Google Earth Engine支持下的江苏省夏收作物遥感提取

doi:10.12082/dqxxkx.2019.180420

地球信息科学学报 ›› 2019, Vol. 21 ›› Issue (5): 752-766.doi: 10.12082/dqxxkx.2019.180420

Google Earth Engine支持下的江苏省夏收作物遥感提取

何昭欣^1,²(), 张淼¹, 吴炳方^1,^2,^*(), 邢强¹

1. 中国科学院遥感与数字地球研究所遥感科学国家重点实验室,北京 100101
2. 中国科学院大学,北京 100049

收稿日期:2018-08-29 修回日期:2019-01-11 出版日期:2019-05-25 发布日期:2019-05-25
作者简介:
作者简介：何昭欣(1991-),男,山东莒县人,硕士,主要从事农作物与果园遥感分类研究。E-mail: hezx@radi.ac.cn
基金资助:
国家重点研发计划项目(2016YFD0300608);中国科学院科技服务网络计划（STS计划）项目（KFJ-STS-ZDTP-009）;国家自然科学基金项目（41561144013、41861144019、41701496）

Extraction of Summer Crop in Jiangsu based on Google Earth Engine

Zhaoxin HE^1,²(), Miao ZHANG¹, Bingfang WU^1,^2,^*(), Qiang XING¹

1. State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2018-08-29 Revised:2019-01-11 Online:2019-05-25 Published:2019-05-25
Contact: Bingfang WU
Supported by:
National Key R&D Program of China, No.2016YFD0300608;Science and Technology Service Network Initiative (STS), No.KFJ-STS-ZDTP-009;National Natural Science Foundation of China, No. 41561144013, 41861144019, 41701496.

摘要/Abstract

摘要：

江苏省是农作物种植大省,国家统计局统计数据显示,江苏省近10年冬小麦、冬油菜的总播种面积分列全国第五、第七,快速准确地获取冬小麦和冬油菜的空间分布对于该省的农业发展具有重意义。基于单机的传统遥感分类能够准确获取农作物的空间分布信息,但是耗时较长。随着地理大数据与云平台、云计算的发展,Google Earth Engine（GEE）作为一个基于云平台的全球尺度地理空间分析平台,为快速遥感分类带来了新的机遇。本文基于GEE,使用Sentinel-2数据快速提取了江苏省2017年冬小麦与冬油菜的空间分布。首先,利用GEE获得覆盖江苏省119景无云质优的Sentinel-2影像;其次,在此基础上分别计算了遥感指数、纹理特征、地形特征,并完成原始特征的构建与优化;最后,分别试验了朴素贝叶斯、支持向量机、分类回归树和随机森林4种分类器,比较了各分类器的分类精度,并提取了冬小麦与冬油菜的空间分布信息。得出以下结论：①GEE能够快速完成覆盖江苏省影像数据的去云、镶嵌、裁剪及特征构建等预处理,较本地处理具有明显优势;②J-M距离值位于前两位且大于1将特征数量从28个压缩到11个,有效压缩了原始特征空间;③光谱+纹理+地形特征组合训练,朴素贝叶斯、支持向量机、分类回归树、随机森林的平均验证精度分别为61%、87%、89%、92%。

关键词: GEE云平台, Sentinel-2, 特征优选, 作物识别, 江苏省

Abstract:

