Please wait a minute...
 
Remote Sensing for Natural Resources    2024, Vol. 36 Issue (2) : 39-49     DOI: 10.6046/zrzyyg.2022413
|
A mapping methodology for wetland categories of the Yellow River Delta based on optimal feature selection and spatio-temporal fusion algorithm
FENG Qian1(), ZHANG Jiahua2,3(), DENG Fan1, WU Zhenjiang3, ZHAO Enling1, ZHENG Peixin1, HAN Yang1
1. School of Geosciences, Yangtze University, Wuhan 430100, China
2. CAS Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
3. College of Earth and Planetary Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
Download: PDF(9727 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

Exploring the remote sensing-based classification of coastal wetlands is significant for their conservation and planning. Hence, this study investigated the Yellow River Delta with the 8-view Landsat8 OIL images from March to October 2019 as the data source. It constructed seven classification schemes based on different features of the images on the Google Earth Engine (GEE) cloud platform. Then, it employed the random forest classifier to classify different feature sets, with the scheme exhibiting the best classification effects selected for mapping the wetland categories of the Yellow River Delta. Considering poor data quality in August and September due to cloud contamination, this study filled in the cloudy zones using the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) algorithm. The results show that: ① The predicted images generated from the ESTARFM manifested a high correlation with the real image bands, with R values above 0.73, suggesting that the reconstructed images could be used in this study; ② The random forest algorithm was used to classify the surface feature types in the study area. Through optimal feature selection, the classification results of Scheme 7 demonstrated an overall accuracy of 92.28%, higher than those of conventional schemes, with a Kappa coefficient of 0.91, aligning with the actual wetland conditions. The results of this study can assist in deeply understanding the spatial distributions of different wetlands in the area, and provide a scientific basis for the conservation and planning of the regional ecological environment.
Keywords Landsat8      multitemporal data      Yellow River Delta wetland      image fusion      Google Earth Engine      random forest     
ZTFLH:  TP753  
Issue Date: 14 June 2024
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Qian FENG
Jiahua ZHANG
Fan DENG
Zhenjiang WU
Enling ZHAO
Peixin ZHENG
Yang HAN
Cite this article:   
