长江流域资源与环境 >> 2016, Vol. 25 >> Issue (07): 1070-1077.doi: 10.11870/cjlyzyyhj201607008

• 自然资源 • 上一篇    下一篇

基于C5.0决策树和时序HJ-1A/BCCD数据的神农架林区植被分类

李梦莹1, 胡勇1,2, 王征禹1   

  1. 1. 武汉大学资源与环境科学学院, 湖北 武汉 430079;
    2. 武汉大学地理信息系统教育部重点实验, 湖北 武汉 430079
  • 收稿日期:2015-11-06 出版日期:2016-07-20
  • 作者简介:李梦莹(1990~),女,硕士研究生,主要从事生态遥感应用研究.E-mail:2013202050012@whu.edu.cn
  • 基金资助:
    国家基础科学人才培养基金武汉大学地理科学理科基地资助项目(J1103409);中央高校基本科研业务专项重大重点培育专项“地理资源环境综合监测”(2042015kf1044);教育部留学回国人员科研启动基金(2013)

STUDY ON VEGETATION CLASSIFICATION IN SHENNONGJIA FOREST DISTRICT BASED ON C5.0 DECISION TREE AND HJ-1 A/B DATA

LI Meng-ying1, HU Yong1,2, WANG Zheng-yu1   

  1. 1. School of Resource and Environment Sciences, Wuhan University, Wuhan 430079, China;
    2. Key Laboratory of Geographic Information System of Ministry of Education, Wuhan 430079, China
  • Received:2015-11-06 Online:2016-07-20
  • Supported by:
    National science funds for fostering talents in basic science,geographical science, wuhan university (No.J1103409);The Fundamental Research Funds for the Central Universities "Integrated monitoring of Geographical resources andenvironment" (2042015kf1044);The Project Sponsored by the Scientific Research Foundation forthe Returned Overseas Chinese Scholars, State Education Ministry(2013)

摘要: 我国神农架林区海拔高、气候复杂,森林类型多样,结构破碎,森林遥感分类难度较大。将2013年时间序列HJ-1A/B CCD遥感影像作为数据源,计算出植被指数(NDVI、DVI、RVI)和主成分第一分量(PC1),使用DEM数据生成地形因子(高程、坡度、坡向),构建植被分类时序因子集。运用C5.0决策树分类法将神农架林区植被细分为七类:针叶林;针阔混交林;落叶阔叶林;常绿和落叶阔叶混交林;常绿阔叶林;灌丛和草甸。结果表明:该方法的总体精度为72.7%,Kappa系数为0.67;在6~8月,针叶林、草甸和灌丛的植被指数明显低于常绿阔叶林、常绿和落叶阔叶混交林、落叶阔叶林和针阔混交林,对分类的贡献较大,称为植被分类的“窗口期”。PC1、NDVI和高程因子对神农架林地的区分度较高,而坡度、坡向和RVI因子对分类帮助不大。作为一种智能分类方法,C5.0决策树分类方法应用于30m分辨率的时间序列HJ-1A/B CCD数据,能够将地貌复杂的神农架林区植被分为七类,提高了类别精度,具有更高的应用价值。

