Please wait a minute...
img

官方微信

遥感技术与应用  2020, Vol. 35 Issue (6): 1368-1376    DOI: 10.11873/j.issn.1004-0323.2020.6.1368
灯光遥感专栏     
融合灯光强度和斑块空间分布特征的贫困区域识别模型构建——以山西省为例
昝骁毓1,2,3(),谭晓悦1,4,李强1(),陈晋1
1.北京师范大学 地理科学学部,北京 100875
2.中国科学院电子学研究所苏州研究院,江苏 苏州 215123
3.苏州市空天大数据智能应用技术重点实验室,江苏 苏州 215123
4.香港理工大学 土地测量及地理资讯学系,香港
Recognition Model of Poverty Areas Combining Light Intensity and Patch Spatial Distribution Characteristics: A Case Study of Shanxi Province
Xiaoyu Zan1,2,3(),Xiaoyue Tan1,4,Qiang Li1(),Jin Chen1
1.Faculty of Geographical Science,Beijing Normal University,Beijing 100875,China
2.Institute of Electronics,Chinese Academy of Sciences,Suzhou 215123,China
3.Key Laboratory of Intelligent Aerospace Big Data Application Technology,Suzhou 215123,China
4.The Department of Land Surveying and Geo-Informatics,The Hong Kong Polytechnic University,Hong Kong,China
 全文: PDF(3140 KB)   HTML
摘要:

贫困区域识别对于国家实施精准扶贫方略具有重要作用。基于山西省2013~2017年NPP-VIIRS夜间灯光数据,提取灯光总强度、平均灯光强度、灯光斑块面积、最大斑块灯光强度、灯光斑块聚集度等参数,应用方差分析方法检验贫困县与非贫困县的参数差异;以2013年NPP-VIIRS数据构建贫困区域识别模型,并应用于2014~2017年的贫困县识别。结果表明:模型的综合识别准确率为71.43%~77.31%,贫困县识别精度较高,为79.31%~86.21%,非贫困县识别精度为59.02%~73.77%。除了灯光强度参数,模型中包含灯光斑块空间分布特征参数能够提高总体精度。进一步分析贫困概率与GDP关系、不同类型县的贫困概率年际变化,可以认为:夜间灯光数据能够用于贫困区域识别和退出评估,融合灯光强度与灯光斑块空间分布特征有助于提高贫困区域识别精度。

关键词: 贫困区域识别NPP-VIIRS数据判别分析山西省灯光斑块空间特征    
Abstract:

The poverty area recognition is the key to formulate national poverty alleviation policies. Based on satellite-based nighttime light data (NPP-VIIRS data) of 119 counties in Shanxi Province from 2013 to 2017, the statistical significance of differences between poverty counties and other counties was tested by variance analysis in terms of total light intensity, average light intensity, maximum patch light intensity, total patch area, and patch agglomeration. The recognition model of poverty areas was then developed using the NPP-VIIRS data of 2013 and applied to recognize poverty counties in 2014~2017. The results showed that the recognition accuracy of the model for poverty counties is relatively high, ranging from 79.31% to 86.21%. For non-poverty counties, the recognition accuracy is relatively lower, ranging from 59.02% to 73.77%. The comprehensive recognition accuracy is between 71.43% and 77.31%. Besides parameters of light intensity, including parameters related to landscape characteristics of lighted patches helps to improve model accuracy. In addition, we analyzed the relationship between poverty probability and GDP, the reasons of the counties with incorrect cognition, and annual variation of the poverty probability for 58 poverty counties and 15 counties out of poverty. The results not only confirmed the applicability of nighttime light data in the poverty counties recognition and assessment of the counties out of poverty, but also highlighted the important role of landscape characteristics of lighted patches, which were not included in the existing studies.

