文献类型：期刊文献

中文题名：基于无人机和决策树算法的榆树疏林草原植被类型划分和覆盖度生长季动态估计

英文题名：Vegetation type classification and fractional vegetation coverage estimation for an open elm( Ulmus pumila) woodland ecosystem during a growing season based on an unmanned aerial vehicle platform coupled with decision tree algorithms

作者：韩东[1] 王浩舟[1,2] 郑邦友[3] 王锋[1]

第一作者：韩东

机构：[1]中国林业科学研究院荒漠化研究所,北京100091;[2]The Faculty of Forestry&Environmental Management,University of New Brunswick,Fredericton,NB E3B 5A3,Canada;[3]CSIRO Agricuhure and Food,Queensland Biosciences Precinct 306 Carmody Road,St Lucia,4067,QLD,Australia

年份：2018

卷号：38

期号：18

起止页码：6655-6663

中文期刊名：生态学报

外文期刊名：Acta Ecologica Sinica

收录：CSTPCD;;Scopus;北大核心:【北大核心2017】；CSCD:【CSCD2017_2018】；

基金：国家重点研发计划(2016YFC0500801,2017YFC0503804);国家自然科学基金项目(31570710);中央级公益性科研院所基本科研业务费专项资金青年人才项目(CAFYBB2017QC007)

语种：中文

中文关键词：浑善达克沙地;无人机监测平台;机器学习;正射影像;模式识别

外文关键词：Otindag sandyland;unmanned aircraft vehicle platform;machine learning;digital orthophoto map;pattern recognition

分类号：S288

摘要：植被覆盖度是评估生态环境质量与植被生长的重要指标,也是全球众多陆面过程模型和生态系统模型中表达植被动态的重要参数。卫星遥感和地面测量是估算植被覆盖度的常见方法。然而,如何精确估计榆树疏林草原上木本、草本不同类型植被的覆盖度仍然具有挑战性。无人机飞行系统有效的补充了区域尺度低空间分辨率的卫星遥感影像与样地尺度实地调查之间的缺口,为精确的监测、评估疏林草原的植被动态提供了新途径。利用无人机监测平台和决策树算法构建了一套快速、准确、自动获取景观尺度植被类型和估算植被覆盖度的自动化工具,以浑善达克沙地榆树疏林草原为对象,应用无人机监测平台对榆树疏林草原长期定位监测大样地2017年生长季植被状况进行7次监测。结果表明:1)无人机植被监测平台数据飞行高度100 m,获取的样地数字正射影像空间分辨率为2.67 cm/像元,远高于高分卫星影像,利用决策树算法基于数字正射影像可以实现自动划分榆树疏林草原木本和草本植被类型和估算植被覆盖度; 2)生长季内榆树疏林草原木本植被覆盖度为(19±2)%,草本植被覆盖度为(50±8)%,植被总覆盖度为(69±9)%,相对于木本植被,草本植被生长季内盖度变幅较大; 3)在整个生长季中,木本植被和草本植被对植被总覆盖度的平均贡献率分别为27%和73%,草本植被对植被总盖度的贡献远大于木本植被,榆树疏林草原植被的盖度主要受草本植被的影响。本研究证明无人机监测平台是一种高效、准确的植被监测工具,结合机器学习算法,实现了景观尺度植被类型的自动划分和不同类型植被覆盖度快速获取;在浑善达克沙地榆树疏林草原地区首次获取了木本植被和草本植被覆盖度的生长季动态。该平台未来可应用于各种类型生态系统植被类型划分、监测和评估。
Fractional vegetation coverage （FVC） is an important indicator to assess ecological environments and vegetation growing. It is also an important parameter in many land surface and ecological models, k is generally estimated by satellite- based remote sensing and ground investigation. However, it is challenging to precisely estimate the FVC of woody and herbaceous plants in elm sparse forest grasslands. Unmanned aerial systems （UAS） provide a solution for effectively bridging the gap between satellite-based remote sensing and field-based measurements. The purpose of this study was to propose an integrative tool for quickly, accurately, and automatically classifying the vegetation types and estimating FVC by coupling a UAS monitoring platform with decision tree algorithms. We applied this tool to observe the vegetation dynamics in an elm （Ulmus pumila） sparse forest grassland ecosystem （ESFOGE） plot during a growing season in 2017. The spatial resolution of the digital orthophoto map （DOM） derived from UAS was 2.67 cm/pixel with UAV flights at a height of 100 m. The woody and herbaceous plants of the ESFOGE plot were classified and their FVC were estimated as （19＋2） % and （50＋ 8） %, respectively, on the DOM by decision tree algorithms. The FVC variation of herbaceous plants was larger than that of woody plants during a growing season. The FVC of the ESFOGE plot was （69 _＋ 9 ）%. The contribution of woody and herbaceous plants to vegetation coverage was 27% and 73%, respectively. The FVC of the ESFOGE-plot was more influenced by herbaceous plants. Overall, this research proved that a UAS monitoring platform is an effective tool for observing the vegetation status at a landscape scale. It automatically and quickly classified the vegetation type and estimated the FVC by coupling with decision tree algorithms. To our knowledge, it is the first time that the FVC dynamics of woody and herbaceous plants were derived from a UAS platform during a growing season in the ESFOGE. This UAS platform can be applied to monitor and evaluate the vegetation status in hard-to-reach areas in the future.