基于RF分类调优和SNIC聚类的新疆红枣种植区遥感提取

doi:10.12118/j.issn.1000-6060.2023.382

Abstract

Abstract:

This study aims to efficiently extract the distribution information and planting area of jujube crops in Xinjiang, China, providing essential data support for predicting yield and price, consolidating poverty alleviation achievements, and aiding rural revitalization. Utilizing the Google Earth Engine cloud platform, this research accesses Sentinel-1 radar images, Sentinel-2 optical images, and SRTM terrain data covering Xinjiang. From these data, 44 features including spectral, textural, and terrain attributes are extracted, followed by a feature selection process. The optimized random forest classifier, after hyperparameter tuning, produces a spatial distribution map of Xinjiang’s jujube planting areas with a 10 m resolution for the year 2021. Superpixel clustering method further processes the major jujube planting areas to determine the exact planting extents. The findings are as follows: (1) Employing a simple non-iterative clustering algorithm for classification and post-processing, the identified jujube cultivated area in Xinjiang spans 4253 km², predominantly located in the southern regions of Aksu, Kashgar, Hotan Prefectures, and Bayingolin Mongol Autonomous Prefecture, as well as Turpan and Hami Cities in the east. (2) The accuracy of feature extraction is significantly enhanced through hyperparameter optimization of the random forest classifier, yielding an average overall classification accuracy of 0.86, a Kappa coefficient of 0.82, a producer accuracy for jujube extraction of 0.87, and a user accuracy of 0.80, as assessed via the confusion matrix. (3) Features from the Sentinel-1 polarization band are crucial for jujube information extraction, supplemented effectively by spectral and textural features. Leveraging multisource remote sensing data, this method facilitates rapid acquisition of distribution and area data for jujube planting in Xinjiang, markedly benefiting agricultural modernization, resource conservation, and regional economic development.

Key words: Google Earth Engine, Sentinel-1/2, jujube, feature optimization, random forest, super-pixel clustering

ZHAO Guobing, ZHENG Jianghua, WANG Lei, GAO Jian, LUO Lei, Nigela TUERXUN, HAN Wanqiang, GUAN Jingyun. Remote sensing extraction of jujube planting area in Xinjiang based on RF classification optimization and SNIC clustering[J].Arid Land Geography, 2024, 47(6): 1004-1014.

