基于QUEST决策树兼容多源数据的淡水沼泽湿地信息提取

生态学杂志

基于QUEST决策树兼容多源数据的淡水沼泽湿地信息提取

那晓东^1,2;张树清¹;李晓峰^1,2;于欢^1,2;刘春悦^1,2

¹中国科学院东北地理与农业生态研究所, 长春130012; ²中国科学院研究生院，北京 100049

收稿日期:2008-06-02 修回日期:1900-01-01 出版日期:2009-02-10 发布日期:2009-02-10

Freshwater marsh wetland information extraction based on QUEST decision tree integrating with multi-source data.

NA Xiao-dong^1,2;ZHANG Shu-qing¹;Li Xiao-feng^1,2;YU Huan^1,2;LIU Chun-yue^1,2

¹Northeast Institute of Geography and Agricultural Ecology, Chinese Academy of Sciences, Changchun 130012, China;²Graduate University of Chinese Academy of Sciences, Beijing 100049, China

Received:2008-06-02 Revised:1900-01-01 Online:2009-02-10 Published:2009-02-10

摘要/Abstract

摘要： 以三江平原东北部为例，探讨了中国典型淡水沼泽湿地信息的提取方法。利用TM卫星影像数据，基于半方差分析和Z检验方法对比研究区典型地物不同尺度的各种纹理特征，从而遴选最优的窗口大小、纹理特征及其派生波段以提高地物之间的可分性。采用快速、无偏、高效统计树(quick, unbiased, and efficient statistical tree，QUEST)算法集成遥感影像的光谱特征、多尺度纹理特征和地学辅助数据建立研究区湿地信息提取的决策树模型。基于实测的GPS样本点采用混淆矩阵的方法对分类结果进行精度验证，并与传统的最大似然监督分类方法(maximum likelihood classification, MLC)进行对比。结果表明，基于QUEST的决策树分类结果的总精度和Kappa系数分别为84.58%和0.816，分类精度较MLC监督分类方法有明显提高，是内陆淡水沼泽湿地信息提取的有效手段。

关键词: 杂草稻, 落粒粳, 生物学, 抗逆境特性

Abstract: Taking the northeast part of Sanjiang Plain as a case, the information extraction method for typical freshwater marsh wetland was approached. By using TM images and based on semi-variograms and Z-test, different scales texture features of typical vegetations in study area were comparatively studied, and the optimum window size, texture features, and their derivative spectral bands were selected to maximize the structural separation of the vegetations. The quick, unbiased, and efficient statistical tree (QUEST) algorithm was used to build the decision tree model of wetland information extraction, integrating the spectral and texture features with assistant geographical data. The classification results based on QUEST algorithm were examined by confusion matrix accuracy assessment using field GPS samples, and the validation showed that the total classification accuracy was 8458%, and the Kappa coefficient was 0816. It was suggested that the accuracy of classification based on QUEST algorithm was higher than that based on maximum likelihood classification (MLC) supervised method, being proved to be an effective means to extract inland freshwater marsh wetland information.

Key words: Weedy rice, Luolijing (Oryza sativa), Biology, Stress-resistance

那晓东;张树清;李晓峰;于欢;刘春悦. 基于QUEST决策树兼容多源数据的淡水沼泽湿地信息提取[J]. 生态学杂志.

NA Xiao-dong^1,2;ZHANG Shu-qing¹;Li Xiao-feng^1,2;YU Huan^1,2;LIU Chun-yue^1,2. Freshwater marsh wetland information extraction based on QUEST decision tree integrating with multi-source data.[J]. cje.

[1]	冯建设, 薛晓萍, 李曼华, 李楠. 苹果花期预报中的生物学机理及应用 [J]. 生态学杂志, 2022, 41(3): 618-624.
[2]	王洪浩, 何涛, 陆化杰, 陈子越, 宁欣, 刘凯, 陈新军. 日本海舍氏贝乌贼渔业生物学特性 [J]. 生态学杂志, 2021, 40(8): 2478-2484.
[3]	周全来, 王正文, 齐凤林, 杨达志, 门红艳, 孙彪, 齐楠, 崔雪, 王永翠. 少花蒺藜草生物生态学特征与综合防除策略 [J]. 生态学杂志, 2021, 40(8): 2593-2600.
[4]	冯丹, 高小迪, 李云凯. 海洋鱼类肠道微生物研究进展及应用前景 [J]. 生态学杂志, 2021, 40(1): 255-265.
[5]	朱冰涛,徐猛,刘超,顾党恩,余梵冬,杨叶欣,胡隐昌,牟希东. 外来鱼类革胡子鲶与本地鲶的功能反应及生物学特性的比较 [J]. 生态学杂志, 2020, 39(2): 567-575.
[6]	洪小帆, 张俊, 江艳娥, 蔡研聪, 杨玉滔, 王欢欢, 李纲, 陈作志. 南海西沙群岛琛航岛犬牙锥齿鲷生物学特征 [J]. 生态学杂志, 2020, 39(10): 3320-3331.
[7]	魏莹,李倩,李阳,毛祝新,王宇超,岳明. 外来入侵植物反枝苋的研究进展 [J]. 生态学杂志, 2020, 39(1): 282-291.
[8]	聂孝红1,尹昊1,郭东矗1,国辉1,周金星2,彭霞薇1*. 四株耐锑细菌的生物学特性及其对油菜在锑污染土壤中的促生作用 [J]. 生态学杂志, 2017, 36(6): 1658-1666.
[9]	宁应之*,烟郑杰,孙静,陈凌云. 黑河干流纤毛虫群落组成及其对水质的响应 [J]. 生态学杂志, 2017, 36(5): 1350-1356.
[10]	朱赟杰1,2,顾党恩1,韦慧1,牟希东1,罗渡1,徐猛1,罗建仁1，胡隐昌1*. 华南地区外来鱼类革胡子鲶的繁殖生物学 [J]. 生态学杂志, 2017, 36(1): 137-143.
[11]	李晓冬,吴元华*. 辣椒轻斑驳病毒研究进展 [J]. 生态学杂志, 2016, 35(10): 2831-2837.
[12]	李胜男1,2,周建1,2,魏利军1,2,孔繁翔1,史小丽1**. 淡水超微型浮游植物多样性及其研究方法 [J]. 生态学杂志, 2015, 34(4): 1174-1182.
[13]	梁君,虞宝存,毕远新,王伟定**. 中街山列岛海域厚壳贻贝生物学特征及生长规律 [J]. 生态学杂志, 2015, 34(2): 471-476.
[14]	王琚钢1,峥嵘1,2,白淑兰1**,高晓敏3,刘敏1. 菌根分子生物学研究进展 [J]. 生态学杂志, 2014, 33(3): 816-824.
[15]	胡忠俊1,2,张镱锂1**,刘林山1,于海彬1,2. 生物避难所及其识别方法评述 [J]. 生态学杂志, 2013, 32(12): 3397-3406.