关键词: C5.0决策树, HJ-1A/B CCD数据, 神农架林区, 时间序列, 森林次级分类

Abstract: Forest classification plays an important role in understanding the structure and function of forest ecosystem. Shennongjia Forest district belongs to the northern subtropical monsoon climate zone with vegetations distributed in different vertical belts. Because of its high altitude, complicated climate, rich forest types and fragmented landscape, it is difficult to classify the vegetation types in forest region of Shennongjia district. This paper constructed a time series analyses for vegetation classification. The time series of factors collection consisted of the vegetation indices, the first principal component (PC1) and topographic factors, which were calculated from 24 HJ-1A/B CCD images of 2013 and DEM. The vegetation indices collection included NDVI (Normalized Difference Vegetation Index), DVI (Difference Vegetation Index) and RVI (Ratio Vegetation Index). The topographic factors collection included altitude, slope and aspect. By means of the C5.0 Intelligent decision tree algorithm, seven categories were classified in the Shennongjia forest district. They were:cold-temperate coniferous forest, temperate coniferous and broad-leaved mixed forest, temperate deciduous broad-leaved forest, broad-leaved evergreen and deciduous mixed forest, north-subtropical evergreen broad-leaved forest, shrub and meadow. The results showed that:(1) Using the intelligent decision tree algorithm, the overall accuracy of the classification reached 72.7%, with a Kappa coefficient of 0.67; (2) the Vegetation Index values of north-subtropical evergreen broad-leaved forest, the broad-leafed evergreen and deciduous mixed forest, temperate deciduous broad-leafed forest and the temperate coniferous and broad-leafed mixed forest were higher than the cold temperate coniferous forest, scrub and meadow in June to August; the window period of forest vegetation classification was identified as June to August. Using the time series of factors collection can show up "the window" and provide a theoretical basis for the vegetation classification; (3) the time series of PC1, NDVI and altitude as well had a significant contribution to the forest classification; the time series of DVI can help to distinguish between north-subtropical evergreen broad-leaved forest, broad-leafed evergreen and deciduous mixed forest, temperate coniferous and broad-leaved mixed forest, temperate deciduous broad-leaved forest; while slope, aspect and the time series of RVI had much less help in the automatic generation of classification rules, thus, they were of little value to vegetation classification. Overall, the time series of data derived from 30m-resolution HJ-1A/B CCD imagery can accurately categorize the Shennongjia forest vegetation into seven classes based on the C5.0 decision tree method. As an intelligent decision tree classification algorithm, the method has the advantages of identifying more categories and is of high application value. There is still space to improve the classification accuracy, i.e., a more considerate classification system of Shennongjia Forest, the increasing of field samples at mixed vegetation belt, and the use of higher spatial and temporal resolution images.

Key words: C5.0 Intelligent decision tree, HJ-1A/B CCD data, Shennongjia, time-series, forest sub-categories

中图分类号: 