Figures/Tables 11

Fig. 1

Tab. 1

Tab. 2

Fig. 2

Tab. 3

Fig. 3

Tab. 4

Fig. 4

Fig. 5

Fig. 6

Tab. 5

References 29

[1]	Tiecheng B, Nannan Z, Mercatoris B, et al. Jujube yield prediction method combining Landsat 8 vegetation index and the phenological length[J]. Computers and Electronics in Agriculture, 2019, 162: 1011-1027. doi: 10.1016/j.compag.2019.05.035
[2]	徐翔燕, 侯瑞环, 牛荣. 基于GF-1号的红枣种植面积提取方法[J]. 塔里木大学学报, 2019, 31(3): 32-38.
	[Xu Xiangyan, Hou Ruihuan, Niu Rong. Extraction method of Chinese jujube planting area based on GF-1[J]. Journal of Tarim University, 2019, 31(3): 32-38.]
[3]	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. doi: 10.12082/dqxxkx.2018.170553
	[Xu Hanzeyu, Liu Chong, Wang Junbang, 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.]
[4]	乔海浪. 基于NDVI时间序列重构的经济型人工林时空分布信息提取研究[D]. 北京: 中国科学院大学(中国科学院遥感与数字地球研究所), 2017.
	[Qiao Hailang. The extraction of spatial and temperal information of economic man-made forests based on NDVI time series[D]. Beijing: University of Chinese Academy of Sciences (Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences), 2017.]
[5]	Li R, Fang P, Xu W, et al. Classifying forest types over a mountainous area in southwest China with Landsat data composites and multiple environmental factors[J]. Forests, 2022, 13(1): 135, doi: 10.3390/f13010135.
[6]	美合日阿依·莫一丁, 买买提·沙吾提, 李金朝. 基于Sentinel-2时间序列数据及物候特征的棉花种植区提取[J]. 干旱区地理, 2022, 45(6): 1847-1859.
	[Moyidin Mihray, Sawut Mamat, Li Jinzhao. Extraction of cotton planting area based on Sentinel-2 time series data and phenological characteristics[J]. Arid Land Geography, 2022, 45(6): 1847-1859.]
[7]	沈江龙, 郑江华, 尼格拉·吐尔逊, 等. 若羌绿洲特色林果种植信息遥感提取方法适用性分析[J]. 中国农业资源与区划, 2022, 43(2): 206-219.
	[Shen Jianglong, Zheng Jianghua, Tuerxun Nigela, et al. Applicability analysis of remote sensing extraction method for planting information of characteristic forest fruit in Ruoqiang oasis[J]. Chinese Journal of Agricultural Resources and Regional Planning, 2022, 43(2): 206-219.]
[8]	王来刚, 郭燕, 贺佳, 等. 遥感数据辅助下县域耕地质量评价与空间分布研究[J]. 中国农业资源与区划, 2022, 43(12): 137-146.
	[Wang Laigang, Guo Yan, He Jia, et al. Cultivated land quality evaluation and spatial distribution in Anyang County supported by remote sensing data[J]. Chinese Journal of Agricultural Resources and Regional Planning, 2022, 43(12): 137-146.]
[9]	杨梅花, 程锦涛, 郭佳星, 等. 新疆城市规模分布与自然地理相关性分析[J]. 干旱区地理, 2022, 45(6): 1958-1967.
	[Yang Meihua, Cheng Jintao, Guo Jiaxing, et al. Correlation analysis of urban scale distribution and physical geography in Xinjiang[J]. Arid Land Geography, 2022, 45(6): 1958-1967.]
[10]	李金叶, 袁强, 蒋慧. 基于区域适应性的特色林果业发展探讨[J]. 新疆农业科学, 2010, 47(4): 741-749.
	[Li Jinye, Yuan Qiang, Jiang Hui. A discussion on development of featured forestry and fruit growing based on the regional adaptability[J]. Xinjiang Agricultural Sciences, 2010, 47(4): 741-749.]
[11]	李曦光, 王蕾, 刘平, 等. 基于MaxEnt模型的新疆红枣生态适宜性与区划分析[J]. 新疆农业科学, 2020, 57(10): 1785-1791. doi: 10.6048/j.issn.1001-4330.2020.10.003
	[Li Xiguang, Wang Lei, Liu Ping, et al. Study on ecological suitability and regionalization of Xinjiang jujube based on MaxEnt model[J]. Xinjiang Agricultural Sciences, 2020, 57(10): 1785-1791.] doi: 10.6048/j.issn.1001-4330.2020.10.003
[12]	马战林, 刘昌华, 薛华柱, 等. GEE环境下融合主被动遥感数据的冬小麦识别技术[J]. 农业机械学报, 2021, 52(9): 195-205.
	[Ma Zhanlin, Liu Changhua, Xue Huazhu, et al. Identification of winter wheat by integrating active and passive remote sensing data based on Google Earth Engine platform[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(9): 195-205.]
[13]	王林江, 吴炳方, 张淼, 等. 关键生育期冬小麦和油菜遥感分类方法[J]. 地球信息科学学报, 2019, 21(7): 1121-1131. doi: 10.12082/dqxxkx.2019.180421
	[Wang Linjiang, Wu Bingfang, Zhang Miao, et al. Winter wheat and rapeseed classification during key growth period by integrating multi-source remote sensing data[J]. Journal of Geo-information Science, 2019, 21(7): 1121-1131.]