Qian FENG,Jiahua ZHANG,Fan DENG, et al. A mapping methodology for wetland categories of the Yellow River Delta based on optimal feature selection and spatio-temporal fusion algorithm[J]. Remote Sensing for Natural Resources, 2024, 36(2): 39-49.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2022413     OR     https://www.gtzyyg.com/EN/Y2024/V36/I2/39
Fig.1  Location and Landsat8 image of Yellow River Delta
影像编号 获取时间 云量/% 波段数① 影像质量
1 2019-03-14 <1% 6 良好
2 2019-04-15 <1% 6 良好
3 2019-05-01 <1% 6 良好
4 2019-06-02 <1% 6 良好
5 2019-07-20 <1% 6 良好
6 2019-08-21 约90% 6 差
7 2019-09-22 约95% 6 差
8 2019-10-24 <1% 6 良好
Tab.1  Image information of Landsat8 OIL
Landsat波段 波段宽度/nm 空间分辨率/m MOD09A1波段 波段宽度/nm 空间分辨率/m
B2蓝 450~510 30 B3 459~479 500
B3绿 530~590 30 B4 545~565 500
B4红 640~670 30 B1 620~670 500
B5近红外 850~880 30 B2 841~876 500
B6 SWIR1 1 570~1 650 30 B6 1 628~1 652 500
B7 SWIR2 2 110~2 290 30 B7 2 105~2 155 500
Tab.2  Spectral bands and resolutions of Landsat and MODIS
地物类别 浅海水域 泥质海滩 河流 草本沼泽 灌木沼泽 水库/坑塘 水田 盐田 建筑物 养殖池 农田
分类样
本数量		 33 927 1 086 2 275 471 595 3 652 2 974 249 1 822 844 793
验证样
本数量		 8 238 285 570 128 133 929 762 67 484 222 193
Tab.3  Figure sample point information
一级分类 二级分类 说明
近海与海岸湿地 浅海水域 低潮时水深<6 m的浅海水域,包括海湾海峡
泥质海滩 由淤泥质组成的植被覆盖度<30%的淤泥质海滩
河流湿地 河流 常年有水或间歇性有水流动的河流,包括河床部分
沼泽湿地 草本沼泽 以草本植物为主的永久或季节性咸淡水沼泽,喜湿多年生草本和禾本科植物占优势,研究区典型植被如芦苇、香蒲、盐地碱蓬、互花米草等
灌木沼泽 以灌木为主的永久性或季节性沼泽,如柽柳等
人工湿地 水库 /坑塘 包括水库、坑塘、养殖池以及城市景观和娱乐水面等人工建造的静止水体
水田 用于种植水稻田、水生作物的耕地,如水稻田、藕池
盐田 为获取盐业资源而修建的晒盐场所或盐池
Tab.4  Categories plan of wetlands in the Yellow River Delta
Fig.2  The flowchart of the experiment
特征类别 特征名称 特征描述/公式
光谱特征 波段(band) 蓝,绿,红,近红,中红1,中红2
植被/水体指数 归一化植被指数(normalized difference vegetation index,NDVI) R n i r - R r e d R n i r + R r e d
比值植被指数(ratio vegetation index,RVI) R n i r R r e d
差值植被指数(differential vegetation index,DVI) R n i r - R r e d
归一化水体指数(normalized difference water index,NDWI) R g r e e n - R n i r R g r e e n + R n i r
盐分/土壤指数 盐分指数 2(salinity index 2,SI2) R g r e e n 2 + R r e d 2 + R n i r 2 　
盐分指数 3(salinity index 3,SI3) R g r e e n 2 + R r e d 2 　
盐分指数(salinity index,SI-T) ( R r e d R n i r ) × 100
优化型土壤调节植被指数(soil adjusted vegetation index,SAVI) R n i r - R r e d R n i r + R r e d + 0.6
土壤亮度指数(soil brightness index,SBI) R r e d 2 + R n i r 2 　
K-T变换 亮度(brightness) 0.3029 R b l u e + 0.2786 R g r e e n + 0.4733 R r e d + 0.5599 R n i r + 0.5080 R s w i r l + 0.1872 R s w i r 2
绿度(greenness) - 0.2941 R b l u e - 0.2430 R g r e e n + 0.5424 R r e d + 0.7276 R n i r - 0.7170 R s w i r l - 0.1680 R s w i r 2
湿度(wetness) 0.1511 R b l u e + 0.1973 R g r e e n + 0.3283 R r e d + 0.3407 R n i r - 0.7117 R s w i r l - 0.4559 R s w i r 2
纹理特征 方差 (GLGM_Variance) ∑ i ∑ j p ( i , j ) × ( i - M e a n ) 2
对比度(GLGM_Contrast) ∑ i ∑ j p ( i , j ) × ( i - j ) 2
熵(GLGM_Entropy) ∑ i ∑ j p ( i , j ) × l n p ( i , j )
相关性(GLGM_Correlation) ∑ i ∑ j ( i - M e a n ) × ( j - M e a n ) p ( i , j ) 2 V a r i a n c e
