摘要
以桂林市主城区为研究区,基于谷歌地球引擎(GEE)采用随机森林算法对2010、2014及2018年3期Landsat遥感影像进行土地利用分类,并采用单窗算法进行地表温度反演,根据NDVI像元二分线性模型解算地表植被覆盖度,最终对土地利用、植被覆盖及地表温度进行动态的统计及对比分析。结果表明:2010—2018年桂林市主城区平均温度呈上升趋势,8年共增加1.29℃,且各级别温区由低温区、较低温区及中等温区转化为较高温区及高温区;较低温区及低温区主要分布于植被及水体覆盖区域,而中等温区、较高温区及高温区主要分布于建设用地及未利用土地覆盖区域;2014—2018年,高植被覆盖度面积大幅缩减(缩减31.34%)主要原因在于建设用地面积的大幅增长(扩张30.19%);基于GEE的随机森林算法土地利用分类具有较高的分类精度(3个时期均高于80%)。研究结果可为改善城市热环境提供科学依据,也可为桂林市制定的发展战略提供科学参考。
The dynamic changes of urban thermal environment caused by the change of land use types become important in urban ecological environment protection.In the research of Guilin,based on the Google Earth Engine(GEE),the random forest algorithm was used to classify the land use classification of Landsat remote sensing images in 2010,2014 and 2018,and mono-window algorithm was used to calculate the surface temperature.The surface vegetation was studied according to the NDVI pixel binary model.Finally,the land use types,vegetation coverage and surface temperature were analyzed.There are following main findings.(1)From 2010 to 2018,the average temperature in the main urban area of Guilin is on the rise(increased by 1.29℃),and the temperature district in each class are converted from low temperature district,lower temperature district and medium temperature district to higher temperature district and high temperature district.(2)Lower temperature district and the low temperature district are mainly distributed in vegetation and water body coverage areas,while the medium temperature district,higher temperature district and the high temperature district are mainly distributed in construction land and unused land cover area.(3)High vegetation cover area in 2014-2018 reduced(31.34%).The main reason for the sharp decline is due to the 30.19%substantial expansion in the area of construction land.(4)GEE-based random forest algorithm land use classification had higher classification accuracy(more than 80%in all three periods).The results can provide scientific basis for improving urban thermal environment and scientific reference in the development of Guilin.
作者
娄佩卿
付波霖
何宏昌
高二涛
范冬林
唐廷元
林星辰
闭璐
LOU Pei-qing;FU Bo-lin;HE Hong-chang;GAO Er-tao;FAN Dong-lin;TANG Ting-yuan;LIN Xing-chen;BI Lu(College of Geomatics and Geoinformation,Guilin University of Technology,Guilin 541006,China)
出处
《桂林理工大学学报》
CAS
北大核心
2020年第2期330-337,共8页
Journal of Guilin University of Technology
基金
国家自然科学基金项目(41801071)
广西自然科学基金项目(2018GXNSFBA281015)
广西研究生教育创新计划项目(YCSW2020168)
广西八桂学者团队项目。
