GEE支持下的河南省冬小麦面积提取及长势监测

doi:10.3864/j.issn.0578-1752.2021.11.005

摘要/Abstract

摘要：

【目的】使用遥感技术对2017—2020年河南省冬小麦的空间分布信息进行高精度的提取,然后对2020年冬小麦的长势进行高频度的监测并结合气象条件进行分析。【方法】本文基于谷歌地球引擎（Google Earth Engine,GEE）云平台,对选取的Landsat 8影像数据根据NDVI最大值进行合成,然后进行特征构建,添加地形特征、纹理特征、NDVI以及一个新特征NDVI增幅,使用随机森林分类方法对样本数据按照构建的特征进行训练提取河南省2017—2020年冬小麦的播种面积信息;经过精度验证后对提取的河南省2020年的冬小麦种植区域生成掩膜,对掩膜区域（冬小麦种植区域）结合MODIS高时间分辨率影像数据,使用NDVI同期差值法对2020年2—4月份的冬小麦进行高频度的长势监测。【结果】使用GEE云平台能够对河南省冬小麦种植区域的空间分布信息进行快速制图;使用随机森林方法加入地形特征、纹理特征、NDVI后再加入新特征NDVI增幅,能够有效提高冬小麦的提取精度以及降低与统计数据的相对误差,基于混淆矩阵计算的平均总体分类精度为95.2%、平均kappa系数为0.909、冬小麦的平均分类精度为95.3%,与河南省统计年鉴数据相比,本文方法提取的2017—2019年河南省冬小麦播种面积相对误差均低于3%,河南省冬小麦主要种植区域的冬小麦播种面积的平均相对误差低于6%;使用MODIS影像数据结合NDVI差值模型能够对河南省2020年的冬小麦进行高频度的长势监测,河南省冬小麦在返青初期长势较往年及2019年好,到生育后期大部分区域长势与往年及2019年持平,总体上2020年冬小麦的长势较往年及2019年好。【结论】本文提出的方法能够对河南省冬小麦进行高精度的提取以及高频度的长势监测,且能够为地方政府或者一些农业部门在安排指导农事活动上提供科学依据。

关键词: 冬小麦, 长势监测, 谷歌地球引擎, 随机森林, 归一化植被指数, Landsat, MODIS

Abstract:

【Objective】 The aim of this study was to use remote sensing technology to extract the spatial distribution information of winter wheat in Henan province from 2017 to 2020, and then to monitor the growth of winter wheat in 2020 with high frequency and to analyze the meteorological conditions. 【Method】 Based on the cloud platform of Google Earth engine (GEE), the selected Landsat 8 image data were synthesized according to the maximum value of NDVI, and then the features were constructed to add terrain features, texture features, NDVI and a new feature NDVI amplification. Random forest classification method was used to train the sample data according to the constructed features to extract the winter wheat planting area in Henan province from 2017 to 2020. The accuracy of the extracted winter wheat sown area was verified by confusion matrix and Henan statistical yearbook data. After accuracy verification, a mask was generated for the extracted winter wheat planting area in Henan province in 2020. In the mask area (winter wheat planting area) combined with MODIS high time resolution image data, the NDVI synchronization difference method was used to monitor the winter wheat growth from February to April in 2020. 【Result】 The GEE cloud platform could be used to quickly map the spatial distribution information of winter wheat planting areas in Henan province. Using random forest method to add terrain feature, texture feature, NDVI and new feature NDVI could effectively improve the extraction accuracy of winter wheat and reduce the relative error with statistical data. Based on confusion matrix, the average overall classification accuracy was 95.2%, the average kappa coefficient was 0.909, and the average classification accuracy of winter wheat was 95.3%. Compared with the statistical yearbook data of Henan province, the relative errors of winter wheat sown area extracted by this method in Henan province from 2017 to 2019 were all less than 3%. The average relative error of winter wheat sown area in the main planting areas of winter wheat in Henan province was less than 6%. MODIS image data combined with NDVI difference model could be used to monitor the growth of winter wheat in Henan province in 2020. The growth of winter wheat in Henan province was better than that of previous years and 2019 during the return to green period. In the later growth stage of winter wheat, the growth of most areas was the same as that of previous years and 2019. On the whole, the growth of winter wheat in 2020 was better than that of previous years and 2019. 【Conclusion】 The method proposed in this paper could carry out high-precision extraction and high-frequency growth monitoring of winter wheat in Henan province, and could provide a scientific basis for local governments or some agricultural departments in arranging and guiding agricultural activities.

