面向自然资源信息提取的多源异构数据融合技术——以汉江流域NDVI数据为例

doi:10.19388/j.zgdzdc.2021.02.11

Abstract
Figure/Table
References
Related Citation (14)

Download: PDF (4413 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Natural resource indicator data with high spatio-temporal resolution are essential for large-scale natural resource dynamic observation and trend assessment. The large amount of multi-source data under big data era could provide the possibility for efficient utilization and fusion of data. Taking the Normalized Difference Vegetation Index (NDVI) in Hanjiang Basin as an example, the authors in this paper have built a spatio-temporal big data processing underlying architecture for natural resources based on PostgreSQL, and integrated three types of methods, including data-level fusion, feature-level fusion and decision-level fusion. Besides, the intelligent fusion system of multi-source heterogeneous data has been constructed based on the machine learning algorithms to achieve efficient utilization of multi-source data and feature spatial preference. Meanwhile, the year-by-year NDVI 1 km dataset of Hanjiang Basin from 2000 to 2019 has been reconstructed to comprehensively reflect the dynamic changes of vegetation in Hanjiang Basin. These results could provide some scientific reference for the efficient extraction and simulation analysis of spatio-temporal big data in earth sciences, and provide a more accurate and convenient technical means for quantitatively accounting the scale of forest and grassland resources endowment and exploring the spatio-temporal evolution of ecosystem.

Key words： natural resources multi-source heterogeneity spatio-temporal data fusion machine learning

Received: 26 February 2021

ZTFLH:	P96
	TP391
	TP75

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	TANG Yulei
	WU Yangyang
	JIANG Xingzheng
	FENG Liang
	GAO Yang

Cite this article:

TANG Yulei,WU Yangyang,JIANG Xingzheng, et al. Multi-source heterogeneous data fusion technology for natural resource information extraction: A case study of NDVI data in Hanjiang Basin[J]. , 2021, 8(2): 74-82.

URL:

http://journal25.magtechjournal.com/Jwk_dzdc/EN/10.19388/j.zgdzdc.2021.02.11 OR http://journal25.magtechjournal.com/Jwk_dzdc/EN/Y2021/V8/I2/74