Key words: Poverty area recognition    NPP-VIIRS data    Discriminant analysis    Shanxi Province    Landscape characteristics of light patches
收稿日期: 2019-08-23 出版日期: 2021-01-26
ZTFLH:  TP79  
基金资助: 科技基础资源调查专项(2019FY202502)
通讯作者: 李强     E-mail: zanxy@mail.bnu.edu.cn;liqiang@bnu.edu.cn
作者简介: 昝骁毓(1995-),女,陕西西安人,硕士研究生,主要从事遥感与GIS应用研究。E?mail:zanxy@mail.bnu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
昝骁毓
谭晓悦
李强
陈晋

引用本文:

昝骁毓,谭晓悦,李强,陈晋. 融合灯光强度和斑块空间分布特征的贫困区域识别模型构建——以山西省为例[J]. 遥感技术与应用, 2020, 35(6): 1368-1376.

Xiaoyu Zan,Xiaoyue Tan,Qiang Li,Jin Chen. Recognition Model of Poverty Areas Combining Light Intensity and Patch Spatial Distribution Characteristics: A Case Study of Shanxi Province. Remote Sensing Technology and Application, 2020, 35(6): 1368-1376.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2020.6.1368        http://www.rsta.ac.cn/CN/Y2020/V35/I6/1368

图1  研究区灯光分布及地形特征
参数组间方差组内方差F值P值
灯光总强度x10.090.017.040.01
平均灯光强度x20.320.0218.580.00
灯光斑块面积x30.200.037.950.01
最大斑块灯光强度x40.130.019.940.00
灯光斑块聚集度x50.580.0416.330.00
表1  贫困识别参数的方差分析结果

实际结果

(个)

识别结果综合识别 准确率/%
贫困县非贫困县
%%
贫困县(58)4475.861424.1473.95
非贫困县(61)1727.874472.13
表2  贫困区域识别模型的精度
年份

实际结果

(个)

识别结果综合识别 准确率/%
贫困县非贫困县
%%
2014贫困县(58)5086.21813.7977.31
非贫困县(61)1931.154268.85
2015贫困县(58)5086.21813.7975.63
非贫困县(61)2134.434065.57
2016贫困县(58)4984.48915.5271.43
非贫困县(61)2540.983659.02
2017贫困县(58)4679.311220.6976.47
非贫困县(61)1626.234573.77
表3  贫困区域识别模型的应用及精度分析结果
年份

实际结果

(个)

识别结果综合识别 准确率/%
贫困县非贫困县
%%
2014贫困县(58)5594.8335.1772.27
非贫困县(61)3049.183150.82
2015贫困县(58)5798.2811.7272.27
非贫困县(61)3252.462947.54
2016贫困县(58)5798.2811.7272.27
非贫困县(61)3252.462947.54
2017贫困县(58)5798.2811.7273.11
非贫困县(61)3150.823049.18
表4  仅考虑灯光强度参数的贫困区域识别模型
年份全省贫困县非贫困县
2013-0.60**-0.39**-0.47**
2014-0.58**-0.40**-0.42**
2015-0.58**-0.27*-0.42**
2016-0.58**-0.23-0.46**
2017-0.57**-0.30*-0.47**
2013~2017-0.58**-0.34**-0.45**
表5  贫困概率与GDP相关分析结果
图2  2014~2017年所有判别结果有误的县
贫困概率变化县区及数目
识别为非贫困县安泽县、保德县、大同县、古县、壶关县、交城县、离石区、柳林县、平鲁区、闻喜县、中阳县(11)
贫困概率下降

代县、繁峙县、方山县、汾西县、广灵县、和顺县、河曲县、浑源县、静乐县、岢岚县、岚县、

临县、灵丘县、陵川县、娄烦县、偏关县、平陆县、沁水县、沁源县、石楼县、天镇县、五台县、五寨县、武乡县、夏县、 乡宁县、兴县、阳高县、阳曲县、永和县、右玉县、榆社县(32)

