Please wait a minute...
img

官方微信

遥感技术与应用  2020, Vol. 35 Issue (5): 1187-1196    DOI: 10.11873/j.issn.1004-0323.2020.5.1187
遥感应用     
基于大数据分析框架的生态脆弱型人地系统模式研究
宫晨1,2(),李新武1(),吴文瑾1
1.中国科学院遥感与数字地球研究所,北京 100094
2.中国科学院大学,北京 100049
Study on the Model of Ecological Vulnerable Human-land System based on Big Data Analysis Framework
Chen Gong1,2(),Xinwu Li1(),Wenjin Wu1
1.Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences,Beijing 100049,China
2.University of Chinese Academy of Sciences,Beijing 100049,China
 全文: PDF(4434 KB)   HTML
摘要:

针对生态脆弱型人地系统模式研究中存在的数据处理繁杂、模式识别偏主观、内在机理复杂等问题,提出了基于云平台及大数据方法的模式分析框架。通过遥感及社会经济云平台实现数据的云上收集及处理,利用自组织映射神经网络聚类(Self-Organizing Map,SOM)方法实现无先验知识的模式识别;同时利用知觉图从社会经济发展与生态友好性两个角度分析变化轨迹,利用关联规则方法筛选社会经济与生态环境之间的潜在规律。以“一带一路”65国进行实验分析,实验结果将“一带一路”65个国家有效划分为10类模式,并分析了10类模式的变化轨迹及关系规律。结果表明:该分析框架能够快速实现数据获取及处理、人地系统多模式识别、变化轨迹可视化和规律探测等功能,有效弥补了人地系统多模式研究中的不足。

关键词: 生态脆弱型人地系统SOM知觉图关联规则    
Abstract:

To solve the problems of complex data processing, subjective model recognition and complex internal mechanism in the study of ecological vulnerable human-land system, a model analysis framework based on cloud platform and big data methods was proposed. Remote sensing and socio-economic cloud platform are used to collect and process data. Self-organizing mapping neural network clustering (SOM) method is used to recognize model without prior knowledge. The trajectories was analyzed from the perspective of social-economic development and ecological friendliness by using perceptual map, and the laws between social economy and ecological environment was selected by using association rules.The experimental analysis was carried out in 65 Belt and Road countries. The experimental results effectively divided 65 countries into 10 models, and analyzed the trajectories and relationship rules of 10 models. The results show that the framework can perform the functions of data acquisition and processing, multi-model recognition of human-land system, trajectories visualization and rules detection. It effectively makes up for the deficiencies in the multi-model study of human-land system.

Key words: Ecological vulnerable human-land system    SOM    Perceptual map    Association rules
收稿日期: 2018-12-26 出版日期: 2020-11-26
ZTFLH:  X22  
基金资助: 海南省重点研发计划(ZDYF2019005);中国科学院国际合作局对外合作重点项目(131C11KYSB20160061)
通讯作者: 李新武     E-mail: gongchen@radi.ac.cn;lixw@radi.ac.cn
作者简介: 宫 晨(1993-),男,甘肃兰州人,硕士研究生,主要从事资源环境遥感研究。E?mail: gongchen@radi.ac.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  
宫晨
李新武
吴文瑾

引用本文:

宫晨,李新武,吴文瑾. 基于大数据分析框架的生态脆弱型人地系统模式研究[J]. 遥感技术与应用, 2020, 35(5): 1187-1196.

Chen Gong,Xinwu Li,Wenjin Wu. Study on the Model of Ecological Vulnerable Human-land System based on Big Data Analysis Framework. Remote Sensing Technology and Application, 2020, 35(5): 1187-1196.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2020.5.1187        http://www.rsta.ac.cn/CN/Y2020/V35/I5/1187