Jiangsu province, with 13 municipalities and located in the east of China, is an important part of the Yangtze river delta economy belt. The temperature is appropriate and the rainfall is moderate. Jiangsu province enjoys a moderate climate, which is suitable for the agricultural development. Winter wheat is distributed throughout the whole province, whereas the planting structure of winter rapeseed is complex and mainly scattered in Southern Jiangsu. As reported by the State Statistics Bureau, the total planting area of winter wheat and winter rapeseed in Jiangsu ranked the fifth and seventh in China, respectively, during the last 10 years. Fast obtaining the precise planting area of these two crops in Jiangsu is crucial for the agricultural development. Remote sensing classification based on local host can obtain spatial distribution of crops with high accuracy, but is time-consuming. With the development of geographical big data, cloud platform, and cloud computation, the Google Earth Engine (GEE), a global scale geospatial analysis platform based on the cloud platform, has brought new opportunities for rapid remote sensing classification. Based on the GEE cloud platform, a time-saving method of obtaining the spatial distribution of winter wheat and winter rapeseed by use of sentinel-2 data in Jiangsu was proposed. First, 119 sentinel-2 images without cloud were obtained using the GEE in Jiangsu. The time interval was set from March 1 to June 1, 2017, and the space area was Jiangsu province. Based on the spatio-temporal information, the 119 remote sensing images were mosaicked and clipped. Secondly, remote sensing indices, texture, and terrain features were calculated respectively, and the original features were extracted. The original feature space was optimized by an algorithm named Separability and Thresholds (SEaTH algorithm). Finally, four classifiers including naive Bayes, support vector machine, classification regression tree, and random forest were tested and evaluated by the average assessment accuracy. The spatial distribution information of winter wheat and winter rapeseed were obtained quickly. The following conclusions are drawn: (1) the GEE can quickly complete pre-processing of cloud-masking, image-mosaicking, image-clipping, and feature extraction, which is superior to the local processing. (2) The distance values of J-M that are higher than 1 and rank top two highest can reduce the number of features from 28 to 11 and effectively compress the original feature space. (3) With the combined training of spectral, texture and terrain features, the average assessment accuracy of naive Bayes, support vector machine, classification regression tree, and random forest was 61%, 87%, 89% and 92%, respectively.

Key words: GEE cloud platform, Sentinel-2, feature optimization, crop identification, Jiangsu Province

何昭欣, 张淼, 吴炳方, 邢强. Google Earth Engine支持下的江苏省夏收作物遥感提取[J]. 地球信息科学学报, 2019, 21(5): 752-766.DOI:10.12082/dqxxkx.2019.180420

Zhaoxin HE, Miao ZHANG, Bingfang WU, Qiang XING. Extraction of Summer Crop in Jiangsu based on Google Earth Engine[J]. Journal of Geo-information Science, 2019, 21(5): 752-766.DOI:10.12082/dqxxkx.2019.180420

图/表 17

图1

表1

表2

图2

表3

J-M距离

	0-1	0-2	0-3	0-4	1-2	1-3	1-4	2-3	2-4	3-4
B1	0.2680	0.1899	0.3451	0.8664	0.3541	0.2860	0.9974	0.0699	0.4645	0.5532
B10	0.1086	0.0510	0.2655	0.4685	0.2786	0.2367	0.7439	0.4025	0.3023	0.6612
B11	0.0345	0.2059	1.7859	0.8597	0.3667	1.7725	0.9742	1.7906	0.5136	1.5788
B12	0.0986	0.1134	0.9006	1.0067	0.3045	1.1916	1.2127	1.2405	0.8051	1.4930
B2	0.4440	0.1323	0.4348	1.0042	0.4218	0.4415	1.1720	0.1188	0.7053	0.6220
B3	0.5995	0.1026	0.2994	0.8887	0.2938	0.1648	0.7916	0.0623	0.6161	0.4861
B4	0.1689	0.0809	0.1894	1.1174	0.0806	0.0721	1.0340	0.0265	0.8892	0.8105
B5	0.8843	0.1368	0.0526	0.8874	0.4293	1.1382	0.8545	0.2567	0.5771	0.9491
B6	0.3152	0.2685	1.9948	0.4921	0.5103	1.9985	0.6967	1.6821	0.0608	1.3003
B7	0.0068	0.4568	1.9962	0.8542	0.4653	1.9980	0.8656	1.6988	0.1047	1.3183
B8	0.0303	0.3785	1.9981	0.8838	0.5434	1.9999	1.0667	1.7931	0.1511	1.4576
B8A	0.0126	0.4349	1.9984	0.9105	0.4010	1.9989	0.8751	1.8037	0.1397	1.4569
B9	0.4272	0.6179	1.9324	0.6222	0.0246	1.5326	0.0662	1.3821	0.0265	1.1396
EVI	0.0890	0.4287	1.9808	1.9302	0.4344	1.9970	1.9851	1.8262	1.5374	0.8268
LSWI	0.0513	0.4662	0.0249	1.7987	0.7753	0.1316	1.9234	0.3106	1.2424	1.6268
NDBI	0.0513	0.4662	0.0249	1.7987	0.7753	0.1316	1.9234	0.3106	1.2424	1.6268
NDVI	0.1701	0.2972	1.9492	1.9432	0.3385	1.9726	1.9892	1.7693	1.6042	0.8157
NDWI	0.3376	0.4312	1.9838	1.6811	0.4369	1.9919	1.7671	1.9134	1.0092	1.4172
B8_asm	0.0750	0.0302	1.4439	0.0103	0.1730	1.5201	0.1250	1.3745	0.0055	1.4037
B8_contrast	0.8985	0.3195	0.2373	0.5606	0.3501	0.4561	0.1051	0.0777	0.1247	0.1443
B8_corr	0.1056	0.0312	0.1653	0.0426	0.1877	0.3961	0.2288	0.0639	0.0040	0.0458
B8_ent	0.0552	0.0296	1.1539	0.0099	0.1488	1.2592	0.1035	1.0524	0.0054	1.0964
B8_idm	0.1398	0.0183	1.0954	0.0127	0.1780	1.2619	0.1310	1.0107	0.0045	1.0511
B8_var	0.8535	0.3683	0.3689	0.6562	0.2288	0.2918	0.0621	0.0559	0.1381	0.1123
aspect	0.0047	0.0084	0.1336	0.0136	0.0142	0.1159	0.0316	0.2022	0.0317	0.1383
elevation	0.1988	0.7377	0.0249	0.0298	1.0175	0.2476	0.3239	0.6190	0.5991	0.0141
hillshade	0.0098	0.4100	0.0847	0.1292	0.4665	0.1360	0.1714	0.1881	0.1197	0.0228
slope	0.0095	0.8064	0.3598	0.1896	0.8690	0.4255	0.2569	0.2386	0.4186	0.0585

