基于随机森林的成都市2015—2020年土地利用变化检测  

Detection of Land Use Changes in Chengdu from 2015 to 2020 Based on Random Forest

作　　者：李伊波 简季[1] LI Yibo;JIAN Ji

机构地区：[1]成都理工大学地球科学学院,成都610059

出　　处：《科技创新与应用》2023年第3期95-97,102,共4页Technology Innovation and Application

基　　金：国家自然科学基金项目(41771444)。

摘　　要：土地利用变化检测对于合理地组织土地利用、国土空间规划和城市可持续发展等具有重要意义。鉴于成都市新一轮城市总体规划“一山连两翼”(以龙泉山为界,西部为中心城市,东部塑造产业新城)建设目标逐步实施,对土地利用类型的变化影响较大。基于此,本研究以成都市为研究区,以2015年和2020年Landsat-8遥感影像作为数据源,在GEE平台上对数据预处理,采用随机森林算法和众数滤波处理实现土地利用分类和精度评价。结果表明,2015年和2020年数据Kappa系数和总体精度均分别在0.75和80.00%以上,同时浅析成都市2015—2020年土地利用类型变化主要原因,为成都市城区发展提供合理的参考规划。Land use change detection is of great significance for rational organization of land use, land spatial planning and urban sustainable development. In view of the gradual implementation of the construction goal of "one mountain and two wings" in Chengdu’s new round of urban overall planning(with Longquan Mountain as the boundary, the west as the central city and the east shaping the industrial new city), it has a great impact on the change of land use types. Based on this,this study takes Chengdu as the study area, takes the 2015 and 2020 Landsat-8 remote sensing images as the data source,preprocesses the data on the GEE platform, and uses random forest algorithm and multi-filter processing to achieve land use classification and accuracy evaluation. The results show that the Kappa coefficient and the overall accuracy of the data in2015 and 2020 are more than 0.75% and 80.005% respectively. Meanwhile, the main reasons for the change of land use types in Chengdu from 2015 to 2020 are analyzed to provide a reasonable reference planning for the urban development of Chengdu.

关 键 词：土地利用 Google Earth Engine 随机森林 变化检测 遥感影像 

分 类 号：P237[天文地球—摄影测量与遥感]