A comparison of SOFM ordination with DCA and PCA in gradient analysis of plant communities in the midst of Taihang Mountains, China

Abstract The self-organizing feature map (SOFM) neural network is attractive for ecological investigations for its power in analyzing and solving complicated and non-linear matters and for its freedom from restrictive assumptions that underlie many ordination techniques. The SOFM ordination were described and compared with DCA and PCA, the most common ordination methods, in analysis of plant communities in the midst of Taihang Mountains in China. The dataset consisted of importance values of 88 species in 68 quadrats of 10 m × 20 m. The SOFM ordination successfully displayed quadrats in species space and revealed ecological gradients. The distribution of quadrats and community types on SOFM ordination diagram was fully interpreted. SOFM, DCA and PCA produced consistent results, i.e. their axes were significantly correlated with elevation, soil organic matter, N, P, K and slope. These variables are important to development and distribution of plant communities in the Taihang Mountains. SOFM ordination is effective for analysis of large-dataset of plant communities and has some advantages compared with DCA and PCA. And SOFM is conduced for combination of ordination and classification in vegetation study.

[1]  László Orlóci,et al.  Multivariate Analysis in Vegetation Research , 1975 .

[2]  Hugh G. Gauch,et al.  Multivariate analysis in community ecology , 1984 .

[3]  Mi-Young Song,et al.  Characterization of benthic macroinvertebrate communities in a restored stream by using self-organizing map , 2006, Ecol. Informatics.

[4]  P. Greig-Smith,et al.  QUANTITATIVE PLANT ECOLOGY , 1959 .

[5]  Jintun Zhang.  Succession analysis of plant communities in abandoned croplands in the eastern Loess Plateau of China , 2005 .

[6]  Ter Braak,et al.  Canoco reference manual and CanoDraw for Windows user''s guide: software for canonical community ord , 2002 .

[7]  Huang Min-sheng,et al.  THE APPLICATION OF SOM ON THE CLASSIFICATION OF FUJIAN CITIES' FUNCTIONS , 2005 .

[8]  Erich Tasser,et al.  Impact of land use changes on mountain vegetation , 2002 .

[9]  J.-T. Zhang.  A combination of fuzzy set ordination with detrended correspondence analysis: One way to combine multi-environmental variables with vegetation data , 1994, Vegetatio.

[10]  M. Wong,et al.  Evaluation of major constraints to revegetation of lead/zinc mine tailings using bioassay techniques. , 2002, Chemosphere.

[11]  Jay E. Anderson,et al.  Gradient analysis of vegetation dominated by two subspecies of big sagebrush. , 1986 .

[12]  B. Manly.  Multivariate Statistical Methods : A Primer , 1986 .

[13]  Friedrich Recknagel,et al.  Ecological Informatics: Understanding Ecology by Biologically-Inspired Computation , 2003 .

[14]  B. Glaser,et al.  Soil organic matter quantity and quality in mountain soils of the Alay Range, Kyrgyzia, affected by land use change , 2000, Biology and Fertility of Soils.

[15]  Young-Seuk Park,et al.  Patternizing communities by using an artificial neural network , 1996 .

[16]  D B Kell,et al.  Rapid identification using pyrolysis mass spectrometry and artificial neural networks of Propionibacterium acnes isolated from dogs. , 1994, The Journal of applied bacteriology.

[17]  Jintun Zhang,et al.  A study on relations of vegetation, climate and soils in Shanxi province, China , 2002, Plant Ecology.

[18]  Prediction of Changes in Soil Moisture Associated with Climatic Changes and Their Implications for Vegetation Changes: Waves Model Simulation on Taihang Mountain, China , 2003 .

[19]  Jintun Zhang,et al.  Relationships between vegetation and climate on the Loess Plateau in China , 2006, Folia Geobotanica.

[20]  Young‐Seuk Park,et al.  Collembolan communities in a peat bog versus surrounding forest analyzed by using self-organizing map , 2007 .

[21]  M. Hill,et al.  Data analysis in community and landscape ecology , 1987 .

[22]  Orie L. Loucks,et al.  A Gradient Analysis of Southern Wisconsin Forests , 1977 .

[23]  Giles M. Foody,et al.  Applications of the self-organising feature map neural network in community data analysis , 1999 .

[24]  Jintun Zhang,et al.  A comparison of three methods of multivariate analysis of upland grasslands in North Wales , 1994 .

[25]  M. O. Hill,et al.  DECORANA - A FORTRAN program for detrended correspondence analysis and reciprocal averaging. , 1979 .

[26]  Sovan Lek,et al.  Application of the Self-organizing Mapping and Fuzzy Clustering to Microsatellite Data : How to Detect Genetic Structure in Brown Trout (Salmo trutta) Populations , 2000 .

[27]  Robert J. Schalkoff,et al.  Pattern recognition - statistical, structural and neural approaches , 1991 .

[28]  C. Braak.  Canonical Correspondence Analysis: A New Eigenvector Technique for Multivariate Direct Gradient Analysis , 1986 .

[29]  Sigismond deR. Diettrich.  Florida's Climatic Extremes: Cold Spells and Freezes , 1949 .

[30]  Xiuju Fu,et al.  Artificial Neural Networks , 2009, Wiley Encyclopedia of Computer Science and Engineering.

[31]  Pierre Demartines,et al.  Data Analysis: How to Compare Kohonen Neural Networks to Other Techniques? , 1991, IWANN.

[32]  David W. Roberts,et al.  Ordination on the basis of fuzzy set theory , 1986, Vegetatio.

[33]  Sovan Lek,et al.  A comparison of self-organizing map algorithm and some conventional statistical methods for ecological community ordination , 2001 .

[34]  M. Hill,et al.  Detrended correspondence analysis: an improved ordination technique , 1980 .

[35]  S. Lek,et al.  Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters , 2003 .