表3

表4

表5

表6

不同特征、不同分类器组合的平均验证精度分布

分类器		特征
分类器		光谱	纹理	地形	光谱+纹理	光谱+地形	纹理+地形	光谱+纹理+地形
朴素贝叶斯	0	0.49	0.37	0.21	0.49	0.59	0.29	0.59
	1	0.50	0.21	0.21	0.50	0.60	0.21	0.60
	2	0.51	0.21	0.21	0.51	0.61	0.21	0.65
	3	0.51	0.20	0.20	0.51	0.60	0.20	0.60
	4	0.49	0.21	0.21	0.49	0.60	0.21	0.60
	5	0.49	0.21	0.21	0.49	0.59	0.21	0.65
	6	0.51	0.21	0.21	0.51	0.60	0.21	0.61
	7	0.49	0.21	0.21	0.49	0.58	0.21	0.60
	8	0.50	0.19	0.19	0.50	0.61	0.19	0.61
	9	0.50	0.20	0.20	0.50	0.58	0.20	0.58
均值		0.50	0.22	0.21	0.51	0.60	0.21	0.61
支持向量机	0	0.85	0.23	0.38	0.86	0.85	0.38	0.86
	1	0.87	0.21	0.38	0.87	0.84	0.37	0.87
	2	0.86	0.21	0.40	0.88	0.88	0.41	0.88
	3	0.85	0.20	0.42	0.85	0.86	0.41	0.86
	4	0.84	0.21	0.41	0.86	0.85	0.41	0.86
	5	0.85	0.21	0.40	0.87	0.86	0.38	0.89
	6	0.86	0.21	0.40	0.88	0.85	0.38	0.89
	7	0.85	0.21	0.38	0.84	0.84	0.40	0.86
	8	0.85	0.19	0.38	0.85	0.87	0.37	0.84
	9	0.86	0.20	0.40	0.88	0.85	0.40	0.88
均值		0.85	0.21	0.39	0.86	0.86	0.39	0.87
分类回归树	0	0.82	0.39	0.38	0.82	0.89	0.47	0.89
	1	0.84	0.40	0.37	0.84	0.86	0.49	0.88
	2	0.86	0.41	0.39	0.85	0.90	0.48	0.91
	3	0.82	0.40	0.40	0.82	0.88	0.51	0.91
	4	0.84	0.41	0.39	0.83	0.88	0.51	0.89
	5	0.84	0.39	0.40	0.86	0.88	0.48	0.90
分类器		特征
分类器		光谱	纹理	地形	光谱+纹理	光谱+地形	纹理+地形	光谱+纹理+地形
分类回归树	6	0.84	0.39	0.38	0.84	0.86	0.49	0.86
	7	0.83	0.39	0.37	0.84	0.88	0.49	0.89
	8	0.82	0.37	0.38	0.82	0.87	0.50	0.87
	9	0.84	0.41	0.40	0.85	0.87	0.50	0.88
均值		0.83	0.40	0.39	0.84	0.88	0.49	0.89
随机森林	0	0.87	0.39	0.37	0.87	0.90	0.51	0.90
	1	0.88	0.40	0.38	0.89	0.91	0.55	0.92
	2	0.89	0.39	0.40	0.89	0.93	0.54	0.93
	3	0.88	0.39	0.39	0.89	0.90	0.52	0.91
	4	0.88	0.41	0.39	0.88	0.89	0.54	0.90
	5	0.90	0.43	0.38	0.90	0.91	0.53	0.92
	6	0.87	0.41	0.37	0.88	0.90	0.52	0.91
	7	0.88	0.39	0.46	0.88	0.91	0.55	0.92
	8	0.86	0.41	0.37	0.88	0.89	0.54	0.92
	9	0.88	0.37	0.38	0.88	0.90	0.52	0.91
均值		0.88	0.40	0.39	0.89	0.90	0.53	0.92
分类器		特征
分类器		光谱	纹理	地形	光谱+纹理	光谱+地形	纹理+地形	光谱+纹理+地形
分类回归树	6	0.84	0.39	0.38	0.84	0.86	0.49	0.86
	7	0.83	0.39	0.37	0.84	0.88	0.49	0.89
	8	0.82	0.37	0.38	0.82	0.87	0.50	0.87
	9	0.84	0.41	0.40	0.85	0.87	0.50	0.88
均值		0.83	0.40	0.39	0.84	0.88	0.49	0.89
随机森林	0	0.87	0.39	0.37	0.87	0.90	0.51	0.90
	1	0.88	0.40	0.38	0.89	0.91	0.55	0.92
	2	0.89	0.39	0.40	0.89	0.93	0.54	0.93
	3	0.88	0.39	0.39	0.89	0.90	0.52	0.91
	4	0.88	0.41	0.39	0.88	0.89	0.54	0.90
	5	0.90	0.43	0.38	0.90	0.91	0.53	0.92
	6	0.87	0.41	0.37	0.88	0.90	0.52	0.91
	7	0.88	0.39	0.46	0.88	0.91	0.55	0.92
	8	0.86	0.41	0.37	0.88	0.89	0.54	0.92
	9	0.88	0.37	0.38	0.88	0.90	0.52	0.91
均值		0.88	0.40	0.39	0.89	0.90	0.53	0.92