  • TP79
[1] 李怒云.中国林业碳汇[M]. 2007年6月第一版.中国林业出版社, 2007:14.[LI N Y. Forestry Carbon Sequestration in China. June 2007. China Forestry Publishing House, 2007:14]
[2] 于信芳,庄大方.基于MODIS NDVI数据的东北森林物候期监测[J].资源环境, 2006, 28(4)[YU X F, ZHUANG D F. Monitoring Forest Phenophases of Northeast China based on MODIS NDVI Data[J]. Resources Science 2006, 28(4)]
[3] 李儒,张霞,刘波,等.遥感时间序列数据滤波重建算法发展综述[J].遥感学报, 200913(2):335-341.[LI R, ZHANG X, LIU B, et al. Review on methods of remote sensing time-series data reconstruction[J]. Journal of Remote Sensing, 2009, 13(2):335-341.]
[4] 顾娟,李新,黄春林. NDVI时间序列数据集重建方法述评.遥感技术与应用, 2006, 21(4):391-395.[GU J, LI X, HUANG C L. Research on the Reconstructing of Time-series NDVI Data[J]. Remote Sensing Technology and Application. 2006, 21(4):391-395.]
[5] 李鑫川,徐新刚,王纪华,等.基于时间序列环境卫星影像的作物分类识别[J].农业工程学报, 2013, 29(2):169-176.[LI X C, XU X G, WANG J H, et al. Crop classification recognition based on time-series images from HJ satellite[J]. Transactions of the Chinese society of Agricultural Engineering, 2013, 29(2):169-176.]
[6] 王海忠.基干决策树的网络流量分类系统的设计与实现[D].北京:中国科学院大学, 2014.3.[WANG H Z. The Design and Implementation of Network Traffic Classification Based on Decision Tree[D]. Bei Jing:University of Chinese Academy of Sciences, 2014.3.]
[7] ROGAN J. Mapping Landcover Modifications over Large Areas-A Comparison of Machine Learning Algorithms[J]. Remote Sensing of Environment, 2008, 112:2272-2283
[8] 齐红超,祁元,徐瑱.基于C5.0决策树算法的西北干旱区土地覆盖分类研究——以甘肃省武威市为例[J].遥感技术与应用, 2009, 24(5):648-653.[QI H C, QI Y, XU Z, The Study of the Northwest Arid Zone Land-Cover Classification Bas-ed on C5.0 Decision Tree Algorithm at Wuwei Ci-ty, Gansu Province[J]. Remote Sensing Technology and Application. 2009, 24(5):648-653]
[9] 孙世洲.关于中国国家自然地图集中的中国植被区划图[J].植物生态学报, 1998, 22(6):523-537.[SUN S Z. Concerning the vegetation Chinese regionalization map as a part of in the natural geographical atlas of the people republic of China[J]. Acta phytoecologica sinca, 1998, 22(6):523-537.]
[10] 蒋雪琴,刘艳红,赵本元.湖北神农架地区巴山冷杉(Abies fargesii)种群结构特征与空间分布格局[J].生态学报, 2009, 29(5):2211-2218.)[JIANG X Q, LIU Y H, ZHAO B Y. Struc-ture characteristics and spatial distribution of Abies fargesii population in Shennongjia National Reserve, China[J]. Acta Ecologica Sinica, 2009, 29(5):2211-2218.]
[11] 铁军.神农架川金丝猴(Rhinopithecus roxellana)栖息地植物构成和食源植物评价研究[D].北京:北京林业大学, 2009.6.[TIE J. The Plant Composition in Habitat and Food Rseources Evaluation of Rhinopithecus roxellana in Shennongjia, China[D]. Bei Jing:Beijing fores-t ry university. 2009.6.]
[12] 李天祺,朱秀芳,潘耀忠,等.环境星NDVI时间序列重构方法研究[J].遥感信息, 2015, 30(1):58-65.[LI T Q, ZHU X F, PAN Y Z, et al. NDVI Time-series Reconstruction Methods of China's HJ Satellite Imagery[J].Remote sensing Information, 2015, 30(1):58-65.]
