自组织特征映射网络在芦芽山自然保护区青杄林分类和排序中的应用

doi:10.11707/j.1001-7488.20140501

摘要/Abstract

摘要：

采用自组织特征映射网络（SOM）对芦芽山自然保护区青杄林进行数量分类和排序。结果表明：SOM将60个森林样地划分为8个群落类型，各类型在排序图上都有其分布范围和界限，且群落结构、物种组成差异明显，说明分类和排序结果合理，可较好地揭示群落间的生态关系；通过环境因子梯度的可视化方法，确定海拔、坡位和坡度是影响该地区青杄林生长和分布的主要因子，揭示群落、物种及植被分布和环境因子的关系。结果表明SOM网络适用于表征群落生态特征及探索群落和环境相互关系的研究，将其应用于自然保护方面，将有利于对不同植被类型进行分类和管理。

关键词: 芦芽山自然保护区, 青杄林, 自组织特征映射网络, 分类, 排序

Abstract:

The self-organizing feature map (SOM) was applied to the classification and ordination of Picea wilsonii forests in the Luya Mountain Nature Reserve. It was shown that 60 quadrats were classified into 8 groups, representing 8 types of plant communities. These communities had obvious differences in species composition and structure. Each type had its boundary and distributional range on the ordination map. The SOM clustering showed significant ecological meanings and revealed the relationships among communities. Additionally, by using a visualizing method of environmental factor gradient on topology map, SOM indicated that elevation, slope position and slope were the main environmental factors affecting the distribution of P. wilsonii forests. The SOM ordination clearly showed ecological gradients and revealed the relationships among communities and environmental factors. This study suggests that SOM is a very effective quantitative technique in plant ecology, and it is applicable to describe community characteristics and to analyze relationship between communities and environmental variables.

Key words: Luya Mountain Nature Reserve, Picea wilsonii forest, self-organizing feature map, classification

中图分类号:

S759.92

李林峰, 张金屯, 周兰, 邵丹. 自组织特征映射网络在芦芽山自然保护区青杄林分类和排序中的应用[J]. 林业科学, 2014, 50(5): 1-7.

Li Linfeng, Zhang Jintun, Zhou Lan, Shao Dan. Application of Self-Organizing Feature Map to Classification and Ordination of Picea wilsonii Forest in Luya Mountain Nature Reserve[J]. Scientia Silvae Sinicae, 2014, 50(5): 1-7.

参考文献

程占红,牛莉芹,张峰. 2012. 旅游开发影响下景观特征变化研究——以芦芽山自然保护区为例. 林业经济,(8): 121-125.
(Cheng Z H, Niu L Q, Zhang F. 2012. Change of landscapes characteristics with tourism development——a case study of Luya Mountain nature reserve. Problems of Forestry Economics, (8): 121-125. [in Chinese] )
韩利群. 2007. 人工神经网络理论、设计及应用. 北京: 化学工业出版社.
李宝堂. 2010. 芦芽山自然保护区生物多样性特点及保护对策. 山西林业科技,39 (3): 49-52.
李素清,张金屯,上官铁梁. 2005. 芦芽山亚高山草甸的数量分类与排序研究. 西北植物学报,25 (10):2062-2067.
(Li S Q, Zhang J T, Shangguan T L. 2005. Quantitative classification and ordination of the subalpine meadows in Luyashan Mountain. Acta Botanica Boreali-occidentalia Sinica, 25 (10):2062-2067. [in Chinese] )
苏日古嘎,张金屯,田世广,等. 2010. 自组织特征映射网络在北京松山自然保护区山地草甸数量分析中的应用. 植物生态学报,34 (7):811-818.
(Suri G, Zhang J T, Tian S G, et al. 2010. Application of self-organizing map to quantitative analysis of mountain meadow in the Songshan Nature Reserve of Beijing,China. Chinese Journal of Plant Ecology, 34 (7): 811-818. [in Chinese] )
武秀娟,常建国,于吉祥,等. 2010. 芦芽山阴坡华北落叶松-云杉天然次生林群落特征的海拔梯度格局. 东北林业大学学报,38 (11): 10-14.
(Wu X J, Chang J G, Yu J X, et al. 2010. Spatial distribution of Larix principis-rupprechtii-Picea spp. secondary forests along elevation gradients on north facing slope of Luya Mountain, Shanxi. Journal Of Northeast Forestry University, 38 (11): 10-14. [in Chinese] )
张金屯. 2004. 数量生态学. 北京: 科学出版社.
Céréghino R,Giraudel J L,Compin A. 2001. Spatial analysis of stream invertebrates distribution in the Adour-Garonne drainage basin (France), using Kohonen self organizing maps. Ecological Modelling, 146 (1):167-180.
Chon T S,Park Y S,Moon K H,et al. 1996. Patternizing communities by using an artificial neural network. Ecological Modelling, 90 (2): 69-78.
Guisan A,Zimmermann N E. 2000. Predictive habitat distribution models in ecology. Ecological Modelling, 135 (2): 147-186.
Kohonen T. 2001. Self-organizing maps. 3^rd ed. Berlin: Springer.
Lee J,Kwak I S,Lee E,et al. 2007. Classification of breeding bird communities along an urbanization gradient using an unsupervised artificial neural network. Ecological Modelling, 203 (1): 62-71.
Lek-Ang S,Park Y S,Ait-Mouloud S,et al. 2007. Collembolan communities in a peat bog versus surrounding forest analyzed by using self-organizing map. Ecological Modelling, 203 (1): 9-17.
Mi X C,Ma K P,Zou Y B. 2005. Artificial neural network and its application in agricultural and ecological research. Acta Phytoecologica Sinica, 29 (5):863-870.
Obach M,Wagner R,Werner H,et al. 2001. Modelling population dynamics of aquatic insects with artificial neural networks. Ecological Modelling, 146 (1): 207-217.
Park Y S,Kwak I S,Chon T S,et al. 2001. Implementation of artificial neural networks in patterning and prediction of exergy in response to temporal dynamics of benthic macroinvertebrate communities in streams. Ecological Modelling, 146 (1): 143-157.
Park Y S,Céréghino R,Compin A,et al. 2003. Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters. Ecological Modelling, 160 (3): 265-280.
Park Y S,Tison J,Lek S,et al. 2006. Application of a self-organizing map to select representative species in multivariate analysis: a case study determining diatom distribution patterns across France. Ecological Informatics, 1 (3): 247-257.
Schultz A,Wieland R,Lutze G. 2000. Neurall networks in agroecological modeling-stylish application or helpful tool. Computers and Electronics in Agriculture, 29 (2):73-97.
Song M Y,Hwang H J,Kwak I S,et al. 2007. Self-organizing mapping of benthic macroinvertebrate communities implemented to community assessment and water quality evaluation. Ecological Modelling, 203 (1): 18-25.
Terbraak C J,Fand L P. 2002. Canoco reference manual and user's guide to Canoco for Windows : software for canonical community ordination ( Version 4.5 ). Wageningen: Centre for Biometry Wageningen and Microcomputer Power.
Wu P Q,Huang M S. 2005. The application of SOM on the classification of Fujian cities' functions. Economic Geography, 25 (1): 68-70.
Yuan Z R. 2000. The artificial neural network and its application. Beijing: Tsinghua University Press.
Zhang L X,Zhang F, Shangguan T L. 2001. Quantity analysis of plant communities on Mountain Luya, Shanxi. Chinese Bulletin of Botany, 18 (2):231-239;176-176.
Zhang J T,Dong Y R,Xi Y X. 2008a. A comparison of SOFM ordination with DCA and PCA in gradient analysis of plant communities in the midst of Taihang Mountains, China. Ecological Informatics, 3 (6): 367-374.
Zhang J T,Meng D P,Xi Y X. 2008b. Ordination of self-organizing feature map neural network and its application to the study of plant communities. Journal of Beijing Forestry University, 30 (1):1-5.
Zhang J T,Zhang F. 2007. Diversity and composition of plant functional groups in mountain forests of the Lishan Nature Reserve, North China. Botanical Studies, 48 (3): 339-348.