表6

图3

图4

表7

图5

图6

图7

图8

图9

图10

参考文献 47

[1]	国家统计局.分省年度数据,2008-2017[EB/OL]..
	[ State Statistics Bureau. Provincial annual data, 2008-2017[EB/OL]. . ]
[2]	郭交,朱琳,靳标.基于Sentinel-1和Sentinel-2数据融合的农作物分类[J].农业机械学报,2018,49(4):192-198. doi: 10.6041/j.issn.1000-1298.2018.04.022
	[ Guo J, Zhu L, Jin B.Crop classification based on data fusion of Sentinel-1 and Sentinel-2[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018,49(4):192-198. ] doi: 10.6041/j.issn.1000-1298.2018.04.022
[3]	史飞飞,高小红,杨灵玉,等.基于HJ-1A高光谱遥感数据的湟水流域典型农作物分类研究[J].遥感技术与应用,2017,32(2):206-217.
	[ Shi F F, Gao X H, Yang L Y, et al.Research on typical crop classification based on HJ-1A hyperspectral data in the Huangshui river basin[J]. Remote Sensing Technology & Application, 2017,32(2):206-217. ]
[4]	班松涛. 县域农作物分类类型遥感识别与提取[D].西安:西北农林科技大学,2014.
	[ Ban S T.Remote sensing identification and extraction of county crop classification types[D]. Xi'an: Northwest A&F University, 2014. ]
[5]	程彬. 基于支持向量机的乾安县土地利用遥感分类研究[J].长春师范大学学报,2017,36(12):86-88.
	[ Cheng B.Land use information extraction based on support vector machine using multitemporal remote sensing in Qian'an county[J]. Journal of Changchun Normal University, 2017,36(12):86-88. ]
[6]	关舒婧,韩鹏鹏,王月如,等.华南地区典型种植园地遥感分类研究[J].地球信息科学学报,2017,19(11):1538-1546. doi: 10.3724/SP.J.1047.2017.01538
	[ Guan S J, Han P P, Wang Y R, et al.Study on the classification of typical plantations in south China[J]. Journal of Geo-information Science, 2017,19(11):1538-1546. ] doi: 10.3724/SP.J.1047.2017.01538
[7]	张静,张翔,田龙,等.西北旱区遥感影像分类的支持向量机法[J].测绘科学,2017,42(1):49-52.
	[ Zhang J, Zhang X, Tian L, et al.The support vector machine method for RS images' classification in northwest arid area[J]. Science of Surveying and Mapping, 2017,42(1):49-52. ]
[8]	杨屹鹍,蒋平安,武红旗,等.基于高分一号与Landsat 8卫星影像的库尔勒市香梨种植面积识别研究[J].山东农业科学,2018,50(1):153-157.
	[ Yang Y K, Jiang P A, Wu H Q, et al.Recognition research of Korla fragrant pear planting area based on satellite images of GF-1 and Landsat 8[J]. Shandong Agricultural Sciences, 2018,50(1):153-157. ]
[9]	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.
[10]	Dong J, Xiao X, Menarguez MA, et al.Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, phenology-based algorithm and google earth engine[J]. Remote Sensing of Environment, 2016,185:142-154.
[11]	徐晗泽宇,刘冲,王军邦,等. Google Earth Engine平台支持下的赣南柑橘果园遥感提取研究[J].地球信息科学学报, 2018,20(3):396-404.
	[ Xu H Z Y, Liu C, Wang J B, et al. Study on extraction of citrus orchard in Gannan region based on google earth engine platform[J]. Journal of Geo-Information Science, 2018,20(3):396-404. ]
[12]	Shelestov A, Lavreniuk M, Kussul N, et al.Exploring google earth engine platform for big data processing: classification of multi-temporal satellite imagery for cop mapping[J]. Frontiers in Earth Science, 2017,5(5):1-10. doi: 10.3389/feart.2017.00017
[13]	胡云锋,商令杰,王召海,等.GEE平台和CART方法的北京市土地解译[J].测绘科学,2018,43(4):87-93.
	[ Hu Y F, Shang L J, Wang Z H, et al.Land-cover and land-use classification in Beijing based on cart and gee[J]. Science of Surveying and Mapping, 2018,43(4):87-93. ]
[14]	Xiong J, Thenkabail P S, Gumma M K, et al.Automated cropland mapping of continental Africa using google earth engine cloud computing[J]. Isprs Journal of Photogrammetry & Remote Sensing, 2017,126:225-244. doi: 10.1016/j.isprsjprs.2017.01.019
[15]	王松林. 基于多源遥感的江苏省油菜及其同物候期主要作物面积提取[D].武汉:长江大学,2015.
	[ Wang S L.Extraction of main crop areas in rapeseed and its phenological period in Jiangsu province based on multi-source remote sensing[D]. Wuhan: Yangtze University, 2015. ]
