摘要
卫星遥感的多传感器技术为大尺度上实现工业热源的快速分类、识别提供了可能。利用2012—2019年VIIRS(可见光红外成像辐射仪)Nightfire数据,以山东省为研究区,首先,根据工业热异常点的空间聚集性特征和统计特征,使用DBSCAN聚类和时间序列聚类提取确认工业热源对象。其次,基于工业温度特征模板,使用K最近邻分类算法实现了工业子类热源的分类。研究表明:(1)使用该方法提取工业热源对象精度达到99.81%,比“空间—时间—温度”维度的面向对象方法提高了1.47%,在提取工业热源对象数量上提高了8.99%;工业子类热源对象分类总体精度为84.54%,可较好地对山东省工业热源对象进行提取与分类。(2)山东省工业热源对象主要分布于潍坊市、滨州市、临沂市和东营市4个城市(占比43.30%);工业热源对象集中分布于淄博市、滨州市和东营市交界处,聊城市东部,枣庄市中部及临沂市中部,呈现显著的空间集聚态势;根据工业转型升级政策提出前后工业热源对象数量的变化(减少13.63%),表明山东省推进工业转型升级政策取得一定成效。因此,利用该方法可较好地提取山东省工业热源,为工业相关政策的制定和评价提供客观依据。
Multi-sensor technology of satellite remote sensing provides a possibility for rapid classification and identification of industrial heat sources on a large scale.the Nightfire data of VIIRS(Visible Infrared Imaging Radiometer Suite)from 2012 to 2019 are used,taking Shandong Province as the research area.Firstly,according to the spatial aggregation characteristics and statistical characteristics of industrial heat anomalies,extract and confirm the industrial heat source objects by the DBSCAN clustering and time series clustering.Secondly,based on the industrial temperature feature template,realize the classification of industrial sub-class heat sources by the K-nearest neighbor classification algorithm.The research shows that:(1)The precision of extracting industrial heat source objects using the method in this paper reaches 99.81%,which is 1.47%higher than the object-oriented method in the dimension of“space-time-temperature”,and 8.99%higher than the number of industrial heat source objects.The overall precision of industrial sub-class heat source object classification is84.54%,which can better extract and classify industrial heat source objects in Shandong Province.(2)The industrial heat sources in Shandong Province are mainly distributed in Weifang,Binzhou,Linyi,and Dongying(accounting for 43.30%).Industrial heat source objects are concentrated in the junction of Zibo,Binzhou and Dongying,eastern Liaocheng,central Zaozhuang,and central Linyi,showing a significant spatial agglomeration trend.The change in the number of industrial heat sources before and after the industrial transformation and upgrading policy was proposed(13.63%reduction),indicating that Shandong Province has made some achievements in promoting industrial transformation and upgrading policy.Therefore,the method in this paper can be used to better extract the industrial heat source in Shandong Province and provide an objective basis for the formulation and evaluation of industrial policies.
作者
李博
范俊甫
韩留生
周玉科
张大富
Li Bo;Fan Junfu;Han Liusheng;Zhou Yuke;Zhang Dafu(School of Civil and Architectural Engineering,Shandong University of Technology,Zibo 255049,China;Key Laboratory of Ecosystem Network Observation and Modeling,Institute of Geographic Sciences andNature Resources Research,Chinese Academy of Sciences,Beijing 100101,China)
出处
《遥感技术与应用》
CSCD
北大核心
2022年第4期919-928,共10页
Remote Sensing Technology and Application
基金
国家自然科学基金项目(42171413)
资源与环境信息系统国家重点实验室开放基金项目资助
国家重点研发计划项目(2017YFB0503500、2018YFB0505301)
山东省自然科学基金项目(ZR2020MD0115、ZR2020MD018)
山东理工大学青年教师发展支持计划项目(4072-115016)
作者简介
李博(1989-),男,山东菏泽人,硕士研究生,主要从事城市环境遥感研究。E‐mail:823009251@qq.com;通讯作者:范俊甫(1985-),男,山东聊城人,博士,副教授,主要从事高性能地学计算与城市环境遥感研究。E‐mail:fanjf@sdut.edu.cn