二阶矩(GLGM_Second Moment) ∑ i ∑ j p ( i , j ) 2
Tab.5  Description of the feature set from Landsat8
方案 特征组合
方案1 多时相光谱特征
方案2 多时相光谱特征+多时相植被指数/水体指数
方案3 多时相光谱特征+多时相土壤指数/盐分指数
方案4 多时相光谱特征+多时相K-T变化特征
方案5 多时相光谱特征+多时相纹理特征
方案6 多时相光谱特征+多时相植被/水体指数+多时相盐分/土壤指数+多时相K-T变化特征+多时相纹理特征
方案7 特征优选组合
Tab.6  The information of experimental Programs
Fig.3  Original and predicted images and local maps of Landsat8
指数 日期 蓝 绿 红 近红 SWIR1 SWRI2 NDVI NDWI SAVI SI2 SI3
相关系数R 8月21日 0.87 0.85 0.79 0.88 0.87 0.81 0.85 0.90 0.78 0.85 8.85
9月22日 0.77 0.79 0.73 0.81 0.79 0.73 0.78 0.80 0.84 0.79 0.79
Tab.7  Comparison of original Landsat8 OLI image with ESTARFM
Fig.4  The distribution of characteristic importance
Fig.5  The relation between the number of characteristic variables and the classification accuracy and the Kappa coefficient
月份 优选特征 特征数量
3月 Blue-3,SWIR1-3,NDVI-3,NDWI-3,RVI-3,GK-T-3,BK-T-3,WK-T-3,SI3-3,WL-COR-3 10
4月 WK-T-4,BK-T-4,GK-T-4,OSAVI-4,SBI-4,ST-T-4,WL-ENT-4,WL-SEC-4 8
5月 NIR-5,SWIR2-5,NDWI-5,SI2-5,OSAVI-5,GK-T-5,WK-T-5 7
6月 Green-6,GK-T-6,WL-SEC-6 3
7月 NDVI-7,DVI-7,SI3-7,OSAVI-7,SBI-7,SI2-7,GK-T-7,WL-COR-7,WL-ENT-7 9
8月 Green-8,SI2-8,SI3-8,WL-CON-8,WL-ENT-8,WL-VAR-8,WL-COR-8 7
9月 SI2-9 1
10月 DVI-10,NDWI-10,NDVI-10,SI2-10,BK-T-10,WL-SEC-10,WL-VAR-10,WL-ENT-10 8
Tab.8  Distribution list of optimal features
Fig.6  Classification results of different plans
类别 方案1 方案2 方案3 方案4 方案5 方案6 方案7
PA/% UA/% PA/% UA/% PA/% UA/% PA/% UA/% PA/% UA/% PA/% UA/% PA/% UA/%
浅海水域 95.94 97.35 99.15 96.41 98.31 94.13 99.54 98.35 99.36 97.13 97.50 96.86 99.12 94.88
泥质海滩 81.07 84.69 88.02 86.08 85.79 86.31 95.48 88.61 93.44 87.20 94.69 85.55 98.60 96.98
水库坑塘 80.85 70.03 75.16 81.01 79.07 80.73 83.16 88.91 75.16 85.68 77.06 90.21 83.67 90.33
河流 86.37 89.07 86.92 96.18 87.46 93.93 93.80 96.70 91.26 89.52 88.52 96.41 89.36 99.86
水田 91.89 89.52 93.30 89.51 94.28 85.79 94.84 90.83 90.03 94.42 90.87 92.17 96.86 90.02
农田 93.79 75.57 89.40 97.91 82.72 99.72 90.14 95.31 91.76 95.78 93.91 81.30 84.90 96.12
建筑用地 62.53 79.68 70.69 74.55 70.45 69.63 81.10 81.30 85.70 66.65 76.24 69.00 86.37 86.30
盐田 76.51 84.65 89.06 82.07 87.43 88.62 90.95 90.76 82.22 85.51 93.53 85.92 96.00 97.77
草本沼泽 54.71 73.11 84.28 57.51 74.05 59.39 74.83 77.93 66.87 70.95 83.54 72.93 87.74 86.33
灌木沼泽 64.30 81.72 70.51 82.77 63.36 86.17 70.76 89.77 74.43 84.23 53.84 83.50 71.49 70.85
总精度/% 85.11 89.05 87.39 91.90 90.01 88.89 92.28
Kappa系数 0.83 0.86 0.85 0.91 0.88 0.87 0.91
Tab.9  The statistics of classification accuracy
[1] 张晓龙, 李培英, 李萍, 等. 中国滨海湿地研究现状与展望[J]. 海洋科学进展, 2005, 23(1):87-95.
[1] Zhang X L, Li P Y, Li P, et al. Present conditions and prospects of Study on coastal wetlands in China[J]. Advances in Marine Science, 2005, 23(1):87-95.
[2] 刘润红, 梁士楚, 赵红艳, 等. 中国滨海湿地遥感研究进展[J]. 遥感技术与应用, 2017, 32(6):998-1011.