贫困概率稳定浮山县、交口县、宁武县、蒲县、山阴县、神池县、万荣县、昔阳县、隰县、垣曲县、左权县(11)
贫困概率上升大宁县、吉县、平顺县、沁县(4)
表6  58个贫困县2013~2017年的贫困概率年际变化
图3  贫困退出县的贫困概率年际变化
1 Sen A. Development as Freedom[M]. Oxford: Oxford University Press, 1999.
2 Wang Xiaolin. The Measurement of Poverty Theories and Methods[M]. Beijing: Social Sciences Academic Press(CHINA), 2012.王小林. 贫困测量:理论与方法[M]. 北京: 社会科学文献出版社, 2012.
3 Liu Hong, Wang Chao. On the Chinese Rural Poverty Identification: Based on the Hierarchical Logistic Regression Model[J]. Journal of Agrotechnical, 2018(2): 130-140.刘洪,王超. 基于分层Logistic回归模型的中国农村贫困识别研究[J]. 农业技术经济, 2018(2): 130-140.
4 Liu Yanhua, Xu Yong. Geographical Identification and Classification of Multi-dimensional Poverty in Rural China[J]. Arta Geographica Sinica,2015, 70(6): 993-1007.
4 刘艳华,徐勇. 中国农村多维贫困地理识别及类型划分[J]. 地理学报, 2015, 70(6): 993-1007.
5 Ghosh T, Sharolyn A, Rebecca P, et al. Estimation of Mexico’s Informal Economy and Remittances Using Nighttime Imagery[J]. Remote Sensing, 2009, 1(3): 418-444.doi:10.3390/rs1030418.
doi: 10.3390/rs1030418
6 Elvidge C D, Baugh K E, Kihn E A, et al. Relation between Satellite Observed Visible-near Infrared Emissions, Population, Economic Activity and Electric Power Consumption[J]. International Journal of Remote Sensing, 1997, 18(6): 1373-1379.doi:10.1080/014311697218485.
doi: 10.1080/014311697218485
7 Chen Jin, Zhuo Li, Shi Peijun, et al. The Study on Urbanization Process in China based on DMSP/OLS Data : Development of a Light Index for Urbanization Level Estimation[J]. Journal of Remote Sensing, 2003, 7(3): 168-175,241.
7 陈晋,卓莉,史培军,等. 基于DMSP/OLS数据的中国城市化过程研究——反映区域城市化水平的灯光指数的构建[J]. 遥感学报, 2003, 7(3): 168-175,241.
8 Shu Song, Yu Bailang, Wu Jianping, et al. Methods for Deriving Urban Built-up Area Using Night-light Data:Assessment and Application[J]. Remote Sensing Technology and Application, 2011, 26(2):169-176.
8 舒松, 余柏蒗, 吴健平, 等. 基于夜间灯光数据的城市建成区提取方法评价与应用[J]. 遥感技术与应用, 2011, 26(2) : 169-176.
9 Zhuo Li, Shi Peijun, Chen Jin, et al. Application of Compound Night Light Index Derived from DMSP/OLS Data to Urbanization Analysis in China in the 1990s[J]. Acta Geographica Sinica, 2003, 58(6) :893-902.
9 卓莉, 史培军, 陈晋, 等. 20世纪90年代中国城市时空变化特征——基于灯光指数CNLI方法的探讨[J]. 地理学报, 2003, 58(6): 893-902.
10 Bai Heting, Ma Mingguo, Yan Ran, et al. Evaluation of Urban Expansion in Chongqing City based on the Nighttime Light Data[J]. Remote Sensing Technology and Application,2019,34(1):216-224.
10 白贺庭,马明国,阎然, 等. 基于夜间灯光数据的重庆市城市扩张研究[J].遥感技术与应用,2019,34(1): 216-224.
11 Li Deren, Li Xi. An Overview on Data Mining of Nighttime Light Remote Sensing[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(6): 591-601.
11 李德仁,李熙. 论夜光遥感数据挖掘[J]. 测绘学报, 2015, 44(6): 591-601.
12 Elvidge C D, Sutton P C, Ghosh T. A Global Poverty Map Derived from Satellite Data[J]. Computes & Geosciences, 2009, 35(8):1652-1660. doi:10.1016/j.cageo.2009.01.009.
