm |
Quantization | 6 bits | 14 bits | 14 bits |
Spatial Resolution | 2700 m | 750 m | 130 m |
Calibration | N/A | On-board Calibration | On-board Calibration |
Saturation | Saturated | Not Saturated | Not Saturated |
Dimension | Indicator | Attribute | Weight | Interpretation of the Indicator |
---|---|---|---|---|
Economic Conditions | County GDP | + | 0.2494 | Reflects the overall state of economic development in the county |
Proportion of secondary industry | + | 0.0062 | Percentage of the secondary industry in GDP | |
Proportion of tertiary industries | + | 0.0075 | Percentage of the tertiary industry in GDP | |
County fiscal revenue | + | 0.2108 | Reflects the financial level of the government in the county | |
County total retail sales of consumer goods | + | 0.1097 | Reflects the consumption level of residents in the county | |
People’s Livelihood | Urban per capita disposable income | + | 0.0197 | Reflects the income and living standards of urban residents in the county |
Rural per capita disposable income | + | 0.0418 | Reflects the income and living standards of rural residents in the county | |
Urban per capita living space | + | 0.0042 | Reflects the housing conditions of urban residents in the county | |
Rural per capita living space | + | 0.0022 | Reflects the housing conditions of rural residents in the county | |
Social Development | Urbanization rate | + | 0.1297 | Reflects urbanization level in the county |
Urban unemployment rate | - | 0.0095 | Reflects the employment situation of the resident in the county | |
Population density | + | 0.1150 | Reflects the density of population in the county | |
Public Resources | Number of students per 10,000 people in general primary and secondary schools | + | 0.0080 | Reflects educational conditions in the county |
Number of beds per 10,000 people in health institutions | + | 0.0212 | Reflects medical conditions in the county | |
Road network density | + | 0.0065 | The ratio of the total length of roads at all levels and area of the county, reflecting traffic conditions in the county | |
Natural Vulnerability | Potential productivity of farmland | + | 0.0092 | Reflects the potential of agriculture production in the county |
Average slope | − | 0.0144 | Reflects terrain conditions in the county | |
Area with slope greater than 15° | − | 0.0342 | Reflects terrain conditions in the county | |
Average precipitation | − | 0.0007 | Reflects climate conditions in the county; high precipitation is detrimental to agricultural production in the study area | |
Average temperature | + | 0.0001 | Reflects climate conditions in the county; low temperatures are detrimental to agricultural production in the study area |
N | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
RI | 0 | 0.58 | 0.9 | 1.12 | 1.24 | 1.32 | 1.41 | 1.45 | 1.49 |
Dimension | Feature Description | Feature Indicator | Calculation |
---|---|---|---|
Central tendency | Average nighttime light index (ANLI) in the county | MEAN | |
Total nighttime light index (TNLI) in the county | SUM | ||
Dispersion degree | Range of light value in the county | RANGE | MAX–MIN |
Standard deviation of light value in the county | STD | ||
Spatial characteristics | Maximum light value in the county | MAX | – |
Minimum light value in the county | MIN | - | |
Number of bright light pixels (DN > 0) in the county | COUNT | - | |
Relative light area in the county | AREA | ||
Local Moran’s index of light value in the county | MORAN’S I |
