基于时序Sentinel-2影像的现代农业园区作物分类研究  

Crop classification of modern agricultural park based on time-series Sentinel-2 images

作　　者：张东彦[1] 戴震[1,2] 徐新刚 杨贵军[2] 孟炀[2] 冯海宽 洪琪[1] 姜飞[1,3] Zhang Dongyan;Dai Zhen;Xu Xingang;Yang Guijun;Meng Yang;Feng Haikuan;Hong Qi;Jiang Fei(National Engineering Research Center for Agro-Ecological Big Data Analysis&Application,Anhui University,Hefei 230601,China;Beijing Agricultural Information Technology Research Center,Beijing 100097,China;School of Information Engineering,Suzhou University,Suzhou 234000,China)

机构地区：[1]安徽大学农业生态大数据分析与应用技术国家地方联合工程技术研究中心,安徽合肥230601 [2]北京农业信息技术研究中心,北京100097 [3]宿州学院信息工程学院,安徽宿州234000

出　　处：《红外与激光工程》2021年第5期254-264,共11页Infrared and Laser Engineering

基　　金：安徽省科技重大专项(18030701209);国家重点研发计划(2017YFD0201501);现代农业产业技术体系建设专项(CARS-03);农业生态大数据分析与应用技术国家地方联合工程研究中心开放课题(AE2019011)。

摘　　要：快速、准确地掌握作物空间分布,估算不同作物种植面积及范围,这对制定宏观农业政策并指导农民进行农业生产具有重要意义。以我国内蒙古自治区扎赉特旗现代农业示范园区为研究区域,基于2019年5月至10月共9景多时相Sentinel-2卫星遥感影像,通过计算并分析不同作物归一化差值植被指数(NDVI)、比值植被指数(RVI)、增强型植被指数(EVI)等多种典型植被指数和近红外波段Ref(NIR)的时序变化特征,采用随机森林(Random Forest,RF)、决策树(Decision Tree,DT)、支持向量机(Support Vector Machine,SVM)和最大似然法(Maximum Likelihood,ML)4种分类方法对研究区多种作物进行分类识别,成功提取园区内主要作物(水稻、玉米、甜叶菊、旱稻和大豆等)空间分布情况。将RF结果与DT、SVM和ML分类结果对比,结果显示,RF总体分类精度最高,达到95.8%,Kappa系数为0.944;DT、SVM和ML分类精度分别为92.2%、91.6%和86.5%。上述研究结果表明,多时相Sentinel-2遥感影像经过光谱指数时序变化特征提取后,利用随机森林算法进行作物分类可得到精度较高的结果,这为精细指导规模化园区农业生产提供了有效的技术支持。Quickly and accurately grasping the spatial distribution of crops,estimating the area and scope of different crops were of great significance for the country to formulate macroscopic agricultural policies and guide farmers in agricultural production.To explore an efficient and accurate crop classification method,this paper took the agricultural area of Jalaid Banner of Hinggan League in Inner Mongolia Autonomous Region of China as the study area and extracted main crop classification based on the Sentinel-2 satellite remote sensing image data from May to October 2019.By analyzing the time-series curves of the four characteristic indexes of NDVI,RVI,EVI and Ref(NIR)in the study area,a total of four classification methods including Random Forest(RF),Decision Tree(DT),Support Vector Machine(SVM),and Maximum Likelihood(ML)were used to classify various crops in the study area.The RF results were compared with the classification results of DT,SVM and ML,and the spatial distribution of major crops such as rice,corn,stevia,dry rice and soybean were successfully extracted and identified.The results showed that RF had the highest overall classification accuracy of 95.8%with a Kappa coefficient of 0.944,DT,SVM and ML had classification accuracy of 92.2%,91.6%and 86.5%,respectively.The above results indicate that the multitemporal Sentinel-2 remote sensing images can be extracted by spectral index time-varying features,and the crop classification using the random forest algorithm can obtain high accuracy results,which provides effective technical support for the fine guidance of large-scale agricultural production in the park.

关 键 词：随机森林算法 近红外波段 时间序列 Sentinel-2 作物分类 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置] S127[自动化与计算机技术—控制科学与工程]