摘要
针对珊瑚礁白化事件在全球范围内频繁发生的现象,以南海西沙群岛华光礁和盘石屿为例,基于Landsat-8遥感数据,利用K最邻近节点算法(KNN),对白化前后的影像进行分类,之后借助珊瑚类别内反射率的变化监测珊瑚礁白化情况。研究结果表明,利用该方法可以提高分类精度、消除白化珊瑚与沙地之间的误分类效应,有利于开展珊瑚礁群落白化监测研究。
Coral bleaching events are becoming more frequent globally,posing a serious threat to the survival of corals.This paper takes Huaguang reef and Panshiyu island of Xisha islands in the south China sea as examples to study the monitoring methods of coral reef bleaching.Based on Landsat-8 remote sensing data,the K-nearest neighbor algorithm(KNN)is used to classify the images before and after bleaching,and the bleaching of coral reefs is then detected by virtue of the changes in the reflectivity of coral species.The results show that this method can improve the classification accuracy and eliminate the misclassification effect between albino coral and sandy land,which is conducive to the study of albino coral reef community monitoring.
作者
王雪丽
蔡玉林
索琳琳
秦鹏
孙孟昊
WANG Xueli;CAI Yulin;SUO Linlin;QIN Peng;SUN Menghao(Shandong University of Science and Technology,Qingdao,Shandong 266590,China;Shandong Key Laboratory of Basic Geographic Information and Digital Technology,Qingdao,Shandong 266590,China)
出处
《遥感信息》
CSCD
北大核心
2019年第6期119-124,共6页
Remote Sensing Information
基金
国家重点研发计划专项(2017YFC1405006)
国家自然科学基金(41807170)