[16]	Farr T G, Rosen P A, Caro E, et al.The shuttle radar topography mission[J]. Reviews of Geophysics, 2007,45(2):361.
[17]	贾坤,李强子.农作物遥感分类特征变量选择研究现状与展望[J].资源科学,2013,35(12):2507-2516.
	[ Jia K, Li Q Z.Review of features selection in crop classification using remote sensing data[J]. Resources Science, 2013,35(12):2507-2516. ]
[18]	Yang X, Zhao S, Qin X, et al.Mapping of urban surface water bodies from Sentinel-2 msi imagery at 10 m resolution via ndwi-based image sharpening[J]. Remote Sensing, 2017,9(6):596-614.
[19]	Li K, Chen Y.A genetic algorithm-based urban cluster automatic threshold method by combining viirs dnb, ndvi, and ndbi to monitor urbanization[J]. Remote Sensing, 2018,10(2):277-297.
[20]	裴欢,孙天娇,王晓妍.基于Landsat 8 OLI影像纹理特征的面向对象土地利用/覆盖分类[J].农业工程学报,2018,34(2):248-255.
	[ Pei H, Sun T J, Wang X Y.Object-oriented land use/cover classification based on texture features of Landsat 8 OLI image[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018,34(2):248-255. ]
[21]	张博.基于灰度共生矩阵的遥感影像纹理特征提取分析[J].城市地理,2017(22):190-200.
	[ Zhang B.Texture feature extraction analysis of remote sensing image based on gray level co-occurrence matrix[J]. Cultural Geography, 2017(22):190-200. ]
[22]	林雪,彭道黎,黄国胜,等.结合多尺度纹理特征的遥感影像面向对象分类[J].测绘工程,2016,25(7):22-27.
	[ Lin X, Peng D L, Huang G S, et al.Object-oriented classification with multi-scale texture feature based on remote sensing image[J]. Engineering of Surveying and Mapping, 2016,25(7):22-27. ]
[23]	Haralick R M, Shanmugam K, Dinstein I.Textural features for image classification[J]. IEEE Transactions on systems, man, and cybernetics, 1973,3(6):610-621.
[24]	方天红,陈庆虎,鄢煜尘,等.基于统计纹理特征的打印文档认证[J].武汉大学学报(工学版),2016,49(1):154-160.
	[ Fang T H, Chen Q H, Yan Y C.et al.Print document identification based on statistical texture feature[J]. Engineering Journal of Wuhan University, 2016,49(1):154-160. ]
[25]	冯建辉,杨玉静.基于灰度共生矩阵提取纹理特征图像的研究[J].北京测绘,2007,84(3):19-22.
	[ Feng J H, Yang Y J.Study of texture images extraction based on gray level co-occurrence matrix[J]. Beijing Surveying and Mapping, 2007,84(3):19-22. ]
[26]	焦蓬蓬,郭依正,刘丽娟,等.灰度共生矩阵纹理特征提取的Matlab实现[J].计算机技术与发展,2012,22(11):169-171.
	[ Jiao P P, Guo Y Z, Liu L J, et al.Implementation of gray level co-occurrence matrix texture feature extraction using matlab[J]. Computer Technology and Development, 2012,22(11):169-171. ]
[27]	张秀英,冯学智,江洪.面向对象分类的特征空间优化[J].遥感学报,2009,13(4):659-669.
	[ Zhang X Y, Feng X Z, Jiang H.Feature set optimization in object-oriented methodology[J]. Journal of Remote Sensing, 2009,13(4):659-669. ]
[28]	De Sa J P M. Pattern recognition: Concepts, methods and applications[M]. Berlin: Springer Science & Business Media, 2012.
[29]	Nussbaum S, Niemeyer I, Canty M J.Seath-a new tool for automated feature extraction in the context of object-based image analysis[C]//1st International Conference on Object-based Image Analysis, Salzburg: Austria. 2006.
[30]	余晓敏,湛飞并,廖明生,等.利用改进SEaTH算法的面向对象分类特征选择方法[J].武汉大学学报·信息科学版,2012,37(8):921-924.
	[ Yu X M, Zhan F B, Liao M S, et al.Object-oriented feature selection algorithms based on improved Seath algorithms[J]. Geomatics and Information Science of Wuhan University, 2012,37(8):921-924. ]
[31]	Bruzzone L.An approach to feature selection and classification of remote sensing images based on the bayes rule for minimum cost[J]. IEEE Transactions on Geoscience & Remote Sensing, 2000,38(1):429-438.