[2] Liu R H, Liang S C, Zhao H Y, et al. Progress of Chinese coastal wetland based on remote sensing[J]. Remote Sensing Technology and Application, 2017, 32(6):998-1011.
[3] 朱纹君, 韩美, 魏丹妮, 等. 黄河三角洲人地关系协调度时空演变及其驱动机制[J]. 水土保持研究, 2023, 30(1):388-396.
[3] Zhu W J, Han M, Wei D N, et al. Spatiotemporal evolution and driving mechanism of human-environment coordination in the Yellow River Delta[J]. Research of Soil and Water Conservation, 2023, 30(1):388-396.
[4] 刘海红, 刘胤序, 张春华, 等. 1991—2016年黄河三角洲湿地变化的遥感监测[J]. 地球与环境, 2018, 46(6):590-598.
[4] Liu H H, Liu Y X, Zhang C H, et al. Remote sensing monitoring of wetland changes in the Yellow River Delta during 1991-2016[J]. Earth and Environment, 2018, 46(6):590-598.
[5] 钟燕飞, 吴浩, 刘寅贺. 湿地遥感制图研究现状与展望[J]. 中国科学基金, 2022, 36(3):420-431.
[5] Zhong Y F, Wu H, Liu Y H. Research status and prospects of remote sensing for wetland mapping[J]. Bulletin of National Natural Science Foundation of China, 2022, 36(3):420-431.
[6] 祁欣. 基于机器学习的遥感数据处理方法综述[J]. 品牌与标准化, 2022(s1):148-150.
[6] Qi Y. Survey of Remote sensing data processing methods based on machine learning[J]. Brand & Standardization, 2022(s1):148-150.
[7] 刘春亭, 冯权泷, 金鼎坚, 等. 随机森林协同Sentinel-1/2的东营市不透水层信息提取[J]. 自然资源遥感, 2021, 33(3):253-261.doi:10.6046/zrzyyg.2020310.
[7] Liu C T, Feng Q L, Jin D J, et al. Application of random forest and Sentinel-1/2 in the information extraction of impervious layers in Dongying City[J]. Remote Sensing for Natural Resources, 2021, 33(3):253-261.doi:10.6046/zrzyyg.2020310.
[8] 黄佩, 普军伟, 赵巧巧, 等. 植被遥感信息提取方法研究进展及发展趋势[J]. 自然资源遥感, 2022, 34(2):10-19.doi:10.6046/zrzyyg.2021137.
[8] Huang P, Pu J W, Zhao Q Q, et al. Research progress and development trend of remote sensing information extraction methods of vegetation[J]. Remote Sensing for Natural Resources, 2022, 34(2):10-19.doi:10.6046/zrzyyg.2021137.
[9] Wu Z J, Zhang J H, Deng F, et al. Fusion of GF and MODIS data for regional-scale grassland community classification with EVI2 time-series and phenological features[J]. Remote Sensing, 2021, 13(5):835.
[10] 史飞飞, 高小红, 肖建设, 等. 基于集成学习和多时相遥感影像的枸杞种植区分类[J]. 自然资源遥感, 2022, 34(1):115-126.doi:10.6046/zrzyyg.2021064.
[10] Shi F F, Gao X H, Xiao J S, et al. Classification of wolfberry planting areas based on ensemble learning and multi-temporal remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(1):115-126.doi:10.6046/zrzyyg.2021064.
[11] 程筱茜, 洪友堂, 陈劲松, 等. 基于ESTARFM的内陆湖泊遥感动态变化监测[J]. 国土资源遥感, 2020, 32(3):183-190.doi:10.6064/zrzyyg.2020.03.24.
[11] Cheng X Q, Hong Y T, Chen J S, et al. A study of the long-term remote sensing dynamic monitoring of inland based on ESTARFM[J]. Remote Sensing for Land and Resources, 2020, 32(3):183-190.doi:10.6064/zrzyyg.2020.03.24.
[12] Gao F, Masek J, Schwaller M, et al. On the blending of the Landsat and MODIS surface reflectance: Predicting daily Landsat surface reflectance[J]. IEEE Transactions on Geoscience and Remote sensing, 2006, 44(8):2207-2218.