doi: 10.1016/j.cageo.2009.01.009
13 Wang W, Cheng H, Zhang L. Poverty Assessment Using DMSP/OLS Night-time Light Satellite Imagery at A Provincial Scale in China[J]. Advances in Space Research, 2012, 49(8): 1253-1264.doi:10.1016/j.asr.2012.01.025.
doi: 10.1016/j.asr.2012.01.025
14 Yuan Tao. Monitoring Methods for Poor Areas Supported by DMSP/OLS Night-time Light Imgery[D]. Beijing: China University of Geosciences, 2013.
14 袁涛. DMSP/OLS数据支持的贫困地区测度方法研究[D]. 北京:中国地质大学, 2013.
15 Zhou Yuke, Gao Xizhang, Ni Xiliang. Analyzing Regional Inequality of Socioeconomic Development in China with Nighttime Light[J]. Remote Sensing Technology and Application, 2017, 32(6): 1107-1113.
15 周玉科,高锡章,倪希亮. 利用夜间灯光数据分析我国社会经济发展的区域不均衡特征[J]. 遥感技术与应用, 2017, 32(6): 1107-1113.
16 Yu B, Shi K, Hu Y, et al. Poverty Evaluation Using NPP-VIIRS Nighttime Light Composite Data at the County Level in China[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(3): 1-13.doi:10.1109/JSTARS.2015.2399416.
doi: 10.1109/JSTARS.2015.2399416
17 Pan Jinghu, Hu Yanxing. Spatial Identification of Multidimensional Poverty in China based on Nighttime Light Remote Sensing Data[J]. Economic Geography, 2016, 36(11): 124-131.
17 潘竟虎,胡艳兴. 基于夜间灯光数据的中国多维贫困空间识别[J]. 经济地理, 2016, 36(11): 124-131.
18 Shen Dan, Zhou Liang, Wang Peian. Identification of Poverty based on Nighttime Light Remote Sensing Data: A Case Study on Contiguous Special Poverty-stricken Areas in Liupan Mountains[J].Remote Sensing for Land and Resources, 2019, 31(2): 157-163.
18 沈丹, 周亮, 王培安. 基于夜间灯光数据的六盘山连片特困区贫困度识别[J]. 国土资源遥感, 2019, 31(2): 157-163.
19 Li Zongguang, Hu Deyong, Li Jihe, et al. Simulation and Spatialization of GDP in Poverty Areas based on Night Light Imagery[J]. Remote Sensing for Land and Resources, 2016, 28(2): 168-174.
19 李宗光,胡德勇,李吉贺,等. 基于夜间灯光数据的连片特困区GDP估算及其空间化[J]. 国土资源遥感, 2016, 28(2): 168-174.
20 Zhuo Li, Li Qiang, Shi Peijun, et al. Identification and Characteristics Analysis of Urban Land Expansion Types in China in the 1990s Using DMSP/OLS Data[J]. Acta Geographica Sinica, 2006, 61(2): 169-178.
20 卓莉,李强,史培军,等. 基于夜间灯光数据的中国城市用地扩展类型[J]. 地理学报, 2006, 61(2): 169-178.
21 Xu Weijie, Bian Panpan, Bai Jueying, et al. Study on the Distribution of Rural Residential Areas Based on GIS and Landscape Index[J]. Geospatial Information, 2017, 15(7): 59-62,72.
21 徐威杰,卞盼盼,白珏莹,等. 基于GIS和景观指数的农村居民点分布研究[J]. 地理空间信息, 2017, 15(7): 59-62,72.
22 Pan Jinghu, Jin Xuetao, Han Wenchao. Landscape Patterns and Spatial Distribution Characteristics of Rural Residential Areas in Gangu County[J]. Journal of Northwest University (Natural Science Edition), 2011, 41(1): 127-133.
22 潘竟虎,靳学涛,韩文超. 甘谷县农村居民点景观格局与空间分布特征[J].西北大学学报(自然科学版),2011,41(1):127-133.
[1] 黄妙芬,齐小平,于五一,张一民. 水环境石油类污染遥感识别模式及其应用[J]. 遥感技术与应用, 2007, 22(3): 314-320.