Key words: winter wheat, growth monitoring, Google Earth Engine, random forests, NDVI, Landsat, MODIS

周珂, 柳乐, 张俨娜, 苗茹, 杨阳. GEE支持下的河南省冬小麦面积提取及长势监测[J]. 中国农业科学, 2021, 54(11): 2302-2318.

ZHOU Ke, LIU Le, ZHANG YanNa, MIAO Ru, YANG Yang. Area Extraction and Growth Monitoring of Winter Wheat in Henan Province Supported by Google Earth Engine[J]. Scientia Agricultura Sinica, 2021, 54(11): 2302-2318.

图/表 15

图1

表1

表2

表3

样本选取依据"

样本种类 Sample type	解译标志 Interpretation mark	描述 Description
冬小麦 Winter wheat		研究区域冬小麦主要分布在平原地带的农村周边,在Google earth纹理较为清晰,成片出现,有较为规则的形状（矩形）,颜色为绿色或深绿色 Winter wheat in the study area is mainly distributed in the rural periphery of the plain area, the texture of Google earth is relatively clear, appears in pieces, has a more regular shape (rectangle), and the color is green or dark green
水体 Water		研究区域的水体区域主要由水库、湖泊、河流等组成,纹理上边缘明显,在颜色上水体区域在颜色上的表现为青色、淡蓝以及土黄色（黄河） The water area of the study area is mainly composed of reservoirs, lakes, rivers and so on, and the upper edge of the texture is obvious. In color, the water area is cyan, light blue and earth yellow
不透水面Town		研究区域内的不透水面有城镇建筑以及城镇周边道路组成,在Google earth上纹理信息较明显,也是成片出现,能够清晰的识别 The impervious water surface in the study area is composed of urban buildings and roads around towns, and the texture information is more obvious on Google earth, and it also appears in pieces, which can be clearly identified
其他植被 Other vegetation		其他植被由山体植被、城镇中的景观植物以及裸地植被等组成。在Google earth上此类地物具有清晰的特征,山体植被海拔较高成山体状;景观植物分布在城镇生活区域中;裸地植被也分布于城镇各处,表面较为稀疏 Other vegetation is composed of mountain vegetation, urban landscape plants and bare land vegetation. On Google earth, such features have clear characteristics, mountain vegetation is mountain-shaped at high altitude; Landscape plants are distributed in urban living areas; Bare land vegetation is also distributed throughout cities and towns, and the surface is relatively sparse

