Supervised classification of Buxus hyrcana plant communities using artificial neural network

In this research, the application of Artificial Neural Network or MLP method in the process Assignment of relevé-groups/ plant communities allocation was evaluated using Buxus hyrcana forests database. For this purpose, firstly, the ecological and sociological groups of B. hyrcana were determined using TWINSPAN and Braun-Blanquet method, respectively. The results of both numerical and expert based classification dendrogram of the B. hyrcana communities, which included seven levels of classification as primary groups/plant communities, were introduced to MLP. Then, with assignments in three sets of training (70%), test (15%) and validation (15%), the MLP classification was performed on each level of the two dendrogram. The results showed that by increasing the level of classification, the degree of adaptation of the MLP result to primary results of TWINSPAN (99% to 60%) and Braun-Blanquet (98% to 68%) from the cutoff level of 1 to 7. Results of sensitivity and kappa cross tab coefficients, except in 7 cut level, imply that the quality of MLP groups based on TWINSPAN primary ecological group is upper than primary Braun-Blanquet groups.Appropriate adaptation of the MLP results in Buxus hyrcana plant communities classification with the TWINSPAN and Braun-Blanquet ecological/syntaxa groups at the fifth cut level of both dendrograms indicate that application of MLP aim at a reliable results in plant community classification. So our result reiterate that MLP could be introduced as a suitable method in the assignment of releves to plant communities.