ARTIFICIAL NEURAL NETWORKS AS NEW ALTERNATIVE METHOD TO ESTIMATING SOME POPULATION PARAMETERS OF TIGRIS LOACH (OXYNOEMACHEILUS TIGRIS (HECKEL, 1843)) IN THE KARASU RIVER, TURKEY

In this study, a new method (Artificial Neural Networks) to estimating some population parameters of Tigris loach (Oxynoemacheilus tigris (Heckel, 1843)) collected between 2014 and 2015 in 14 different stations from Karasu River (East Anatolia, Turkey). The total length and weight of the species ranged from 62 to105 mm and from 1.7 to 10.9 g for females and 65 to 100 mm and from 2.4 to 9.8 g for males, respectively. The new maximum length for O. tigris was found to be 105 mm in this study. The length-weight relation of O. tigris was carried out with artificial neural networks (ANNs) and length-weight relationships (LWRs). The results obtained were compared. Length-weight relationships of O. tigris were found as W=0.0049*L-3.29 , R-2 =0.95 for all individuals. According to these values, the growth type of this species was positive allometric (b>3) for all individuals. Regression analysis showed that fish length has high significant correlation with weight (R=0.97, R-2 =0.95, F-1,F-185=31930.3, P<0.001). According to the comparison of the results obtained with MAPE (%), ANNs provide better results than the LWRs. The results of this study could give useful insight that ANNs can be evaluated as an alternative for length-weight relation estimation. The condition factor values (min-max) were observed as 0.680-1.239 for females and 0.699-1.074 for males. No studies have been done before on this species population parameters.