[13] Zhu X L, Chen J, Gao F, et al. An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions[J]. Remote Sensing of Environment, 2010, 114(11):2610-2623.
[14] 高瑞, 王志勇, 周晓东, 等. 利用多时相遥感监测与分析黄河三角洲湿地变化动态[J]. 测绘通报, 2021(4):22-27.
doi: 10.13474/j.cnki.11-2246.2021.0105
[14] Gao R, Wang Z Y, Zhou X D, et al. Monitoring and analysis of wetland change dynamics in the Yellow River Delta using multi-temporal remote sensing[J]. Bulletin of Surveying and Mapping, 2021(4):22-27.
doi: 10.13474/j.cnki.11-2246.2021.0105
[15] 程丽娜, 钟才荣, 李晓燕, 等. Sentinel-2密集时间序列数据和Google Earth Engine的潮间带湿地快速自动分类[J]. 遥感学报, 2022, 26(2):348-357.
[15] Cheng L N, Zhong C R, Li Xiao Yan, et al. Rapid and automatic classification of intertidal wetlands based on intensive time series Sentinel-2 images and Google Earth Engine[J]. National Remote Sensing Bulletin, 2022, 26(2):348-357.
[16] 张磊, 宫兆宁, 王启为, 等. Sentinel-2影像多特征优选的黄河三角洲湿地信息提取[J]. 遥感学报, 2019, 23(2):313-326.
[16] Zhang L, Gong Z N, Wang Q W, et al. Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images[J]. National Remote Sensing Bulletin, 2019, 23(2):313-326.
[17] 杨迎港, 刘培, 张合兵, 等. 基于特征优选随机森林算法的GF-2影像分类[J]. 航天返回与遥感, 2022, 43(2):115-126.
[17] Yang Y G, Liu P, Zhang H B, et al. Research on GF-2 image classification based on feature optimization random forest algorithm[J]. Spacecraft Recovery & Remote Sensing, 2022, 43(2):115-126.
[18] 朱琦, 郭华东, 张露. 基于多时相Landsat8 影像的海南岛热带天然林类型遥感分类[J]. 自然资源遥感, 2022, 34(2):215-223.doi:10.6046/zrzyyg.2021156.
[18] Zhu Q, Guo H D, Zhang L, et al. Classification of tropical natural forests in Hainan Island based on multi-temporal Landsat8 remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(2):215-223.doi:10.6046/zrzyyg.2021156.
[19] 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.
[20] 王渊, 赵宇豪, 吴健生. 基于Google Earth Engine云计算的城市群生态质量长时序动态监测——以粤港澳大湾区为例[J]. 生态学报, 2020, 40(23):8461-8473.
[20] Wang Y, Zhao Y H, Wu J S. Dynamic monitoring of long time series of ecological quality in urban agglomerations using Google Earth Engine cloud computing:A case study of the Guang dong-Hong Kong-Macao Greater Bay Area,China[J]. Acta Ecologica Sinica, 2020, 40(23):8461-8473.
[21] 徐振田, 张莎, 白雲, 等. 基于 Landsat 数据的黄河三角洲湿地提取及近 30 年动态研究[J]. 海洋湖沼通报, 2020(3):70-79.
[21] Xu Z T, Ail S, Zhang S, et al. Mapping the wetland in Yellow River Delta and its dynamics in recent 30 years based on Landsat data[J]. Transactions of Oceanology and Limnology, 2020(3):70-79.
[22] 牟晓杰, 刘兴土, 阎百兴, 等. 中国滨海湿地分类系统[J]. 湿地科学, 2015, 13(1):19-26.
[22] Mou X J, Liu X T, Yan B X, et al. Classification system of coastal wetlands in China[J]. Wetland Science, 2015, 13(1):19-26.
[23] Bradley A, Jackway P, Lovell B. Classification in scale-space:Applications to texture analysis[C]// Int.Conf.on Information Processing in Medical Imaging, 1995:375-376.
[24] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.
[1] ZHANG Haojie, YANG Lijuan, SHI Tingting, WANG Shuai. Derivation of tasseled cap transformation coefficients for GF-6 WFV sensor data[J]. Remote Sensing for Natural Resources, 2024, 36(2): 105-115.
