Application of self-organizing map to quantitative analysis of mountain meadow in the Songshan Nature Reserve of Beijing, China

doi:10.3773/j.issn.1005-264x.2010.07.006

Abstract

Abstract:

Aims Vegetation classification is an important topic in plant ecology, and many quantitative techniques for vegetation classification have been developed. The artificial neural network is a comparative new tool of data analysis. In this paper, self-organizing map (SOM) is applied to cluster analysis of mountain meadow data to determine whether SOM is suitable for classifying meadow vegetation.

Methods Data for 40 quadrats, 87 species, and six environment variables (elevation, slope, aspect, litter layer thickness, soil depth and soil density) from mountain meadow communities in the Sonshan Nature Reserve were analyzed. SOM was used to classify sample quadrats using importance values of species.

Important findings The trained SOM classified sample quadrats into seven groups: Saussurea nivea + Sanguisorba officinalis + Bupleurum chinensis, Sanguisorba officinalis + Artemisia annua + Vicia unijuga, Polygonum divaricatum + Sanguisorba officinalis + Carex rigescens, Carex rigescens + Sanguisorba officinalis + Saussurea nivea, Carex rigescens + Polygonum divaricatum + Rosa dahurica, Polygonum bistorta + Carex rigescens + Artemisia gmelinii and Carex rigescens + Saussurea iodostegia + Polygonum bistorta. The characteristics of community structure and species composition were significant. SOM classification and the dominant species enumeration in the meadow community data reflected the effects of elevation, slope, litter layer thickness and soil depth. SOM is suitable for classifying the mountain meadow communities and could be useful for assessing ecosystem quality and meadow community variations caused by environmental disturbances.

Key words: classification, mountain meadow, numerical method, self-organizing map, Songshan Nature Reserve

SURI Guga, ZHANG Jin-Tun, TIAN Shi-Guang, ZHANG Qin-Di, ZHANG Bin, CHENG Jia-Jia, LIU Su-Jun. Application of self-organizing map to quantitative analysis of mountain meadow in the Songshan Nature Reserve of Beijing, China[J]. Chin J Plant Ecol, 2010, 34(7): 811-818.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.plant-ecology.com/EN/10.3773/j.issn.1005-264x.2010.07.006

https://www.plant-ecology.com/EN/Y2010/V34/I7/811

Figures/Tables 5

Fig. 1 Classification of the quadrats of the Songshan mountain meadow by self-organizing map (SOM). I-VII represent seven meadow types. SU shows the name of sample units.

Fig. 2 Cluster analysis self-organizing map (SOM) unit with the complete linkage method using Euclidean distance. The numbers (1-49) on the dendrogram indicate their corresponding SOM units.

Fig. 3 Visualization of dominant species of the Songshan mountain meadow in the trained self-organizing map (SOM). d means important value (IV).

Table 1 Kruskal-Wallis test of six environmental variables between seven clusters of the Songshan mountain meadow

	海拔 Elevation	坡度 Slope	坡向 Slope aspect	枯枝落叶层厚度 Litter layer thickness	土壤深度 Soil depth	土壤紧实度 Soil solidity
卡方检验Chi-Square	23.751	22.628	7.117	18.163	21.255	6.779
自由度 df	6	6	6	6	6	6
p	0.001	0.001	0.310	0.006	0.002	0.342

Fig. 4 Differences of environmental variables at seven clusters of the Songshan mountain meadow (mean ± SD). Different letters indicate significant difference at the 0.05 level. A, Elevation. B, Slope. C, Aspect. D, Litter layer thickness. E, Soil depth. F, Soil solidity.