表3

图2

图3

表4

表5

表6

图4

图5

图6

图7

图8

图9

参考文献 38

[1]	郑文倩. 我国小麦价格形成机制及波动特征分析[D]. 北京: 中国农业科学院, 2016.
	ZHENG W Q. Study on wheat price formation mechanism and price volatility characteristics in China[D]. Beijing: Chinese Academy of Agricultural Sciences, 2016. (in Chinese)
[2]	盛磊, 何亚娟, 吴全, 王飞. 河南省冬小麦产量遥感监测精度比较研究. 中国农业信息, 2018,30(2):95-102.
	SHENG L, HE Y J, WU Q, WANG F. Comparative study on accuracy of winter wheat production by remote sensing monitoring in Henan province. China Agricultural Information, 2018,30(2):95-102. (in Chinese)
[3]	HAN J C, ZHANG Z, CAO J, LUO Y C, ZHANG L L, LI Z Y, ZHANG J. Prediction of winter wheat yield based on multi-source data and machine learning in China. Remote Sensing, 2020,12(2):236. doi: 10.3390/rs12020236
[4]	刘新杰, 魏云霞, 焦全军, 孙奇, 刘良云. 基于时序定量遥感的冬小麦长势监测与估产研究. 遥感技术与应用, 2019,34(4):756-765.
	LIU X J, WEI Y X, JIAO Q J, SUN Q, LIU L Y. Growth monitoring and yield prediction of winter wheat based on time-series quantitative remote sensing data. Remote Sensing Technology and Application, 2019,34(4):756-765. (in Chinese)
[5]	杨珺雯, 张锦水, 潘耀忠, 孙佩军, 朱爽. 基于遥感识别误差校正面积的农作物种植面积抽样高效分层指标研究——以冬小麦为例. 中国农业科学, 2018,51(4):675-687.
	YANG J W, ZHANG J S, PAN Y Z, SUN P J, ZHU S. An efficient hierarchical indicator based on the correction area of remote sensing identification error for planting acreage sampling-A case study of winter wheat. Scientia Agricultura Sinica, 2018,51(4):675-687. (in Chinese)
[6]	FRANCH B, VERMOTE E F, SKAKUN S, ROGER J C, BECKER- RESHEF I, MURPHY E, JUSTICE C. Remote sensing based yield monitoring: Application to winter wheat in United States and Ukraine. International Journal of Applied Earth Observation and Geoinformation, 2019,76:112-127. doi: 10.1016/j.jag.2018.11.012
[7]	HAO Z, ZHAO H L, ZHANG C, WANG H, JIANG Y, YI Z. Estimating winter wheat area based on an SVM and the variable fuzzy set method. Remote Sensing Letters, 2019,10(4):343-352. doi: 10.1080/2150704X.2018.1552811
[8]	ZHANG X W, LIU J F, QIN Z Y, QIN F. Winter wheat identification by integrating spectral and temporal information derived from multi- resolution remote sensing data. Journal of Integrative Agriculture, 2019,18(11):2628-2643. doi: 10.1016/S2095-3119(19)62615-8
[9]	MENG S Y, ZHONG Y F, LUO C, HU X, WANG X Y, HUANG S X. Optimal temporal window selection for winter wheat and wapeseed mapping with sentinel-2 images: A case study of Zhongxiang in China. Remote Sensing, 2020,12(2):226. doi: 10.3390/rs12020226
[10]	谭昌伟, 罗明, 杨昕, 马昌, 严翔, 周健, 杜颖, 王雅楠. 用PLS算法由HJ-1A/1B遥感影像估测区域冬小麦理论产量. 中国农业科学, 2015,48(20):4033-4041.
	TAN C W, LUO M, YANG X, MA C, YAN X, ZHOU J, DU Y, WANG Y N. Remote sensing estimation of winter wheat theoretical yield on regional scale using partial least squares regression algorithm based on HJ-1A/1B images. Scientia Agricultura Sinica, 2015,48(20):4033-4041. (in Chinese)
[11]	DONG C, ZHAO G X, QIN Y W, WAN H. Area extraction and spatiotemporal characteristics of winter wheat-summer maize in Shandong province using NDVI time series. PLoS ONE, 2019,14(12):226508.
[12]	王利民, 刘佳, 姚保民, 季富华, 杨福刚. 基于GF-1影像NDVI年度间相关分析的冬小麦面积变化监测. 农业工程学报, 2018,34(8):184-191.
	WANG L M, LIU J, YAO B M, JI F H, YANG F G. Area change monitoring of winter wheat based on relationship analysis of GF-1 NDVI among different years. Transactions of the Chinese Society of Agricultural Engineering, 2018,34(8):184-191. (in Chinese)