图1  基于大数据方法的生态脆弱型人地系统模式分析框架
图2  数据获取及处理云平台(a:Google Earth Engine云平台;b:Climate Engine云平台;c:World Map云平台;d:World Bank云平台)
图3  基于SOM聚类的发展模式识别
图4  Apriori算法流程图
序号数据集GEE ImageCollection ID时间范围空间分辨率时间分辨率
1AVHRR NPPusers/ gongchen9369/ 1992- 2000_npp_latlon1992~20008 km1 a
2MODIS NPPMODIS/ 055/ MOD17A32001~20141 km1 a
3Landsat 5 NDVILANDSAT/ LT05/ C01/ T1_8DAY_NDVI1992~200030 m8 d
4MODIS NDVIMODIS/ MCD43A4_NDVI2001~2014250 m16 d
表1  生态遥感数据集
序号数据集数据来源时间范围空间分辨率时间分辨率
1城市人口占总人口比例United Nations World Urbanization 2014 Prospects1992~2014国别1 a
2总GDPWorld Bank national accounts and OECD data files1992~2014国别1 a
3人均GDPWorld Bank national accounts and OECD data files1992~2014国别1 a
4第一产业比例World Bank national accounts and OECD data files1992~2014国别1 a
5第二产业比例World Bank national accounts and OECD data files1992~2014国别1 a
6第三产业比例World Bank national accounts and OECD data files1992~2014国别1 a
表2  社会经济数据集
发展模式国家
SOM 1巴林、伊朗、伊拉克、科威特、阿曼、卡塔尔、沙特阿拉伯、阿联酋
SOM 2哈萨克斯坦、俄罗斯、土耳其
SOM 3阿塞拜疆、中国、埃及、蒙古、叙利亚、土库曼斯坦、也门
SOM 4亚美尼亚
SOM 5阿富汗、不丹、柬埔寨、印度、吉尔吉斯斯坦、缅甸、尼泊尔、巴基斯坦、塔吉克斯坦、乌兹别克斯坦
SOM 6以色列、约旦、新加坡
SOM 7文莱、保加利亚、克罗地亚、塞浦路斯、捷克、爱沙尼亚、希腊、匈牙利、拉脱维亚、黎巴嫩、立陶宛、波兰、斯洛伐克、斯洛文尼亚
SOM 8白俄罗斯、乌克兰
SOM 9波黑、格鲁吉亚、印度尼西亚、马其顿、马来西亚、马尔代夫、黑山、菲律宾、罗马尼亚、塞尔维亚、泰国
SOM 10阿尔巴尼亚、孟加拉、老挝、摩尔多瓦、斯里兰卡、越南
表3  SOM聚类分析结果
Kaiser-Meyer-Olkin测量取样适当性0.65
Bartlett's球形度检验近似卡方5 361.56
自由度28
显著性0.000
表4  KMO和Bartlett检验
关键因子成分1成分2
城市人口占总人口比例0.84-0.24
总GDP0.04-0.17
人均GDP0.69-0.30
第一产业比例-0.890.15
第二产业比例0.07-0.77
第三产业比例0.670.58
NPP-0.230.67
NDVI-0.110.70
表5  正交旋转后的因子矩阵
图5  10类发展模式的知觉图变化轨迹
评价指标中心1中心2中心3中心4
城市人口占总人口比例/%28.4551.1269.1788.88
总GDP(US $)1.01E+104.85E+109.84E+101.61E+11
人均GDP(US $)747.502390.734731.787744.12
第一产业比例/%4.5115.1226.9844.08
第二产业比例/%20.5630.4442.9463.51
第三产业比例/%26.8641.0253.3666.96
NPP/gCm-2202.63720.251616.67
NDVI0.150.460.64
表6  关键因子离散化
IDUnGDPGDP perAgInSeNPPNDVI
BHR1992I14I21I34I41I53I64E11E21
BHR1993I14I21I34I41I53I64E11E21
BHR1994I14I21I34I41I53I64E11E21
BHR1995I14I21I34I41I53I63E11E21
BHR2007I14I21I34I41I53I63E11E21
?????????
表7  规范化社会经济与生态环境事务表
IDAssociation RulesST_supST_conf
1E11 → I4188.98%88.98%
2I41 → E2188.98%100%
3E11 → E21, I4188.98%88.98%
4I34 → E1177.17%100%
5E21 → I3477.17%77.17%
6I34 → E11, E2177.17%100%
????
表8  关联规则部分挖掘结果
1 Pattison, William D. The Four Traditions of Geography[J]. Journal of Geography, 1990, 89(5):202-206.
2 Newbold T, Bentley L F, Hill S L, et al. Global Effects of Land Use on Biodiversity Differ Among Functional Groups[J]. Functional Ecology,2020,34(3):684-693. doi: 10.1111/1365-2435.13500.
doi: 10.1111/1365-2435.13500
3 Probert J R, Parr C L, Holdo R M, et al. Anthropogenic Modifications to Fire Regimes in the Wider Serengeti-Mara Ecosystem[J]. Global Change Biology, 2019, 25(10):3406-3423. doi: 10.1111/gcb.14711.
doi: 10.1111/gcb.14711