[32]	Yang J, Ye Z, Zhang X, et al.Attribute weighted naive bayes for remote sensing image classification based on cuckoo search algorithm[C]//International Conference on Security, Pattern Analysis, and Cybernetics. IEEE, 2017:169-174.
[33]	Breiman L, Friedman J H, Olshen R, et al.Classification and regression trees[J]. Encyclopedia of Ecology, 1984,40(3):582-588.
[34]	Bittencourt H R, Clarke R T.Use of classification and regression trees (cart) to classify remotely-sensed digital images[C]//Geoscience and Remote Sensing Symposium, 2003. Igarss '03. Proceedings. 2003 IEEE International. IEEE, 2003,6:3751-3753.
[35]	Zhou W, Song Y Q, Pan Z K, et al.Classification of urban construction land with worldview-2 remote sensing image based on classification and regression tree algorithm[C]// Computational Science and Engineering (CSE) and Embedded and Ubiquitous Computing (EUC), 2017 IEEE International Conference on. IEEE, 2017,2:277-283.
[36]	Mallet C, Bretar F, Roux M, et al.Relevance assessment of full-waveform lidar data for urban area classification[J]. Isprs Journal of Photogrammetry & Remote Sensing, 2011,66(6):S71-S84.
[37]	Gulnaz A, Sun T L, Liang Y, et al.A new technique for remote sensing image classification based on combinatorial algorithm of svm and knn[J]. International Journal of Pattern Recognition & Artificial Intelligence, 2018,32(7):1-23.
[38]	Breiman L.Random forests[J]. Machine Learning, 2001,45(1):5-32.
[39]	Feng Q, Liu J, Gong J.Uav remote sensing for urban vegetation mapping using random forest and texture analysis[J]. Remote Sensing, 2015,7(1):1074-1094.
[40]	马玥,姜琦刚,孟治国,等.基于随机森林算法的农耕区土地利用分类研究[J].农业机械学报,2016,47(1):297-303.
	[ Ma Y, Jiang Q G, Meng Z G, et al.Classification of land use in farming area based on random forest algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016,47(1):297-303. ]
[41]	Rodriguez-galiano V F, Chica-olmo M, Abarca-hernandez F, et al. Random forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture[J]. Remote Sensing of Environment, 2012,121(138):93-107.
[42]	侯西勇,邸向红,侯婉,等.中国海岸带土地利用遥感制图及精度评价[J].地球信息科学学报,2018,20(10):1478-1488.
	[ Hou X Y, Di X H, Hou W, et al.Accuracy evaluation of land use mapping using remote sensing techniques in coastal zone of China[J]. Journal of Geo-information Science, 2018,20(10):1478-1488. ]
[43]	Huang D, Xu S, Sun J, et al.Accuracy assessment model for classification result of remote sensing image based on spatial sampling[J]. Journal of Applied Remote Sensing, 2017,11(4):1-13.
[44]	Melville B, Lucieer A, Aryal J.Object-based random forest classification of Landsat etm+ and Worldview-2 satellite imagery for mapping lowland native grassland communities in Tasmania, Australia[J]. International Journal of Applied Earth Observation & Geoinformation, 2018,66:46-55.
[45]	杨文杰. 基于Landsat 8生长时序遥感信息的玉米干旱监测研究[D].石河子:石河子大学,2017.
	[ Yang W J.Maize drought monitoring based on Landsat 8 growth time series remote sensing information[D]. Shihezi: Shihezi University, 2017. ]
[46]	陈威. 基于Hadoop的K-means遥感影像分类算法的研究[D].赣州:江西理工大学,2017.
	[ Chen W.Research on k-means remote sensing image classification algorithm based on hadoop[D]. Ganzhou: Jiangxi University of Science and Technology, 2017. ]
[47]	乌兰,乌兰吐雅,包珺玮.基于Landsat 8 OLI影像的大兴安岭西麓春小麦识别方法的比较研究[J].北方农业学报,2017,45(2):109-112.
	[ Wu L, Wu L T Y, Bao J W. Study on comparison of identification methods for spring wheat at Great Khingan western slope based on Landsat 8 OLI[J]. Journal of Northern Agriculture, 2017,45(2):109-112. ]