County | CEI Rank | GDP Rank | TNLI-VIIRS Rank | TNLI-LJ1 Rank | Rank Difference CEI vs. GDP | Rank Difference CEI vs. TNLI-VIIRS | Rank Difference CEI vs. TNLI-LJ1 |
---|---|---|---|---|---|---|---|
Wuchang | 5 | 5 | 5 | 5 | 0 | 0 | 0 |
Yangxin | 4 | 3 | 5 | 3 | 1 | −1 | 1 |
Yunxin | 1 | 1 | 3 | 1 | 0 | −2 | 0 |
Zhushan | 1 | 2 | 3 | 2 | −1 | −2 | −1 |
Zigui | 1 | 2 | 2 | 1 | −1 | −1 | 0 |
Zhongxiang | 4 | 5 | 5 | 4 | −1 | −1 | 0 |
Hanchuan | 5 | 5 | 5 | 5 | 0 | 0 | 0 |
Gongan | 4 | 4 | 4 | 3 | 0 | 0 | 1 |
Wuxue | 4 | 4 | 4 | 4 | 0 | 0 | 0 |
Lichuan | 2 | 2 | 5 | 4 | 0 | −3 | −2 |
Badong | 1 | 2 | 4 | 2 | −1 | −3 | −1 |
Laifeng | 1 | 1 | 2 | 1 | 0 | −1 | 0 |
Liuyang | 5 | 5 | 5 | 5 | 0 | 0 | 0 |
Chaling | 2 | 3 | 2 | 2 | −1 | 0 | 0 |
Xiangtan | 4 | 5 | 4 | 4 | −1 | 0 | 0 |
Changning | 3 | 4 | 3 | 3 | −1 | 0 | 0 |
Xinshao | 2 | 2 | 3 | 2 | 0 | −1 | 0 |
Dongkou | 2 | 3 | 2 | 1 | −1 | 0 | 1 |
Yueyang | 3 | 4 | 4 | 3 | −1 | −1 | 0 |
Linxiang | 3 | 4 | 3 | 3 | −1 | 0 | 0 |
Wulin | 5 | 5 | 5 | 5 | 0 | 0 | 0 |
Yongding | 3 | 3 | 5 | 3 | 0 | −2 | 0 |
Cili | 2 | 3 | 4 | 1 | −1 | −2 | 1 |
Taojiang | 3 | 4 | 3 | 3 | −1 | 0 | 0 |
Linwu | 2 | 2 | 2 | 2 | 0 | 0 | 0 |
Rucheng | 1 | 1 | 2 | 2 | 0 | −1 | −1 |
Shuangpai | 1 | 1 | 1 | 1 | 0 | 0 | 0 |
Lianyuan | 2 | 4 | 3 | 3 | −2 | −1 | −1 |
Changjiang | 4 | 4 | 3 | 4 | 0 | 1 | 0 |
Leping | 4 | 4 | 3 | 4 | 0 | 1 | 0 |
Yushui | 5 | 5 | 5 | 5 | 0 | 0 | 0 |
Jingan | 1 | 1 | 1 | 1 | 0 | 0 | 0 |
Yushan | 3 | 3 | 2 | 3 | 0 | 1 | 0 |
Methods | LR Model | RF Algorithm | ||
---|---|---|---|---|
Data | LJ1-01 | NPP-VIIRS | LJ1-01 | NPP-VIIRS |
R2 | 0.6380 | 0.4700 | 0.8168 | 0.7245 |
MAE | 0.0056 | 0.074 | 0.0027 | 0.0380 |
10-times cross-validated R2 | 0.6215 | 0.4533 | 0.7920 | 0.7054 |
ID | Variable | LJ1-01 | NPP-VIIRS |
---|---|---|---|
1 | AREA | 0.3445 | 0.1241 |
2 | COUNT | 0.1581 | 0.0593 |
3 | MEAN | 0.1474 | 0.0664 |
4 | SUM | 0.1399 | 0.1732 |
5 | MORAN’S I | 0.1301 | 0.0556 |
6 | STD | 0.0331 | 0.4681 |
7 | RANGE | 0.0246 | 0.0232 |
8 | MAX | 0.0211 | 0.0216 |
9 | MIN | 0.0023 | 0.0088 |
Index | CEI | GDP | ||
---|---|---|---|---|
Data | LJ1-01 | NPP-VIIRS | LJ1-01 | NPP-VIIRS |
R2 | 0.8168 | 0.7245 | 0.6858 | 0.6451 |
MAE | 0.0027 | 0.038 | 17,465.84 | 19,731.34 |
Province | Moran’s I | Z Score | p-Value |
---|---|---|---|
Hubei | 0.7125 | 11.710 | <0.001 |
Hunan | 0.6641 | 11.967 | <0.001 |
Jiangxi | 0.4976 | 8.053 | <0.001 |
Province | LJ1-01 | NPP-VIIRS | Range of CEI |
---|---|---|---|
Hubei | 0.8610 | 0.8388 | 0.0246–0.7513 |
Hunan | 0.7832 | 0.7286 | 0.0393–0.6016 |
Jiangxi | 0.7647 | 0.7082 | 0.0297–0.3547 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 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 (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, H.; Luo, N.; Hu, C. Detection of County Economic Development Using LJ1-01 Nighttime Light Imagery: A Comparison with NPP-VIIRS Data. Sensors 2020, 20, 6633. https://doi.org/10.3390/s20226633
Liu H, Luo N, Hu C. Detection of County Economic Development Using LJ1-01 Nighttime Light Imagery: A Comparison with NPP-VIIRS Data. Sensors. 2020; 20(22):6633. https://doi.org/10.3390/s20226633
Chicago/Turabian StyleLiu, Hongliang, Nianxue Luo, and Chunchun Hu. 2020. "Detection of County Economic Development Using LJ1-01 Nighttime Light Imagery: A Comparison with NPP-VIIRS Data" Sensors 20, no. 22: 6633. https://doi.org/10.3390/s20226633
APA StyleLiu, H., Luo, N., & Hu, C. (2020). Detection of County Economic Development Using LJ1-01 Nighttime Light Imagery: A Comparison with NPP-VIIRS Data. Sensors, 20(22), 6633. https://doi.org/10.3390/s20226633