[13]	申健, 常庆瑞, 李粉玲, 王力. 基于时序NDVI的关中地区冬小麦种植信息遥感提取. 农业机械学报, 2017,48(3):215-220, 260.
	SHEN J, CHANG Q R, LI F L, WANG L. Extraction of winter wheat information based on time-series NDVI in Guanzhong area. Transactions of the Chinese Society for Agricultural Machinery, 2017,48(3):215-220, 260. (in Chinese)
[14]	安塞, 沈彦俊, 赵彦茜, 郭英, 郭硕, 肖捷颖. 基于NDVI时间序列数据的冬小麦种植面积提取. 江苏农业科学, 2019,47(15):236-240.
	AN S, SHEN Y J, ZHAO Y Q, GUO Y, GUO S, XIAO J Y. Extraction of winter wheat planting area based on NDVI time series data. Jiangsu Agricultural Science, 2019,47(15):236-240. (in Chinese)
[15]	SHAN J, WANG Z M, SUN L, QIU L, YU K, WNAG J G. Study on extraction methods of winter wheat area based on GF-1 satellite images//2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics). IEEE, 2019: 1-5.
[16]	罗桓, 李卫国, 景元书, 徐向华, 陈华. 基于SVM的县域冬小麦种植面积遥感提取. 麦类作物学报, 2019,39(4):81-88.
	LUO H, LI W G, JING Y S, XU X H, CHEN H. Remote sensing extraction of winter wheat planting area based on SVM. Journal of Triticeae Crops, 2019,39(4):81-88. (in Chinese)
[17]	李旭青, 刘世盟, 李龙, 金永涛, 范文磊, 吴怜. 基于RF算法优选多时相特征的冬小麦空间分布自动解译. 农业机械学报, 2019,50(6):218-225.
	LI X Q, LIU S M, LI L, JIN Y T, FAN W L, WU L. Automatic interpretation of spatial distribution of winter wheat based on random forest algorithm to optimize multi-temporal features. Transactions of the Chinese Society for Agricultural Machinery, 2019,50(6):218-225. (in Chinese)
[18]	贺原惠子, 王长林, 贾慧聪, 陈方. 基于随机森林算法的冬小麦提取研究. 遥感技术与应用, 2018,33(6):1132-1140.
	HE Y H Z, WANG C L, JIA H C, CHEN F. Research on extraction of winter wheat based on random forest. Remote Sensing Technology and Application, 2018,33(6):1132-1140. (in Chinese)
[19]	LIU J T, FENG Q L, GONG J H, ZHOU J P, LIANG J M, LI Y. Winter wheat mapping using a random forest classifier combined with multi-temporal and multi-sensor data. International Journal of Digital Earth, 2018,11(8):783-802. doi: 10.1080/17538947.2017.1356388
[20]	周志华. 机器学习. 北京: 清华大学出版社, 2016: 179-180.
	ZHOU Z H. Machine Learning. Beijing: Tsinghua University Press, 2016: 179-180. (in Chinese)
[21]	YOU J, PEI Z Y, WANG F, WU Q, GUO L. Area extraction of winter wheat at county scale based on modified multivariate texture and G satellite images. Transactions of the Chinese Society of Agricultural Engineering, 2016,32(13):131-139.
[22]	杨蕙宇, 王征强, 白建军, 韩红珠. 基于多特征提取与优选的冬小麦面积提取. 陕西师范大学学报(自然科学版), 2020,48(1):40-49.
	YANG H Y, WANG Z Q, BAI J J, HAN H Z. Winter wheat area extraction based on multi-feature extraction and feature selection. Journal of Shaanxi Normal University(Natural Science Edition), 2020,48(1):40-49. (in Chinese)
[23]	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. 地球信息科学学报, 2019,21(5):752-766. doi: 10.12082/dqxxkx.2019.180420
	HE Z X, ZHANG M, WU B F, XING Q. Extraction of summer crop in Jiangsu based on Google Earth Engine. Journal of Geo-information Science, 2019,21(5):752-766. (in Chinese) doi: 10.12082/dqxxkx.2019.180420
[24]	GORELICK N, HANCHER M, DIXON M, ILYUSHCHENKO S, THAU D, MOORE R. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 2017,202:18-27. doi: 10.1016/j.rse.2017.06.031
[25]	朱德海, 刘逸铭, 冯权泷, 欧聪, 郭浩, 刘建涛. 基于GEE的山东省近30年农业大棚时空动态变化研究. 农业机械学报, 2020,51(1):168-175.