地类代码	地类名称	样本数量/个
0	冬小麦	615
1	冬油菜	546
2	其他植被	610
3	水体	653
4	人工地表	666
总计		3090

特征种类	原始特征	数量/个	优化后特征	数量/个
光谱特征	B1、B2、B3、B4、B5、B6、B7、B8、B8A、B9、B10、B11、B12、EVI、LSWI、NDBI、NDVI、NDWI	18	B8、B8A、EVI、LSWI、NDBI、NDVI、NDWI	7
纹理特征	B8_asm、B8_contrast、B8_corr、B8_var、B8_idm、B8_ent	6	B8_asm、B8_idm、B8_ent	3
地形特征	elevation、slope、aspect、hillshade	4	elevation	1
总计		28		11

Google Earth Engine支持下的江苏省夏收作物遥感提取

Extraction of Summer Crop in Jiangsu based on Google Earth Engine

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 47

相关文章 15

Metrics

本文评价

推荐阅读 0

序号	波段名称	中心波长/nm	空间分辨率/m	属性
01	B1	443	60	气溶胶
02	B2	490	10	蓝
03	B3	560	10	绿
04	B4	665	10	红
05	B5	705	20	红边1
06	B6	740	20	红边2
07	B7	783	20	红边3
08	B8	842	10	近红外
09	B8A	865	20	红边4
10	B9	940	60	水蒸气
11	B10	1375	60	卷云
12	B11	1610	20	短波红外1
13	B12	2190	20	短波红外2
14	QA10		10
15	QA20		20
16	QA60		60	云掩膜