4 Fu B J, Tian T, Liu Y X, et al. New Developments and Perspectives in Physical Geography in China[J]. Chinese Geographical Science, 2019, 29(3):363-371.
5 Wu Z H, Lei S G, He B J, et al. Assessment of Landscape Ecological Health: A Case Study of a Mining City in a Semi-Arid Steppe[J]. International Journal of Environmental Research and Public Health, 2019, 16(5):752.doi:10.3390/ijerph16050752.
doi: 10.3390/ijerph16050752
6 Gon S M, Tom S L, Woodside U. 'Aina Momona, Honua Au Loli-Productive Lands, Changing World: Using the Hawaiian Footprint to Inform Biocultural Restoration and Future Sustainability in Hawai'i[J]. Sustainability, 2018, 10(10):3420.doi:10.3390/SU10103420.
doi: 10.3390/SU10103420
7 Liu Yanxu, Fu Bojie, Wang Shuai, et al. Research Progress of Human-earth System Dynamics based on Spatial Resilience Theory[J]. Acta Geographica Sinica, 2020, 75(5): 891-903.
7 刘焱序, 傅伯杰, 王帅,等. 空间恢复力理论支持下的人地系统动态研究进展[J]. 地理学报, 2020, 75(5): 891-903.
8 Lu Dadao. Theoretical Studies of Man-land System as the Core of Geographical Science[J]. Geographical Research, 2002, 21 (2): 135-145.
8 陆大道. 关于地理学的“人—地系统”理论研究[J]. 地理研究, 2002, 21(2):135-145.
9 Ma Hailong. The study on the Coordination and Adjustment Mechanism of Human-land Relationship in the Industry-Development-Restricted Region of Western China[D]. Beijing: Institute of Geographical Sciences and Natural Resources Research, CAS, 2008.马海龙. 西部限制开发区人地关系调控的机理与途径[D]. 北京: 中国科学院地理科学与资源研究所, 2008.
10 Iriarte J L, González H E, Nahuelhual L. Patagonian Fjord Ecosystems in Southern Chile as a Highly Vulnerable Region: Problems and Needs[J]. AMBIO-A Journal of The Human Environment, 2010, 39(7):463-466.
11 Shukla R, Chakraborty A, Joshi P K. Vulnerability of Agro-ecological Zones in India Under the Earth System Climate Model Scenarios[J]. Mitigation and Adaptation Strategies for Global Change, 2017, 22(3):399-425.
12 Liu Xiaoqiong, Liu Yansui. Research on the Sustainable Development of Vulnerable Ecological Region based on AHP—A Case Study of Yulin City[J]. Journal of Arid Land Resources and Environment, 2009,23(5):19-23.
12 刘晓琼, 刘彦随. 基于AHP的生态脆弱区可持续发展评价研究——以陕西省榆林市为例[J]. 干旱区资源与环境, 2009,23(5) :19-23.
13 Zhang Juntao, Fu Xiaofeng. Research on the Sustainable Development of the Vulnerable Eco-Regions[J]. China Population, Resources and Environment, 2005, 15(5):58-62.
13 张军涛, 傅小锋. 东北农牧交错生态脆弱区可持续发展研究[J]. 中国人口·资源与环境, 2005, 15(5):58-62.
14 Leng Shuying, Liu Yanhua. A Conceptual Framework of Sustainable Developmental Indicators of Fragile Environment of China[J]. China Population, Resources and Environment,1999,9(2):3-5.
14 冷疏影, 刘燕华. 中国脆弱生态区可持续发展指标体系框架设计[J].中国人口·资源与环境,1999,9(2):3-5.