	ZHU D H, LIU Y M, FENG Q L, OU C, GUO H, LIU J T. Spatial- temporal dynamic changes of agricultural greenhouses in Shandong province in recent 30 years based on Google Earth Engine. Transactions of the Chinese Society for Agricultural Machinery, 2020,51(1):168-175. (in Chinese)
[26]	LIU X P, HU G H, CHEN Y M, LI X, XU X C, LI S Y, PEI F S, WANG S J. High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine Platform. Remote sensing of environment, 2018,209:227-239. doi: 10.1016/j.rse.2018.02.055
[27]	郝斌飞, 韩旭军, 马明国, 刘一韬, 李世卫. Google Earth Engine在地球科学与环境科学中的应用研究进展. 遥感技术与应用, 2018,33(4):600-611.
	HAO B F, HAN X J, MA M G, LIU Y T, LI S W. Research progress on the application of Google Earth Engine in geoscience and environmental sciences. Remote Sensing Technology and Application, 2018,33(4):600-611. (in Chinese)
[28]	孙丽, 王蔚丹, 陈媛媛, 董沫. 2019年美国冬小麦长势遥感监测分析. 安徽农业科学, 2020,48(1):241-244.
	SUN L, WANG W D, CHEN Y Y, DONG M. Analysis of winter wheat growth of united states with remote sensing data in 2019. Journal of Anhui Agricultural Sciences, 2020,48(1):241-244. (in Chinese)
[29]	黄青, 李丹丹, 陈仲新, 刘佳, 王利民. 基于MODIS数据的冬小麦种植面积快速提取与长势监测. 农业机械学报, 2012,43(7):163-167.
	HUNAG Q, LI D D, CHEN Z X, LIU J, WANG L M. Monitoring of planting area and growth condition of winter wheat in China based on MODIS data. Transactions of the Chinese Society for Agricultural Machinery, 2012,43(7):163-167. (in Chinese)
[30]	何亚萍. 河南省循环农业发展研究[D]. 北京: 中国农业科学院, 2018.
	HE Y P. Study on the development of circular agriculture in Henan province[D]. Beijing: Chinese Academy of Agricultural Sciences, 2018. (in Chinese)
[31]	FARR T G, ROSEN P A, CARO E. The shuttle radar topography mission. Reviews of geophysics, 2007,45(2):1-13.
[32]	ULABY F T, KOUYATE F, BRISCO B, WILLIAMS T L. Textural Infornation in SAR Images. Geoscience and Remote Sensing, IEEE Transactions on GE-24, 1986,24(2):235-245.
[33]	王九中, 田海峰, 邬明权, 王力, 王长耀. 河南省冬小麦快速遥感制图. 地球信息科学学报, 2017,19(6):846-853. doi: 10.3724/SP.J.1047.2017.00846
	WANG J Z, TIAN H F, WU M Q, WANG L, WANG C Y. Rapid mapping of winter wheat in Henan province. Journal of Geo- information Science, 2017,19(6):846-853. (in Chinese) doi: 10.3724/SP.J.1047.2017.00846
[34]	BREIMAN L. Random forests. Machine Learning, 2001,45(1):5-32. doi: 10.1023/A:1010933404324
[35]	王利民, 刘佳, 唐鹏钦, 姚保民, 刘荣高. 农作物长势遥感监测需求、系统框架及业务应用. 中国农业信息, 2019,31(2):1-10.
	WANG L M, LIU J, TANG P Q, YAO B M, LIU R G. Demands, system framework, and operational application of crop growth remote sensing monitoring. China Agricultural Information, 2019,31(2):1-10. (in Chinese)
[36]	千怀遂. 农作物遥感估产最佳时相的选择研究——以中国主要粮食作物为例. 生态学报, 1998,18(1):48-55 .
	QIAN H S. Selection of the optimum temporal for crop estimation using remote sensing data-Main food crops in China. Acta Ecologica Sinica, 1998,18(1):48-55. (in Chinese)
[37]	李方杰, 任建强, 吴尚蓉, 陈仲新, 张宁丹. 河南省冬小麦种植频率时空变化及影响因素分析. 中国农业科学, 2020,53(9):1773-1794.
	LI F J, REN J Q, WU S R, CHEN Z X, ZHANG N D. Spatio-temporal variations of winter wheat planting frequency and their analysis of influencing factors in Henan province. Scientia Agricultura Sinica, 2020,53(9):1773-1794. (in Chinese)
[38]	邓荣鑫, 王文娟, 魏义长, 张富, 李春静, 刘文玉. 河南省冬小麦种植面积遥感监测及其时空特征研究. 灌溉排水学报, 2019,38(9):49-54.
	DENG R X, WANG W Q, WEI Y C, ZHANG F, LI C J, LIU W Y. Remote estimation of winter wheat area and its spatio-temporal characteristics in Henan province. Journal of Irrigation and Drainage, 2019,38(9):49-54. (in Chinese)