[2] LIU Yongxin, ZHANG Siyuan, BIAN Peng, WANG Pijun, YUAN Shuai. Exploring the spatio-temporal evolution of land cover types in the Bayannur section of the Yellow River basin from 1989 to 2020[J]. Remote Sensing for Natural Resources, 2024, 36(2): 207-217.
[3] WEI Xin, REN Yu, CHEN Xidong, HU Qingfeng, LIU Hui, ZHOU Jing, SONG Dongwei, ZHANG Peipei, HUANG Zhiquan. Monitoring of dynamic changes in water bodies of Henan Province based on time-series Sentinel-2 data[J]. Remote Sensing for Natural Resources, 2024, 36(2): 268-278.
[4] XUE Zhiyong, TIAN Zhen, ZHU Jianhua, ZHAO Yang. Monitoring of inter-annual variations in mangrove forests in the Bamen Bay area based on Google Earth Engine[J]. Remote Sensing for Natural Resources, 2024, 36(2): 279-286.
[5] ZHAO Heting, LI Xiaojun, XU Xinyu, GAI Junfei. An ICM-based adaptive pansharpening algorithm for hyperspectral images[J]. Remote Sensing for Natural Resources, 2024, 36(2): 97-104.
[6] SONG Yingxu, ZOU Yujia, YE Runqing, HE Zhixia, WANG Ningtao. Dynamic analysis of landslide hazards in the Three Gorges Reservoir area based on Google Earth Engine[J]. Remote Sensing for Natural Resources, 2024, 36(1): 154-161.
[7] LIU Meiyan, NIE Sheng, WANG Cheng, XI Xiaohuan, CHENG Feng, FENG Baokun. Forest stock volume inversion based on ICESat-2 and Sentinel-2A data[J]. Remote Sensing for Natural Resources, 2024, 36(1): 210-216.
[8] LU Xianjian, ZHANG Huanling, YAN Hongbo, LI Zhenbao, GUO Ziyang. A method for sugarcane information extraction based on multi-feature optimal selection of Sentinel-1/2 image data[J]. Remote Sensing for Natural Resources, 2024, 36(1): 86-94.
[9] DU Xiaochuan, LOU Debo, XU Lingang, FAN Yinglin, ZHANG Lin, LI Wanyue. Extracting granite pegmatite information based on GF-2 images and the random forest algorithm[J]. Remote Sensing for Natural Resources, 2023, 35(4): 53-60.
[10] YU Shaohuai, XU Qiao, YU Fei. Method for assessing landslide susceptibility of highways in mountainous areas based on optical and SAR remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(4): 81-89.
[11] ZHONG Xiaoyong, LI Hongyi, GUO Dongyan, XIE Modian, ZHAO Wanru, HU Bifeng. Spatial distribution prediction of soil pH in arable land of Jiangxi Province based on multi-source environmental variables and the random forest model[J]. Remote Sensing for Natural Resources, 2023, 35(4): 178-185.
[12] HE Suling, HE Zenghong, PAN Jiya, WANG Jinliang. County-scale land use/land cover simulation based on multiple models[J]. Remote Sensing for Natural Resources, 2023, 35(4): 201-213.
[13] LI Guangzhe, WANG Hao, CAO Yinxuan, ZHANG Xiaoyu, NING Xiaogang. Spatio-temporal evolution and influencing factors of ecological environment quality in the Changsha-Zhuzhou-Xiangtan urban agglomeration[J]. Remote Sensing for Natural Resources, 2023, 35(4): 244-254.
[14] CHEN Jian, LI Hu, LIU Yufeng, CHANG Zhu, HAN Weijie, LIU Saisai. Crops identification based on Sentinel-2 data with multi-feature optimization[J]. Remote Sensing for Natural Resources, 2023, 35(4): 292-300.
[15] WU Weichao, YE Fawang. Cloud detection of Sentinel-2 images for multiple backgrounds[J]. Remote Sensing for Natural Resources, 2023, 35(3): 124-133.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech