Developing an Artificial Neural Network (ANN) to Estimate Growth Model of Narrow-Clawed Crayfish (Pontastacus leptodactylus) in Yenice Reservoir (Çanakkale, Turkiye)

This study aims to develop an artificial neural network (ANN) to estimate the growth model of the narrow-clawed crayfish (Pontastacus leptodactylus). A total of 546 (255 males and 291 females) narrow-clawed crayfish individuals were collected monthly between July 2007 and June 2008 by using fyke nets (34 mm mesh size) from Yenice Reservoir, & Ccedil;anakkale, T & uuml;rkiye. Total length (TL) and total weight (TW) were measured, and the relationship between TL and TW was modeled using both the traditional length-weight relationship (LWR) and ANN approaches. The performance of both models was evaluated, and the ANN developed in this study yielded superior results when compared to the traditional LWR method. The R-value was found 0.95077. This value indicates that the model developed using ANN provides better results than traditional growth forecasting models. The present study demonstrates that ANNs can be used as a novel and effective approach to estimating the growth of narrow-clawed crayfish. The ANN approach can provide useful information for sustainable and successful fisheries management.