References 33

[1]	Alhoniemi E, Himberg J, Parhankangas J, Vesanto J (2000). SOM Toolbox. http://www.cis.hut.fi/projects/somtoolbox.
[2]	Céréghino R, Giraudel JL, Compin A (2001). Spatial analysis of stream invertebrates distribution in the Adour-Garonne drainage basin (France), using Kohonen self organizing maps. Ecological Modelling, 146, 167-180.
[3]	Chon TS, Park YS, Moon KH, Cha EY (1996). Patternizing communities by using an artificial neural network. Ecological Modelling, 90, 69-78.
[4]	Dong LS (董林水), Zhang XD (张旭东), Zhou JX (周金星), Song AY (宋爱云) (2007). Quantitative classification and ordination of shrub species and communities in a loess landscape of western Shanxi. Acta Ecologica Sinica (生态学报), 27, 3072-3880. (in Chinese with English abstract)
[5]	Eric BS, Christopher TR, Minshall GW, Samuel RR (2002). Regional patterns in periphyton accrual and diatom assemblage structure in a heterogeneous nutrient landscape. Canadian Journal of Fisheries and Aquatic Sciences, 59, 564-577.
[6]	Foody GM (1999). Applications of the self-organising feature map neural network in community data analysis. Ecological Modelling, 120, 97-107.
[7]	Fu BQ (付必谦) (2006). Principal and Method of Ecology Experimental (生态学实验原理和方法). Science Press, Beijing. (in Chinese)
[8]	Gao J (高隽) (2007). Practical Example of Artificial Neural Network Principal and Simulation (人工神经网络原理及仿真实例). Mechanical Industrial Press, Beijing. (in Chinese)
[9]	Han LQ (韩力群) (2007). Theory, Design and Application of Artificial Neural Network (人工神经网络理论、设计及应用). Chemical Industry Press, Beijing. (in Chinese)
[10]	He HQ (何惠琴), Li SC (李绍才), Sun HL (孙海龙), Liu SC (刘世昌), Xiong WL (熊文兰) (2008). Quantitative classification and ordination of Jingping hydropower station, Sichuan Province, China. Acta Ecologica Sinica (生态学报), 28, 3706-3712. (in Chinese with English abstract)
[11]	Henning KS, Hans Estrup A, Kathrin K (2005). Rejecting the mean: estimating the response of fen plant species to environmental factors by non-linear quantile regression, Journal of Vegetation Science, 16, 373-382.
[12]	Kohonen T (1982) . Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43, 59-69.
[13]	Kohonen T (2001). Self-Organizing Maps. Springer, Berlin.
[14]	Lee J, Kwak IS, Lee E, Kim KA (2007). Classification of breeding bird communities along an urbanization gradient using an unsupervised artificial neural network. Ecological Modelling, 203, 62-71.
[15]	Lek-Ang S, Park YS, Ait-Mouloud S, Deharveng L (2007). Collembolan communities in a peat bog versus surrounding forest analyzed by using self-organizing map. Ecological Modelling, 203, 9-17.
[16]	Niu LL (牛丽丽), Yu XX (余新晓), Yue YJ (岳永杰) (2008). Spatial patterns of different age-class individuals in Pinus tabulaeformis forest in Songshan Nature Reserve of Beijing, China. Chinese Journal of Applied Ecology (应用生态学报), 19, 1414-1418. (in Chinese with English abstract)
[17]	Obach M, Wagner R, Werner H, Schmidt HH (2001). Modelling population dynamics of aquatic insects with artificial neural networks. Ecological Modelling, 146, 207-217.
[18]	Park YS, Céréghino R, Compin A, Lek S (2003a). Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters. Ecological Modelling, 160, 265-280.
[19]	Park YS, Jianbo C, Lek S, Wenxuan C, Brosse S (2003b). Conservation strategies for endemic fish species threatened by the Three Gorges Dam. Conversation Biology, 17, 1748-1758.
[20]	Park YS, Kwak IS, Chon TS, Kim JK, Jørgensen SE (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, 143-157.
[21]	Park YS, Tison J, Lek S, Giraudel JL, Coste M, Delmas F (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, 247-257.
[22]	Song MY, Hwang HJ, Kwak IS, Ji CW, Oh YN, Youn BJ, Chon TS (2007). Self-organizing mapping of benthic macroinvertebrate communities implemented to community assessment and water quality evaluation. Ecological Modelling, 203, 18-25.
[23]	Wu S (吴姗), Qin DH (覃德华), Bi XL (毕晓丽), Wang XC (王秀春), Ge JP (葛剑平) (2004). Purifying service of Songshan mountain and its value. Journal of Beijing Normal University (Natural Science) 北京师范大学学报 (自然科学版)), 40, 386-389. (in Chinese with English abstract)
[24]	Zhang LJ (张良均), Cao J (曹晶), Jiang SZ (蒋世忠) (2008). Practical Course of Neural Network (神经网络实用教程). Mechanical Industrial Press, Beijing. (in Chinese)
[25]	Zhang JT (张金屯) (2004). Quantitative Ecology (数量生态学). Science Press, Beijing. (in Chinese)
[26]	Zhang JT, Dong Y, Xi Y (2008). 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, 367-374.
[27]	Zhang JT (张金屯), Meng DP (孟东平), Xi YX (席跃翔) (2008). Ordination of self-organizing feature map neural network and its application in the study of plant communities. Journal of Beijing Forestry University (北京林业大学学报), 30, 1-5. (in Chinese with English abstract)
[28]	Zhang JT (张金屯), Yang HX (杨洪晓) (2007). Application of self-organizing neural networks to classification of plant communities in Pangquangou Nature Reserve, North China. Acta Ecologica Sinica (生态学报), 27, 1005-1010. (in Chinese with English abstract)
[29]	Zhang JT, Zhang F (2007). Diversity and composition of plant functional groups in mountain forests of the Lishan Nature Reserve, North China. Botanical Studies, 48, 339-348.
[30]	Zhang Y (张赟), Zhao YZ (赵亚洲), Zhang CY (张春雨), Zhao XH (赵秀海) (2009). Structure and spatial distribution of Pinus tabulaeformis population in the Songshan Nature Reserve, Beijing, China. Chinese Journal of Applied and Environmental Biology (应用与环境生物学报), 15, 175-179. (in Chinese with English abstract)
[31]	Zhou R (周睿), Ge JP (葛剑平), Yu B (于波), Liu LJ (刘丽娟), Wu JG (吴记贵) (2007). Simulation of forest dynamics at Songshan Mountain, Beijing. Journal of Beijing Forestry University (北京林业大学学报), 29, 19-25. (in Chinese with English abstract)
[32]	Zhou R (周睿), Wang H (王辉), Ge JP (葛剑平), Xiong YC (熊友才), Wu JG (吴记贵) (2006). Vegetation dynamics and patterns of change in functional protection subzones in Songshan National Nature Reserve, Beijing. Biodiversity Science (生物多样性), 14, 470-478. (in Chinese with English abstract)
[33]	Zuzana R, Michal H (2008). Changes in nutrient limitation of spring fen vegetation along environmental gradients in the West Carpathians. Journal of Vegetation Science, 19, 613-620.