Application of self-organizing neural networks to classification of plant communities in Pangquangou Nature Reserve, North China

Abstract

Vegetation classification is an important topic in plant ecology and many quantitative techniques for classification have been developed in the field. The artificial neural network is a comparatively new tool for data analysis. The self-organizing feature map (SOFM) is powerful tool for clustering analysis. SOFM has been applied to many research fields and it was applied to the classification of plant communities in the Pangquangou Nature Reserve in the present work. Pangquangou Nature Reserve, located at 37°20′–38°20′ N, 110°18′–111°18′ E, is a part of the Luliang Mountain range. Eighty-nine samples (quadrats) of 10 m × 10 m for forest, 4 m × 4 m for shrubland and 1 m × 1 m for grassland along an elevation gradient, were set up and species data was recorded in each sample. After discussion of the mathematical algorism, clustering technique and the procedure of SOFM, the classification was carried out by using NNTool box in MATLAB (6.5). As a result, the 89 samples were clustered into 13 groups representing 13 types of plant communities. The characteristics of each community were described. The result of SOFM classification was identical to the result of fuzzy c-mean clustering and consistent with the distribution patterns of vegetation in the study area and shows significant ecological meanings. This suggests that SOFM may clearly describe the ecological relationships between plant communities and it is a very effective quantitative technique in plant ecology research.

References

1. Chen T G, Zhang J T (2000). A studyof plant community diversity in Shenweigou of the Pengquangou Reserves,Shanxi. Acta Botanica Boreali-OccidentaliaSinica, 20(4): 638–646 (in Chinese)
2. Cheng Z H, Zhang J T, Wu B H, Niu L Q (2006). Relationships between tourism development and vegetation environmentin Luya mountain nature reserve: vegetation landscape types and ordination. Acta Ecologica Sinica, 26(6): 1940–1946 (in Chinese)
3. Feisi Center for Scientific Products. (2004). MATLAB 6.5 Designe and analysisof artificial neural network. Beijing: Electronic Industry Press (in Chinese)
4. Li B, Zhang J T (2003). Analysisof relationships between vegetation and climate variables in LoessPlateau. Acta Botanica Sinica, 23(1): 82–89 (in Chinese)
5. Li S C and Zheng D (2003). Progressof the application of artificial neural network to earth science. Progress of Earth Science, 18(1): 69–70 (in Chinese)
6. Schreer J F, Hines R J O, Kovacs K M (1998). Classification of dive profiles:A comparison of statistical clustering techniques and unsupervisedartificial neural networks. Journal ofAgricultural Biological and Environmental Statistics, 3(4): 383–404. doi:10.2307/1400572
7. Tran L T, Knight C G, O'Neill R V (2003). Self-organizing maps for integratedenvironmental assessment of the Mid-Atlantic region. Environmental Management, 31(6): 822–835. doi:10.1007/s00267-003-2917-6
8. Wu P Q and Huang M S (2005). The applicationof SOM on the classification of Fujian cities' functions. Economic Geography, 25(1): 68–70 (in Chinese)
9. Yang H X, Lu Z Y (1981). Methodsof quantitative classification in plant ecology. Beijing: Science Press (in Chinese)
10. Yu S X (1995). Introduction to mathematical ecology. Beijing: Scientific LiteraturePress (in Chinese)
11. Yuan Z R (2000). The artificial neural network and its application. Beijing: Qinghua University Press (in Chinese)
12. Zhang F, Zhang J T (2000). Progressof quantitative classification and ordination research in China. Journal of Shanxi University (Nat Sci Ed), 23(3): 278–282 (in Chinese)
13. Zhang J T (1994a). A comparison of fuzzy c-mean clustering and TWINSPAN. Journal of Wuhan Botanical Research, 12(1): 11–17 (in Chinese)
14. Zhang J T (1994b). Canonical indicator species analysis, a new extrinsicclassification technique. Acta PhytoecologicaSinica, 18(4): 331–337 (in Chinese)
15. Zhang J T (2004a). Fuzzy mathematic classification and ordination of plantcommunities in Pangquangou Natural Reserve. Journal of Beijing Normal University (Natural Science), 40(2): 249–254 (in Chinese)
16. Zhang J T (2004b). Quantitative ecology. Beijing: Science Press (in Chinese)
17. Zhang J T (2005). Canonical principal component analysis of forest communitiesin Lishan Natural Reserve, Shanxi Province, North China. Journal of Biomathematics, 20(2): 213–218 (in Chinese)
18. Zhang J T, Chen T G (2004). Variationof plant communities along an elevation gradient in the PengquangouReserves, North China. Community Ecology, 5(2): 227–233. doi:10.1556/ComEc.5.2004.2.10