[14]	张学艺, 戴小笠, 张玉兰, 等. 用EOS/MODIS-NDVI监测枣树生长状况的分析[J]. 宁夏大学学报(自然科学版), 2012, 33(2): 201-204.
	[Zhang Xueyi, Dai Xiaoli, Zhang Yulan, et al. Study of jujube growth situation to be monitored with EOS/MODIS-NDVI data[J]. Journal of Ningxia University (Natural Science Edition), 2012, 33(2): 201-204.]
[15]	熊皓丽, 周小成, 汪小钦, 等. 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. doi: 10.12082/dqxxkx.2021.200583
	[Xiong Haoli, Zhou Xiaocheng, Wang Xiaoqin, et al. Mapping the spatial distribution of tea plantations with 10 m resolution in Fujian Province using Google Earth Engine[J]. Journal of Geo-information Science, 2021, 23(7): 1325-1337.]
[16]	Yelu Z, Dalei H, Alfredo H, et al. Optical vegetation indices for monitoring terrestrial ecosystems globally[J]. Nature Reviews Earth & Environment, 2022, 3(7): 477-493.
[17]	敖登, 杨佳慧, 丁维婷, 等. 54种植被指数研究进展综述[J]. 安徽农业科学, 2023, 51(1): 13-21, 28.
	[Ao Deng, Yang Jiahui, Ding Weiting, et al. Review of 54 vegetation indices[J]. Anhui Agricultural Sciences, 2023, 51(1): 13-21, 28.]
[18]	Jinru X, Baofeng S. Significant remote sensing vegetation indices: A review of developments and applications[J]. Journal of Sensors, 2017: 1-17, doi: 10.1155/2017/1353691.
[19]	Haralick R M. Statistical and structural approaches to texture[J]. Proceedings of the IEEE, 1979, 67(5): 786-804.
[20]	Vizzari M. PlanetScope, Sentinel-2, and Sentinel-1 data integration for object-based land cover classification in Google Earth Engine[J]. Remote Sensing, 2022, 14(11): 2628, doi: 10.3390/rs14112628.
[21]	Zhao Y, Zhu W, Wei P, et al. Classification of Zambian grasslands using random forest feature importance selection during the optimal phenological period[J]. Ecological Indicators, 2022, 135: 108529, doi: 10.1016/j.ecolind.2021.108529.
[22]	Agarwal S, Nagendra H. Classification of Indian cities using Google Earth Engine[J]. Journal of Land Use Science, 2019, 14(4-6): 425-439. doi: 10.1080/1747423X.2020.1720842
[23]	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 Yue, Jiang Qigang, Meng Zhiguo, 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.]
[24]	何昭欣, 张淼, 吴炳方, 等. 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
	[He Zhaoxin, Zhang Miao, Wu Bingfang, et al. Extraction of summer crop in Jiangsu based on Google Earth Engine[J]. Journal of Geo-information Science, 2019, 21(5): 752-766.]
[25]	Pelletier C, Valero S, Inglada J, et al. Assessing the robustness of random forests to map land cover with high resolution satellite image time series over large areas[J]. Remote Sensing of Environment, 2016, 187: 156-168.
[26]	Loukika K N, Keesara V R, Sridhar V. Analysis of land use and land cover using machine learning algorithms on Google Earth Engine for Munneru River Basin, India[J]. Sustainability, 2021, 13(24): 13758, doi: 10.3390/su132413758.
[27]	Tassi A, Vizzari M. Object-oriented LULC classification in Google Earth Engine combining SNIC, GLCM, and machine learning algorithms[J]. Remote Sensing. 2020, 12(22): 3776, doi: 10.3390/rs122-23776.
[28]	孙玮婕, 杨军. 改进的简单非迭代聚类的遥感影像分割研究[J]. 计算机工程与应用, 2021, 57(13): 185-192. doi: 10.3778/j.issn.1002-8331.2004-0286
	[Sun Weijie, Yang Jun. Research on remote sensing image segmentation based on improved simple non-iterative clustering[J]. Computer Engineering and Applications, 2021, 57(13): 185-192.] doi: 10.3778/j.issn.1002-8331.2004-0286
[29]	黄文静, 蔡兴航, 张严磊, 等. 基于面向对象分类法的陕西佳县大枣种植面积提取研究[J]. 中国中药杂志, 2019, 44(19): 4116-4120.
	[Huang Wenjing, Cai Xinghang, Zhang Yanlei, et al. Research on extraction of Zizyphus jujuba planting area in Jia County of Shaanxi[J]. China Academy of Chinese Medical Sciences, 2019, 44(19): 4116-4120.]