[1] 余辉,梁镇涛,鄢宇晨.多来源多模态数据融合与集成研究进展[J].情报理论与实践,2020,43(11):169-178.
Yu H,Liang Z T,Yan Y C.Review on multi-source and multi-modal data fusion and integration[J].Inf Stud:Theory Appl,2020,43(11):169-178.
[2] Zhu X L,Cai F Y,Tian J Q,et al.Spatiotemporal fusion of multisource remote sensing data:literature survey,taxonomy,principles,applications,and future directions[J].Remote Sens,2018,10(4):527.
[3] 唐见,曹慧群,陈进.生态保护工程和气候变化对长江源区植被变化的影响量化[J].地理学报,2019,74(1):76-86.
Tang J,Cao H Q,Chen J.Effects of ecological conservation projects and climate variations on vegetation changes in the source region of the Yangtze River[J].Acta Geogr Sin,2019,74(1):76-86.
[4] 徐凯健,田庆久,徐念旭,等.基于时序NDVI与光谱微分变换的森林优势树种识别[J].光谱学与光谱分析,2019,39(12):3794-3800.
Xu K J,Tian Q J,Xu N X,et al.Classifying forest dominant trees species based on high dimensional time-series NDVI data and differential transform methods[J].Spectrosc Spect Anal,2019,39(12):3794-3800.
[5] Leveau L M,Isla F I,Bellocq M I.From town to town:predicting the taxonomic,functional and phylogenetic diversity of birds using NDVI[J].Ecol Indicat,2020,119:106703.
[6] Zhang Y H,Ling F,Foody G M,et al.Mapping annual forest cover by fusing PALSAR/PALSAR-2 and MODIS NDVI during 2007-2016[J].Remote Sens Environ,2019,224:74-91.
[7] Cao R Y,Chen Y,Shen M G,et al.A simple method to improve the quality of NDVI time-series data by integrating spatiotemporal information with the Savitzky-Golay filter[J].Remote Sens Environ,2018,217:244-257.
[8] Luo F L,Zhang L P,Du B,et al.Dimensionality reduction with enhanced hybrid-graph discriminant learning for hyperspectral image classification[J].IEEE Trans Geosci Remote Sens,2020,58(8):5336-5353.
[9] 高艳丽,李红波,侯蕊.汉江流域生态系统服务权衡与协同关系演变[J].长江流域资源与环境,2020,29(7):1619-1630.
Gao Y L,Li H B,Hou R.Evolution analysis on trade-offs and synergies of ecosystem services in Hanjiang River Basin[J].Resour Environ Yangtze Basin,2020,29(7):1619-1630.
[10] 张翔,邓志民,李丹,等.汉江流域土地利用/覆被变化的水文效应模拟研究[J].长江流域资源与环境,2014,23(10):1449-1455.
Zhang X,Deng Z M,Li D,et al.Simulation of hydrological response to land use/cover change in Hanjiang Basin[J].Resour Environ Yangtze Basin,2014,23(10):1449-1455.
[11] Zhang Y Y,Ban X,Li E H,et al.Evaluating ecological health in the middle-lower reaches of the Hanjiang River with casca-de reservoirs using the Planktonic Index of Biotic Integrity (P-IBI)[J].Ecol Indicat,2020,114:106282.
[12] 葛良胜,夏锐.自然资源综合调查业务体系框架[J].自然资源学报,2020,35(9):2254-2269.
Ge L S,Xia R.Research on comprehensive investigation work system of natural resources[J].J Nat Resour,2020,35(9):2254-2269.
[13] White F E.Data Fusion Lexicon[M].Washington:Joint Directors of Labs Washington DC,1991.
[14] Zhou J X,Chen J,Chen X H,et al.Sensitivity of six typical spatio-temporal fusion methods to different influential factors:a compa-rative study for a normalized difference vegetation index time series reconstruction[J].Remote Sens Environ,2021,252:112130.
[15] Millard K,Richardson M.On the importance of training data sample selection in random forest image classification:a case study in peatland ecosystem mapping[J].Remote Sens,2015,7(7):8489-8515.
[16] Belgiu M,Drǎguț L.Random forest in remote sensing:a review of applications and future directions[J].ISPRS J Photogramm Remote Sens,2016,11(4):24-31.
[17] Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.
[18] 李彩霞,邓帆,张佳华,等.基于时序植被指数的湖北省物候空间特征分析[J].长江流域资源与环境,2019,28(7):1583-1589.
Li C X,Deng F,Zhang J H,et al.Phenological spatial characteristics of Hubei Province based on time series vegetation index[J].Resour Environ Yangtze Basin,2019,28(7):1583-1589.
[19] Guzmán Q J A,Sanchez-Azofeifa G A,Espírito-Santo M M.MODIS and PROBA-V NDVI products differ when compared with observations from phenological towers at four tropical dry forests in the Americas[J].Remote Sens,2019,11(19):2316.
[20] Toté C,Swinnen E,Sterckx S,et al.Evaluation of the SPOT/VEGETATION collection 3 reprocessed dataset:surface reflectances and NDVI[J].Remote Sens Environ,2017,201:219-233.
[21] Meroni M,Fasbender D,Balaghi R,et al.Evaluating NDVI data continuity between SPOT-VEGETATION and PROBA-V missions for operational yield forecasting in North African countr-ies[J].IEEE Trans Geosci Remote Sens,2016,54(2):795-804.