月份Month	09			10			11			12			01			02			03			04			05			06
旬 Ten days	上 First	中Middle	下 Last	上First	中Middle	下Last	上First	中Middle	下Last	上First	中Middle	下Last	上First	中Middle	下Last	上First	中 Middle	下 Last	上 First	中Middle	下Last	上 First	中Middle	下 Last	上 First	中 Middle	下 Last	上 First	中Middle	下 Last
冬小麦生育期 Winter wheat growth period			播种期 Sowing stage			出苗-三叶期 Regreening stage			分蘖期 Tillering stage				越冬期 Over-wintering stage				返青期 Re-greening stage		起身拔节期 Rising stage			孕穗-抽穗期 Heading stage		开花期 Flowering stage		灌浆乳熟期 Mature stage

年份 Year	日期 Date (M-D)	选用影像数据年份Year of image data selected	筛选云量 Cloud covered	数量 Count
2017-2018	09-15—11-15	2015-2017	<20%	70
2017-2018	12-01—03-25	2015-2018	<20%	133
2018-2019	09-15—11-15	2016-2018	<20%	83
2018-2019	12-01—03-25	2016-2019	<20%	125
2019-2020	09-15—11-15	2017-2019	<20%	94
2019-2020	12-01—03-25	2019-2020	<10%	36

特征 Feature	年份 Year	提取面积 Extraction area (hm²)	统计面积 Statistical area (hm²)	绝对误差 Absolute error (hm²)	相对误差 Relative error (%)
光谱+地形+纹理+NDVI Spectrum + terrain + texture + NDVI	2017-2018	5930815	5714640	216175	3.78
光谱+地形+纹理+NDVI Spectrum + terrain + texture + NDVI	2018-2019	6043211	5739850	303361	5.28
光谱+地形+纹理+NDVI+NDVI增幅 Spectrum+topography+texture+NDVI+ NDVI_increase	2017-2018	5548529	5714640	166111	2.91
	2018-2019	5604970	5739850	134670	2.35
	2019-2020	5843632

特征 Feature		2017-2018				2018-2019
光谱+地形+纹理+NDVI Spectrum + topography + texture + NDVI	市 City	提取面积 Extraction area (hm²)	统计面积 Statistical area (hm²)	绝对误差 Absolute error (hm²)	相对误差 Relative error (%)	提取面积 Extraction area (hm²)	统计面积 Statistical area (hm²)	绝对误差 Absolute error (hm²)	相对误差 Relative error (%)
	南阳 Nanyang	803278	709020	94258	13.29	771926	724660	47266	4.09
	驻马店 Zhumadian	929103	750520	178583	23.79	914174	781670	132504	16.95
	周口 Zhoukou	846381	718350	128031	17.82	893891	734380	159511	21.72
	商丘 Shangqiu	611644	588870	22774	3.87	705349	603380	101969	16.90
	开封 Kaifeng	330408	299920	30488	10.16	322177	305200	16977	5.50
	许昌 Xuchang	238458	228960	9498	4.15	226581	233010	6429	2.76
	新乡 Xinxiang	442132	379410	62722	16.53	437147	387670	49477	12.76
	安阳 Anyang	307150	320380	13230	7.22	305831	325730	19539	6.00
光谱+地形+纹理+ NDVI+NDVI增幅 Spectrum + topography +texture+NDVI+ NDVI_increase	南阳 Nanyang	721819	709020	12799	1.81	695001	724660	29659	4.09
	驻马店 Zhumadian	849960	750520	9944	13.25	834591	781670	52921	6.77
	周口 Zhoukou	809734	718350	91384	12.72	808415	734380	74035	10.08
	商丘 Shangqiu	575660	588870	13210	2.24	629586	603380	26206	4.34
	开封 Kaifeng	300274	299920	354	0.12	316275	305200	11075	3.63
	许昌 Xuchang	230127	228960	1167	0.51	224240	233010	8770	3.76
	新乡 Xinxiang	427995	379410	485.85	12.80	41784	387670	30170	7.78
	安阳 Anyang	313655	320380	6725	2.10	304353	325730	11377	3.49

特征 Feature	年份 Year	总体精度 OA (%)	Kappa系数 Kappa	冬小麦分类精度 Classification accuracy of winter wheat (%)
光谱+地形+纹理+NDVI Spectrum + topography + texture + NDVI	2017-2018	93.3	0.862	93.5
	2018-2019	94.8	0.891	95.1
	2019-2020	94.7	0.892	94.5
光谱+地形+纹理+NDVI+NDVI增幅 Spectrum + topography + texture + NDVI+NDVI_increase	2017-2018	94.8	0.893	94.6
	2018-2019	95.6	0.921	95.3
	2019-2020	95.8	0.913	95.9