QSAR study for choosing biological and chemical parameters of water in the Anzali international wetland in growth Oligochaetes (L. Claparedeianus, L. Hoffmeisteri)
Subject Areas : International Journal of Bio-Inorganic Hybrid Nanomaterials
Keywords: QSAR, MLR, Genetic algoritm, Limnodrilus claparedeianus,
Abstract :
The Biological and chemical properties of water in the Anzali International Wetland were estimated using multiple linear regression (MLR), artificial neural network (ANN), and genetic algorithm(GA) and simulated annealing algorithm (SA) as optimization methods. The obtained results from MLR-MLR, SA-ANN and GA-ANN techniques were compared and a high predictive ability was observed for the GA-ANN model with the root-mean-sum-squared error (RMSE) of 0.0079 and 0.01535 in L. Claparedeianus and L. hoffmeisteri, respectively. The results obtained using the GA-ANN method indicated that abundance of L. Claparedeianus and L. hoffmeisteri in the Anzali International Wetland depends on different parameters, which include: that NH3 concentration, total nitrogen (TN), dissolved oxygen (DO), Sodium chloride (Sali), Nitrat (NO3), total phosphorus (TP), Biochemical Oxygen demand (BOD), Total dissolved solids (TDS) and electrical conductivity (EC) in water. In conclusion, the comparison of the quality of the ANN with different MLR methods showed that GA-ANN has a better predictive capability.