Determining temporal pattern of community dynamics by using unsupervised learning algorithms

• Published in: Ecological modelling Vol. 132; no. 1; pp. 151 - 166
• Main Authors: Chon, Tae-Soo, Park, Young-Seuk, Park, June Ho
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Amsterdam Elsevier B.V 30.07.2000; Elsevier
• Subjects: Adaptive Resonance Theory; Animal, plant and microbial ecology; Artificial neural network; Benthic macroinvertebrate community; Biological and medical sciences; Community dynamics; Fundamental and applied biological sciences. Psychology; General aspects. Techniques; Kohonen network; Methods and techniques (sampling, tagging, trapping, modelling...); Pattern analysis; Temporal variation; Unsupervised learning algorithm; Asia; Korea; Temporal variation; Community dynamics; Benthic macroinvertebrate community; Adaptive Resonance Theory; Kohonen network; Artificial neural network; Unsupervised learning algorithm; Pattern analysis; Freshwater environment; Community structure; Biotic integrity index; Animal community; Water quality; Zoobenthos; Stream; Population dynamics; Invertebrata; Algorithm; Time variation
• ISSN: 0304-3800; 1872-7026
• DOI: 10.1016/S0304-3800(00)00312-4

Analysis of patterns of temporal variation in community dynamics was conducted by combining two unsupervised artificial neural networks, the Adaptive Resonance Theory (ART) and the Kohonen network. The field data used as input for training represented monthly changes in density and species richness in selected taxa of benthic macroinvertebrates collected in the Suyong River in Korea from September 1993 to October 1994. The sampled data for each month was initially trained by ART, the weights of which preserved conformational characteristics among communities during the process of the training. Subsequently these weights were rearranged sequentially from 2 to 5 months, and were provided as input to the Kohonen network to reveal temporal variations in communities. The network was then able to extract the features of community dynamics in a reduced dimension covering the specified input period.