影像数据集	选取数据	预处理	目的
Sentinel-1（S1）	选取干涉模式为IW，极化方式为VV+VH，时间为 2021-06-01至2021-08-01，共108景	标定轨道参数、边界噪音去除、去除热噪声、辐射定标、地形校正等，最终得到数据产品的空间分辨率为10 m	选用后向散射系数VV和VH作为独立波段参与特征构建
Sentinel-2（S2）	选取Level-2A产品数据，时间为 2021-06-01至2021-08-01，共2018景	辐射定标、几何校正、大气校正等，空间分辨率为10 m；其中QA60波段用来去云	提取原始12个波段并计算22个指数特征，基于Sentinel-2的B8近红外波段生成4种主要的纹理特征
SRTMGL1_003	空间分辨率为30 m	使用resample函数进行重采样，并用reproject函数将分辨率调整至10 m	计算4种常用的地形特征

地类代码	地类名称	样本数量/个
0	水体	180
1	裸地	456
2	人工地表	308
3	耕地	1356
4	红枣	1363
5	雪地	300
6	其他植被	1330
总计		5293

简称	分类特征	简称	分类特征
B1	气溶胶	LSWI812	地表水分指数B8&B12
B2	蓝	MNDWI	改进的归一化水指数
B3	绿	EVI	增强植被指数
B4	红	RVI	比值植被指数
B5	红边1	DVI	差值植被指数
B6	红边2	GCVI	绿色叶绿素植被指数
B7 B8 B8A B9 B11 B12 NDVI NDWI LSWI811	红边3 近红外红边4 水蒸气短波红外1 短波红外2 归一化植被指数归一化水体指数地表水分指数B8&B11	REP SAVI NIRv CIg LSWI8A11 LSWI8A12 B8_asm B8_contrast B8_corr	红边位置指数调节土壤亮度植被指数新型植被指数叶绿素绿光植被指数地表水分指数B8A&B11 地表水分指数B8A&B12 二阶矩相关性对比度
NDTI MNDVI MTCI NDRE1 NDRE2 CIr NDBI	归一化差异耕作指数修正型归一化植被指数地面叶绿素指数归一化差异红边1 归一化差异红边2 红边叶绿素指数归一化建筑指数	B8_entropy VV VH Slope Aspect Elevation Hillshade	熵垂直极化垂直-水平极化坡度坡向海拔高度山体阴影

预测类别	真实类别
预测类别	水体	裸地	人工地表	耕地		红枣	其他植被	雪地	总计	用户精度
水体	55	1	1		0	0	0	0	57	0.98
裸地	0	133	7		2	0	0	0	142	0.93
人工地表	1	4	80		0	1	0	0	86	0.90
耕地	0	1	0		380	48	22	0	451	0.87
红枣	0	1	0		29	364	25	0	419	0.80
其他植被	0	1	1		26	47	310	1	386	0.86
雪地	0	2	0		0	0	2	57	61	0.86
总计	56	143	89		437	460	359	58	1602	0.98
生产者精度	0.96	0.94	0.93		0.84	0.87	0.80	0.93	-	-
总体精度	0.86	-	-		-	-	-	-	-	-
Kappa系数	0.82	-	-		-	-	-	-	-	-

地区	细分	面积/km²	地区	细分	面积/km²
巴音郭楞蒙古自治州（若羌县）	若羌镇	71	喀什地区	巴楚县	257
	瓦石峡镇	62		伽师县	242
	米兰镇	35		麦盖提县	297
	-	-		泽普县	96
巴音郭楞蒙古自治州（且末县）	且末镇	165		疏附县	140
	塔提让镇			岳普湖县	144
	阿热勒镇			疏勒县	191
	-			喀什市	106
巴音郭楞蒙古自治州其余地区	-	150		叶城县	-
和田地区	皮山县	107		-	-
	墨玉县	172	阿克苏地区	温宿县	219
	和田县	71		新和县	111
	和田市	19		阿克苏市	200
	洛浦县	86		阿拉尔市	238
	策勒县	62		库车县	209
	于田县	88		沙雅县	161
	民丰县	14		阿瓦提县	174
	-	-		-	-
吐鲁番市	托克逊县	51	哈密市	-	234
	高昌区	57	北疆	-	-
	鄯善县	24	-	-	-
	-	-	-	共计	4253

Remote sensing extraction of jujube planting area in Xinjiang based on RF classification optimization and SNIC clustering