[22] 汤宇磊,杨复沫,詹宇.四川盆地PM2.5与PM10高分辨率时空分布及关联分析[J].中国环境科学,2019,39(12):4950-4958.
Tang Y L,Yang F M,Zhan Y.High resolution spatiotemporal distributionand correlation analysis of PM2.5 and PM10 concentrations in the Sichuan Basin[J].China Environ Sci,2019,39(12):4950-4958.
[23] 周成虎,程维明.《中华人民共和国地貌图集》的研究与编制[J].地理研究,2010,29(6):970-979.
Zhou C H,Cheng W M.Research and compilation of the Geomorphological Atlas of the People’s Republic of China[J].Geograph Res,2010,29(6):970-979.
[24] 徐新良.中国GDP空间分布公里网格数据集[DB/OL].中国科学院资源环境科学数据中心,2017.http://www.resdc.cn/.
Xu X L.Spatial distribution of national GDP in 1km grid[DB/OL].Data Center for Resources and Environmental Sciences,Chinese Academy of Sciences,2017.http://www.resdc.cn/.
[25] Svetnik V,Liaw A,Tong C,et al.Random forest:a classification and regression tool for compound classification and QSAR modeling[J].J Chem Inf Comput Sci,2003,43(6):1947-1958.
[26] Wright M N,Ziegler A.Ranger:a fast implementation of random forests for high dimensional data in C++ and R[J].J Stat Softw,2017,77(1):1-17.
[27] Sun Q Y,Liu W W,Gao Y N,et al.Spatiotemporal variation and climate influence factors of vegetation ecological quality in the Sanjiangyuan National Park[J].Sustainability,2020,12(16):6634.
[28] Solangi G S,Siyal A A,Siyal P.Spatiotemporal dynamics of land surface temperature and its impact on the vegetation[J].Civil Eng J,2019,5(8):1753-1763.
[29] 赵芳,张久阳,刘思远,等.秦巴山地NPP及对气候变化响应的多维地带性与暖温带-亚热带界线[J].生态学报,2021,41(1):57-68.
Zhao F,Zhang J Y,Liu S Y,et al.Assessing the dividing line between warm temperate and subtropical zones based on the zonality discussion on multi-dimensional response of Net Primary Productivity to climate change in the Qinling-Daba Mountains[J].Acta Ecol Sin,2021,41(1):57-68.
[30] Wang Y K,Wang D,Wu J C.Assessing the impact of Danjiangkou reservoir on ecohydrological conditions in Hanjiang river,Chi-na[J].Ecol Eng,2015,81:41-52.
[31] 杨倩,刘登峰,孟宪萌,等.汉江上游植被指数变化及其归因分析[J].南水北调与水利科技,2019,17(4):138-148.
Yang Q,Liu D F,Meng X M,et al.Vegetation index change in the upper reaches of Han River and its attribution analysis[J].South North Water Transf Water Sci Technol,2019,17(4):138-148.
[32] 马梓策,于红博,曹聪明,等.中国植被覆盖度时空特征及其影响因素分析[J].长江流域资源与环境,2020,29(6):1310-1321.
Ma Z C,Yu H B,Cao C M,et al.Spatiotemporal characteristics of fractional vegetation coverage and its influencing factors in Chi-na[J].Resour Environ Yangtze Basin,2020,29(6):1310-1321.
[33] 徐静文,肖飞,廖炜,等.基于MODIS NDVI汉江中游植被时空变化及其地貌分异分析[J].长江流域资源与环境,2017,26(11):1895-1901.
Xu J W,Xiao F,Liao W,et al.Spatial-temporal changes of vegetation and its geomorphic differentiation in the middle reaches of the Hanjiang River based on MODIS NDVI data[J].Resour Environ Yangtze Basin,2017,26(11):1895-1901.
[34] 刘海,黄跃飞,林苗,等.基于GIS的汉江流域水土保持时空变化特征分析(2001—2017年)[J].地域研究与开发,2019,38(3):154-159,164.
Liu H,Huang Y F,Lin M,et al.Analysis of temporal and spatial variation characteristics of soil and water conservation in Hanjiang River Basin based on GIS (2001-2017)[J].Areal Res Dev,2019,38(3):154-159,164.
[35] 王建邦,赵军,李传华,等.2001—2015年中国植被覆盖人为影响的时空格局[J].地理学报,2019,74(3):504-519.
Wang J B,Zhao J,Li C H,et al.The spatial-temporal patterns of the impact of human activities on vegetation coverage in China from 2001 to 2015[J].Acta Geogr Sin,2019,74(3):504-519.
[36] 任正超,朱华忠,史华,等.最后间冰期至未来2070s中国潜在自然植被时空分布格局及其对气候变化的响应[J].自然资源学报,2020,35(6):1484-1498.
Ren Z C,Zhu H Z,Shi H,et al.Spatio-temporal distribution pattern of potential natural vegetation and its response to climate change from Last Interglacial to future 2070s in China[J].J Nat Resour,2020,35(6):1484-1498.
[37] 邓元杰,姚顺波,侯孟阳,等.长江流域中上游植被NDVI时空变化及其地形分异效应[J].长江流域资源与环境,2020,29(1):66-78.
Deng Y J,Yao S B,Hou M Y,et al.Temporal and spatial variation of vegetation NDVI and its topographic differentiation effect in the middle and upper reaches of the Yangtze River Basin[J].Resour Environ Yangtze Basin,2020,29(1):66-78.
[38] 刘兴,孙新杰.南阳市退耕还林工程建设现状及展望[J].现代园艺,2017(17):183.
Liu X,Sun X J.The status quo and prospect of the program to return farmland to forests in Nanyang[J].Xiandai Hortic,2017(17):183.
[39] Liu Y,Li Y,Li S C,et al.Spatial and temporal patterns of global NDVI trends:correlations with climate and human factors[J].Remote Sens,2015,7(10):13233-13250.