EVALUATION OF GROWTH IN PIKE (Esox lucius L., 1758) USING TRADITIONAL METHODS AND ARTIFICIAL NEURAL NETWORKS

Abstract

Abstract. The present study was performed to assess the population structure and growth of pike in Mogan Lake using length-weight relationships, von Bertalanffy equations and artificial neural networks between February 2013 and March 2014. The age of Esox lucius caught in Mogan Lake ranged between I to VII years. The fork length of the fish ranged from 27.5 cm to 70.0 cm, and the body weight of the fish ranged from 200 g to 2820 g. The von Bertalanffy growth lengths were 130.30 for females, 122.70 for males and 126.50 for all individuals. The von Bertalanffy growth weights were 18889 for females, 14881 for males and 16688 for all pike. The results obtained using the artificial neural networks and regression technique were compared to those obtained using the growth rate of the fish caught from the natural environment and von Bertalanffy growth model. Artificial neural networks are an alternative to von Bertalanffy growth models.

Artificial neural networks approach in length-weight relation of crayfish (Astacus leptodactylus Eschscholtz, 1823) in Eğirdir Lake, Isparta, Turkey

“…Environmental factors may impact crayfish growth by affecting foraging efficiency, feeding behavior, and the availability and [14,[33][34][35][36].…”

Growth parameters with traditional and artificial neural networks methods of big-scale sand smelt (Atherina boyeri Risso, 1810)

“…For years, many scientists have studied the superiority of artificial intelligence (AI) in solving regression problems over conventional classification and statistical models. Benzer and Benzer, (2016) studied the performance of an artificial neural network model, as one of the benchmark modeling techniques in Machine Learning studies, and a statistical linear regression model in fish growth in Mogan Lake. Elsewhere, Benzer et al (2022) classified the fish age by taking into account the biological characteristics of the fish.…”

“…Since ANNs have a nonlinear structure, they perform better than traditional methods in terms of performance criteria. They can detect nonlinear relationships without any hypothesis (Hyun et al, 2005;Türeli Bilen et al;Benzer and Benzer, 2016;Benzer and Benzer, 2017;Özcan and Serdar, 2018;Özcan and Serdar, 2019;Özcan, 2019;Benzer, 2020;Benzer and Benzer, 2020a;Benzer and Benzer, 2020b).…”

The Growth of Crayfish, which Serves as an Indicator of Clean and Healthy Water Ecosystems in the Mediterranean Region

“…There have been numerous studies on predictive modeling using neural networks for the growth of aquatic organisms, specifically focusing on fish (Benzer and Benzer 2016, Benzer and Benzer 2017, Özcan and Serdar 2018, Özcan and Serdar 2019, Özcan 2019, Benzer and Benzer 2020, Benzer and Benzer 2023b, Akkan et al 2024) and crayfish (Türeli Bilen et al 2011, Benzer et al 2015, Benzer and Benzer 2018, Benzer and Benzer 2022.…”