[13] 扈晶晶.基于HJ-1和ZY-3遥感图像的农田防护林信息提取研究[D].北京林业大学, 2014.[HU J J. The farmland shelterbelts extraction based on HJ-1 and ZY-3 satellite images[J]. Beijing Forestry University, 2014.]
[14] 陈雪洋,蒙继华,杜鑫.基于环境星CCD数据的冬小麦叶面积指数遥感监测模型[J].国土资源遥感, 2010, 22(2):55-58.[CHEN X Y, MENG J H, DU X. The Remote Sensing information extraction method based on vegetation coverage[J]. Remote Sensing for Land & Resouces, 2010, 22(2):55-58.]
[15] 罗亚,徐建华,岳文泽.基于遥感影像的植被指数研究方法述评[J].生态科学, 2005, 24(1):75-79.[LUO Y, XU J H, YUE W Z. Research on vegetation indices based on the remote sensing images[J]. Ecologic Science, 2005, 24(1):75-79.]
[16] 严红萍,俞兵.主成分分析在遥感图像处理中的应用[J].资源环境与工程, 2006, 20(2):168-170.[YAN H P, YU B. The principal component analsis for RS MAGE processing[J]. Resoirces Enviroment & Engineerring, 2006, 20(2):168-170.]
[17] 李晓娟,刘晓萌等. ENVI遥感影像处理[M]. 1.北京:中国环境科学出版社, 2007:355.
[18] 姜洋,李艳.浙江省森林信息提取及其变化的空间分布[J].生态学报, 2014, 34(24):7261-7270.[JIANG Y, LI Y. The extraction of forest information and the spatial distribution of ite change in Zhejiang Provice, Acta Ecologica Sinica, 2014, 34(24):7261-7270.]
[19] 韩婷婷,习晓环,王城,等.基于决策树方法的云南省森林分类研究[J].遥感技术与应用, 2014, 29(5):744-751.[HAN T T, XI X H, WANG C, et al. Study on Forest Classification in Yunnan Based on Decision Tree Algorithm[J]. Remote Sensing Techno-logy and Application, 2014, 29(5):744-751.]
[20] 田自强,陈玥,赵常明,等.中国神农架地区的植被制图及植物群落物种多样性[J].生态学报, 2004, 24(8):1611-1621.[TIAN Z Q, CHEN Y, ZHAO C M, et al. Mapping of vegetation and analysis on its biodiversity in Shennongjia region, China[J]. Acta ecologica sinca, 2004, 24(8):1611-1621.]
[1] 邵佳丽, 郑伟, 刘诚. 卫星遥感洞庭湖主汛期水体时空变化特征及影响因子分析[J]. 长江流域资源与环境, 2015, 24(08): 1315-1321.
[2] 许全喜| 张小峰| 袁, 晶. 长江上游河流输沙量时间序列跃变现象研究[J]. 长江流域资源与环境, 2009, 18(6): 555-.
[3] 韩贵锋,徐建华. 人口与经济发展对植被的影响研究[J]. 长江流域资源与环境, 2008, 17(5): 785-785.
[4] 谢平,陈广才,韩淑敏,武方圆. 从潮白河年径流频率分布变化看北京市水资源安全问题[J]. 长江流域资源与环境, 2006, 15(6): 713-713.
[5] 李 娜,许有鹏, 陈 爽. 苏州城市化进程对降雨特征影响分析[J]. 长江流域资源与环境, 2006, 15(3): 335-339.
[6] 刘爱霞,刘正军,王 静. 基于PCA变换和神经元网络分类方法的中国森林制图研究[J]. 长江流域资源与环境, 2006, 15(1): 19-24.
[7] 应 铭,李九发,万新宁,沈焕庭. 长江大通站输沙量时间序列分析研究[J]. 长江流域资源与环境, 2005, 14(1): 81-87.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 宋玉芝,秦伯强, 高光. 附着生物对富营养化水体氮磷的去除效果[J]. 长江流域资源与环境, 2009, 18(2): 180 .
[2] 曾 群, 蔡述明. 武汉市水资源可持续利用评价[J]. 长江流域资源与环境, 2005, 14(4): 429 -434 .
[3] 彭长青,冯金飞,卞新民. 基于遗传算法和GIS的县域水田种植制度空间布局优化[J]. 长江流域资源与环境, 2006, 15(1): 66 -70 .
[4] 唐 琦,虞孝感. 长江三角洲地区经济可持续发展问题初探[J]. 长江流域资源与环境, 2006, 15(3): 269 -273 .
[5] 李 娜,许有鹏, 陈 爽. 苏州城市化进程对降雨特征影响分析[J]. 长江流域资源与环境, 2006, 15(3): 335 -339 .
[6] 张昌顺,李 昆,马姜明,郑志新. 施肥对印楝人工林生长及土壤肥力的影响[J]. 长江流域资源与环境, 2007, 16(3): 329 .
[7] 陈校辉,边文冀,赵 钦,严维辉,彭 刚. 长江江苏段鱼类种类组成和优势种研究[J]. 长江流域资源与环境, 2007, 16(5): 571 .
[8] 王海云,高太忠,高京,黄群贤. 基于AHPLP法的南水北调中线水资源优化配置[J]. 长江流域资源与环境, 2007, 16(5): 588 .
[9] 陈西庆,吕溪溪,严以新,童朝锋,窦希萍, 李键庸,田 磊. 长江河口上边界床沙粒径的长期变化及其原因[J]. 长江流域资源与环境, 2008, 17(4): 598 .
[10] 张 燕, 张 洪, 彭补拙. 土地资源、环境与经济发展的协调性评价[J]. 长江流域资源与环境, 2008, 17(4): 529 .