摘要
选择春、秋季低云量Landsat-8卫星遥感影像,构建包含有多光谱地表反射率、光谱指数、几何纹理和地形因子的分类特征集,通过随机森林分类算法开展赣南柑橘果园空间分布遥感制图研究.研究结果表明:利用春季影像提取的柑橘果园整体精度为91.12%,Kappa系数为0.88,优于秋季影像提取结果;随机森林算法在赣南柑橘果园识别制图中具有较高的分类精度和较好的适用性,利用降维的分类特征提取柑橘果园也具有较高精度;赣南柑橘果园面积约1 794.26 km^2,具有一定比例的陡坡种植现象,寻乌、信丰、安远等3县的柑橘果园呈现规模化、连片化的景观.
Several Landsat OLI images acquired in spring and autumn are selected to map citrus orchards distribution.Random Forest(RF)classifier is utilized to implement a supervised classification on the dataset including multi-spectral reflectance,vegetation and moisture indices,texture information and topographic features.The results show that classification with spring image is successful with an overall accuracy(OA)of 91.12%and a Kappa statistic of 0.88.And it is superior to that with autumn images.RF is highly suitable for the identi-fication and classification of citrus orchards.And classification with an optimal subset of discrimination features is also acceptable with a high accuracy.The area of citrus orchards is about 1 794.26 km 2 and a certain proportion of citrus orchards is cultivated on steep slopes.The landscape characteristics of citrus orchards in some counties such as Xunwu,Xinfeng and Anyuan became single,continuous and massive.
作者
徐晗泽宇
刘冲
齐述华
赵国帅
XU Hanzeyu;LIU Chong;QI Shuhua;ZHAO Guoshuai(School of Geography and Environment,Jiangxi Normal University,Nanchang Jiangxi 330022,China;Key Laboratory of Poyang Lake Wetland and Watershed Research,Ministry of Education,Jiangxi Normal University,Nanchang Jiangxi 330022,China;Jiangxi Provincial Key Laboratory of Poyang Lake Comprehensive Management and Resources Exploitation,Jiangxi Normal University,Nanchang Jiangxi 330022,China;Forest Inventory and Planning Institute of Fujian Province,Fuzhou Fujian 350003,China)
出处
《江西师范大学学报（自然科学版）》
CAS
北大核心
2018年第4期434-440,共7页
Journal of Jiangxi Normal University(Natural Science Edition)
基金
国家自然科学基金(41261069)
江西省重大生态安全问题监控协同创新中心(JXS-EW-00)资助项目
关键词
遥感
分类
随机森林
赣南
柑橘果园
remote sensing
classifier
random forest
Gannan
citrus orchard