[1]	刘宝, 王民煌, 余再鹏, 林思祖, 林开敏. 中亚热带天然林改造成人工林后土壤呼吸的变化特征[J]. 林业科学, 2019, 55(4): 1-12.
[2]	高文文, 曾源, 刘宇, 衣海燕, 吴炳方, 鞠洪波. 南水北调中线水源区2000—2015年森林动态变化遥感监测[J]. 林业科学, 2019, 55(4): 97-107.
[3]	蔡小娜, 苏筱雨, 黄大庄, 沈佐锐. 基于几何形态测量学的天蛾科成虫数字化分类[J]. 林业科学, 2019, 55(1): 38-46.
[4]	周伟, 王文杰, 何兴元, 张波, 肖路, 王琼, 吕海亮, 魏晨辉. 哈尔滨城市绿地土壤肥力及其空间特征[J]. 林业科学, 2018, 54(9): 9-17.
[5]	张莹, 张晓丽, 李宏志, 黎良财. 基于改进转换分离度特征选择规则的土地覆盖分类比较[J]. 林业科学, 2018, 54(8): 88-98.
[6]	温阿敏, 郑江华, 陈梦, 穆晨, 马涛. 荒漠生态林区大沙鼠鼠洞密度的无人机遥感监测技术初探[J]. 林业科学, 2018, 54(4): 186-192.
[7]	李晓红, 陈尔学, 李增元, 李世明. 综合应用多源遥感数据的面向对象土地覆盖分类方法[J]. 林业科学, 2018, 54(2): 68-80.
[8]	刘传泽, 王霄, 陈龙现, 郭慧, 罗瑞, 周玉成. 基于随机森林算法的纤维板表面缺陷识别[J]. 林业科学, 2018, 54(11): 121-126.
[9]	邱帅, 沈柏春, 李婷婷, 郭娟, 王霁, 孙丽娜, 陈徐平, 胡绍庆. 基于随机森林算法和SRAP分子标记的桂花品种鉴定方法[J]. 林业科学, 2018, 54(1): 32-45.
[10]	唐诚, 王春胜, 庞圣江, 黄日逸, 曾杰. 西南桦人工林树皮厚度模型模拟[J]. 林业科学, 2017, 53(7): 85-93.
[11]	赵培平, 姜培坤, 孟赐福, 何珊琼. 中国亚热带4种林分类型凋落叶分解过程中¹³C NMR波谱特征[J]. 林业科学, 2017, 53(6): 127-134.
[12]	龚雪伟, 吕光辉, 马玉, 张雪妮, 何学敏, 郭振洁. 艾比湖流域2种典型荒漠盐生植物冠下土与叶片的生态化学计量特征[J]. 林业科学, 2017, 53(4): 28-36.
[13]	李明泽, 康祥瑞, 范文义. 呼中林区火烧迹地遥感提取及林火烈度的空间分析[J]. 林业科学, 2017, 53(3): 163-174.
[14]	田静, 邢艳秋, 姚松涛, 曾旭婧, 焦义涛. 基于元胞自动机和BP神经网络算法的Landsat-TM遥感影像森林类型分类比较[J]. 林业科学, 2017, 53(2): 26-34.
[15]	毛学刚, 侯吉宇, 范文义. 林隙主被动遥感协同自动识别[J]. 林业科学, 2017, 53(11): 94-103.