15 Dong Suocheng, Li Dai, Li Rongsheng, et al. A Circular Economic Pattern in the Eco-fragile Region of the Loess Plateau: A Case Study in Longxi County of Gansu Province. Resources Science, 2005, 27(4):82-88. [董锁成, 李岱, 李荣生等. 黄土高原生态脆弱区循环经济发展模式研究[J]. 资源科学, 2005, 27(4):82-88.]
16 Gorelick N , Hancher M , Dixon M , et al. Google Earth Engine: Planetary-scale Geospatial Analysis for Everyone[J]. Remote Sensing of Environment, 2017, 202: 18-27.
17 Hegewisch K, Daudert B, Morton C, et al. Climate Engine - Monitoring Drought with Google Earth Engine[C]∥ American Geophysical Union, Fall Meeting, 2016.
18 Liu Y, Weisberg R H. A Review of Self-organizing Map Application in Meteorology and Oceanography[M]. Rijeka: IntechOpen, 2011.
19 Kohonen T. Self-Organized Formation of Topologically Correct Feature Maps[J]. Biological Cybernetics, 1982, 43(1): 59-69.
20 Kalteh A M, Hjorth P, Berndtsson R. Review of the Self-Organizing Map (SOM) Approach in Water Resourse: Analysis, Modeling and Application[J]. Environmental Modeling & Software, 2008, 23(7): 835-845.
21 Tsakovski S , JoannaŻukowska, PeterBode, et al. Self-organizing Maps Classification of Epidemiological Data and Toenail Selenium Dontent Monitored on Cancer and Healthy Patients from Poland[J].Environmental Letters, 2010, 45(3):7.doi:10.10801/10934520903467840.
doi: 10.10801/10934520903467840
22 Gholami V, Khaleghi M R, Salimi,E T. Groundwater Quality Modeling Using self-organizing Map (SOM) and Geographic Information System (GIS) on the Caspian Southern Coasts[J]. Journal of Mountain Science, 2020, 17(7):1724-1734. doi: 10.1007/s11629-019-5483-y.
doi: 10.1007/s11629-019-5483-y
23 Zhang Youyin, Gu Jing. Analysis of British Tourists’ Hotel Property Perception based on Perceptual Mapping[J]. Tourism Forum, 2015(3):8-13.
23 张佑印, 顾静. 基于知觉图的旅华英国游客酒店属性感知分析[J]. 旅游论坛, 2015(3):8-13.
24 Xie Kun, Zhang Junfang. Short-term Wind Speed Forecasting Using PCA-WNN based on KMO-Bartlett Typical Wind Speed Selection[J]. Power Equipment, 2017, 31(2):86-91.
24 解坤, 张俊芳. 基于KMO—Bartlett典型风速选取的PCA-WNN短期风速预测[J]. 发电设备, 2017, 31(2):86-91.
25 Chen M S , Han J , Yu P S. Data Mining: An Overview from a Database Perspective[J]. IEEE Transactions on Knowledge and Data Engineering, 1996, 8(6):866-883.
26 Wu X , Kumar V , Quinlan J R , et al. Top 10 Algorithms in Data Mining[J]. Knowledge and Information Systems, 2008, 14(1):1-37.
27 Dayal U,Whang K Y,Lomet D,et al. Proceedings of the 32nd International Conference on Very Large Data bases[C]∥ International Conference on Very Large Data Bases, 2006.
[1] 周颂洋,谭琨,吴立新. 基于邻域距离ISOMAP算法的高光谱遥感降维算法[J]. 遥感技术与应用, 2014, 29(4): 695-700.
[2] 初佳兰,赵冬至,张丰收 . 基于关联规则的裙带菜筏式养殖遥感识别方法[J]. 遥感技术与应用, 2012, 27(6): 941-946.
[3] 张 扬,周子勇. 基于关联规则的面向对象高分辨率影像分类[J]. 遥感技术与应用, 2012, 27(3): 339-346.
[4] 王贤敏,牛瑞卿. 三峡库区基于概念格算法的遥感岩性分析[J]. 遥感技术与应用, 2009, 24(1): 32-39.
[5] 马超飞,刘建强. 遥感图像多维量化关联规则挖掘[J]. 遥感技术与应用, 2003, 18(4): 243-247.