Abstract:Vegetation classification is an important topic in plant ecology, and many quantitative techniques for classification have been developed in this field. The artificial neural network is a comparative new tool of data analysis, and self-organizing feature map (SOFM) is powerful in clustering analysis. SOFM has been applied to many research fields, and it was applied to the classification of plant cimmunities 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 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 procedure of SOFM, the classification was carried out by use of the NNTool box in MATLAB (65). As the result, the 89 samples were clustered into 13 groups, representing 13 types of plant communities. The characteristics of each community were described in the text. The result of SOFM classification was identical to the result of fuzzy c-mean clustering and consistent to the reality of vegetation in the study area, and show 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.