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 29

Related Articles 15

Metrics

Comments

Recommended 0

[1]	AI Liya, WANG Yongfang, GUO Enliang, YIN Shan, GU Xiling. NDVI change and its influencing factors of Daqingshan National Nature Reserve based on GEE [J]. Arid Land Geography, 2023, 46(8): 1279-1290.
[2]	CHEN Shujun,XU Guochang,LYU Zhiping,MA Mingyue,LI Hanyu,ZHU Yuyan. Spatiotemporal variations of fractional vegetation cover and its response to climate change and urbanization in China [J]. Arid Land Geography, 2023, 46(5): 742-752.
[3]	HE Xugang, Mamat SAWUT, SHENG Yanfang, LI Rongpeng. Remote sensing estimation of cotton water productivity in Ugan-Kuqa River Oasis based on Google Earth Engine [J]. Arid Land Geography, 2023, 46(10): 1632-1642.
[4]	ZHANG Juan, YAO Xiaojun, LI Jing, WANG Xiaoyan. Agricultural drought research based on multi-source remote sensing data in Gansu Province [J]. Arid Land Geography, 2023, 46(1): 11-22.
[5]	Mihray MOYIDIN, Mamat SAWUT, LI Jinzhao. Extraction of cotton planting area based on Sentinel-2 time series data and phenological characteristics [J]. Arid Land Geography, 2022, 45(6): 1847-1859.
[6]	PAN Qun,SHI Haiyang,ZHANG Wenqiang,LUO Geping,CHEN Chunbo. Spatiotemporal distribution of rat population density in grassland on the north slope of Tianshan Mountains based on Cubist model [J]. Arid Land Geography, 2022, 45(4): 1200-1211.
[7]	ZHAO Qiaozhen,DING Jianli,HAN Lijing,JIN Xiaoye,HAO Jianping. Exploring the application of MODIS and Landsat spatiotemporal fusion images in soil salinization: A case of Ugan River-Kuqa River Delta Oasis [J]. Arid Land Geography, 2022, 45(4): 1155-1164.
[8]	XU Li’na,SHEN Yanbo,FENG Zhen,YE Hu. Applicability research and integrated application of various correction methods for wind speed forecast in a wind farm [J]. Arid Land Geography, 2022, 45(4): 1114-1124.
[9]	PAN Zihao,YANG Shengtian,LOU Hezhen,YU Jingjie,WANG Zhongjing,ZHANG Jun. Remote sensing monitoring of ecological water conveyance and benefits evaluation of agricultural water-saving in arid basin without observation station [J]. Arid Land Geography, 2022, 45(3): 774-785.
[10]	JIANG Li,WEI Tianxing,LI Yiran,WEI Anqi. Effects of topographical factors on tree species distribution of shelter forest in Loess hilly region of northern Shaanxi [J]. Arid Land Geography, 2021, 44(6): 1763-1771.
[11]	ZHAO Yongyu,Alimujiang KASIM,GAO Pengwen,LIANG Hongwu. Quantitative analysis of urban expansion and response factors in Urumqi City based on random forest algorithm and geographical detector [J]. Arid Land Geography, 2021, 44(6): 1729-1739.
[12]	LI Jingxin,XU Erqi,ZHANG Hongqi. Accurate calculation of water resources carrying status in arid areas based on Google Earth Engine: A case study of Xinjiang Production and Construction Corps [J]. Arid Land Geography, 2021, 44(5): 1417-1426.
[13]	ZOU Shan,Jilili Abuduwaili,HUANG Wenjing,DUAN Weili. Effects of ecological water conveyance on changes of surface water area in the lower reaches of Tarim River [J]. Arid Land Geography, 2021, 44(3): 681-690.
[14]	WANG Hua, YANG Qian-peng, TIAN Yun-jie, GUO Shan-chuan, TANG Peng-fei. Vegetation coverage monitoring in the Central Asian countries using multi-temporal Landsat images [J]. Arid Land Geography, 2020, 43(4): 1023-1032.
[15]	BAO Qing-ling, DING Jian-li, WANG Jing-zhe, CAI Liang-hong. Hyperspectral detection of soil organic matter content based on random forest algorithm [J]. Arid Land Geography, 2019, 42(6): 1404-1414.