分类器	参数
朴素贝叶斯	Lambda：0.000 000 1
支持向量机	kernelType：RBF; gamma：0.5; cost：50
分类回归树	crossvalidationFactor：10; maxDepth：10
随机森林	NumberOfTrees：200; variablesPerSplit：0

混淆矩阵		真实类别
混淆矩阵		冬小麦	冬油菜	其他植被	水体	人工地表	总计	用户精度
预测类别	冬小麦	155	7	2	0	1	165	0.94
	冬油菜	10	160	2	0	0	172	0.93
	其他植被	18	3	168	0	1	190	0.88
	水体	2	0	0	203	4	209	0.97
	人工地表	2	1	8	1	192	204	0.94
	总计	187	171	180	204	198	940
	制图精度	0.83	0.94	0.93	1.00	0.97
	总体精度	0.93
	Kappa系数	0.92

[1]	袁浩, 姬翠翠, 杨雪梅, 陈茂霖, 潘建平, 曹一鸣. 结合Sentinel-2数据与光谱特征的稀疏非光合植被指数构建[J]. 地球信息科学学报, 2023, 25(9): 1894-1907.
[2]	杨颖频, 吴志峰, 黄启厅, 骆剑承, 吴田军, 董文, 胡晓东, 肖文菊. 协同遥感与统计数据的粤西甘蔗种植分布提取及时空分析[J]. 地球信息科学学报, 2023, 25(5): 1012-1026.
[3]	段艳慧, 赵学胜, 彭舒. 基于信息熵的GlobeLand 30和WorldCover耕地破碎区一致性分析[J]. 地球信息科学学报, 2023, 25(5): 1027-1036.
[4]	于方圆, 曹家玮, 李发源, 李思进. 顾及对象特征的地面式光伏电站提取及减碳效益评估[J]. 地球信息科学学报, 2023, 25(3): 529-545.
[5]	秦肖伟, 程博, 杨志平, 李林, 董文, 张新, 杨树文, 靳宗义, 薛庆. 基于时序遥感影像的西南山区地块尺度作物类型识别[J]. 地球信息科学学报, 2023, 25(3): 654-668.
[6]	尹雄, 陈帮乾, 古晓威, 云挺, 吴志祥, 陈岳, 赖虹燕, 寇卫利. 基于GEE平台LandTrendr算法的海南岛森林扰动快速监测方法及分析[J]. 地球信息科学学报, 2023, 25(10): 2093-2106.
[7]	聂祥琴, 陈瀚阅, 牛铮, 张黎明, 刘炜, 邢世和, 范协裕, 李家国. 基于时序影像的农业活动因子提取与闽西耕地SOC数字制图[J]. 地球信息科学学报, 2022, 24(9): 1835-1852.
[8]	杨泽航, 王文, 鲍健雄. 融合多源遥感数据的黑河中游地区生长季早期作物识别[J]. 地球信息科学学报, 2022, 24(5): 996-1008.
[9]	舒弥, 杜世宏. 国土调查遥感40年进展与挑战[J]. 地球信息科学学报, 2022, 24(4): 597-616.
[10]	陈点点, 陈芸芝, 冯险峰, 武爽. 基于超参数优化CatBoost算法的河流悬浮物浓度遥感反演[J]. 地球信息科学学报, 2022, 24(4): 780-791.
[11]	王紫薇, 蔡红艳, 陈慕琳. 基于大数据的化工企业时空变化特征及其对水域的潜在影响分析方法[J]. 地球信息科学学报, 2022, 24(4): 673-683.
[12]	章敏, 吴文挺, 汪小钦, 孙玉. 基于潮汐动态淹没过程的长江口潮滩地形信息反演研究[J]. 地球信息科学学报, 2022, 24(3): 583-596.
[13]	熊皓丽, 周小成, 汪小钦, 崔雅君. 基于GEE云平台的福建省10 m分辨率茶园专题空间分布制图[J]. 地球信息科学学报, 2021, 23(7): 1325-1337.
[14]	陈赛楠, 蒋弥. Sentinel-1 SAR在洪水范围提取与极化分析中的应用研究[J]. 地球信息科学学报, 2021, 23(6): 1063-1070.
[15]	刘戈, 姜小光, 唐伯惠. 特征优选与卷积神经网络在农作物精细分类中的应用研究[J]. 地球信息科学学报, 2021, 23(6): 1071-1081.