Artificial neural networks and genetic algorithm approach to determine length-weight, length frequency relationships of Lessepsian crab, Charybdis (Goniohellenus) longicollis, Leene, 1938 in the Iskenderun Bay, Turkey

Begüm ÇIĞŞAR, Deniz ÜNAL, Canan TÜRELİ


Mathematical models are created to have information about growth of living beings. Biometric models such as length-frequency and weight-length are also distributions that give information about growth of livings. In this study, the growth of Charybdis (Goniohellenus) longicollis Leene, 1938 is given by von Bertalanffy growth curve, which is a continuous growth model, using length frequency (Carapace Width) data. The TropFishR package program in the R program is used to estimate the von Bertalanffy growth curve. Electronic Length Frequency Analysis of Response Surface Analysis and Genetic Algorithm methods included in this package program are applied, and both methods are compared according to the Rn max value. As a result, the Rn max values of the estimated von Bertalanffy parameters for both methods are found to be equal.

In addition to classical linear regression method, Artificial Neural Networks method is used to estimate the weight-length relationship of the species. The Artificial Neural Networks (ANNs) method is presented by two models. In the first ANNs model, CW was used to estimate the weight. In the second model, age was added, which was estimated in the first part of this study, to the first ANNs model.

Mean Squared Error,  and Mean Absolute Percentage Error criteria are taken into account when comparing the three models used in weight estimation. It is seen that the Artificial Neural Networks model with the age variable added to the weight estimation has the best performance.


Artificial Neural Networks, Genetic Algorithm, Growth, Length-weight relationship

Full Text:



Ataseven B (2013). Yapay sinir ağları ile öngörü modellemesi.

CIESM, 2015. Atlas of exotic species in the Mediterranean Sea.

Clottey, M. N. K. (2020). Population dynamics and reproductive studies of three commercially important sparid species from Ghanaian waters (Doctoral dissertation, University of Cape Coast).

Faris H, Alkasassbeh M, Rodan A (2014). Artificial neural networks for surface ozone prediction: Models and analysis. Polish Journal of Environmental Studies, 23, 341–348.

Günther F, Fritsch S (2010). Neuralnet: Training of neural networks. The R journal, 2(1), 30-38.

Hernández, J. J. C., Fernández, L. P. S., Bautista, I. H., & López, J. H. (2017). Modelo basado en redes neuronales artificiales para la evaluación de la calidad del agua en sistemas de cultivo extensivo de camarón. Tecnología y ciencias del agua, 8(5), 71-89.

Holthuis, L. B. 1961. Report on a collection of Crustacea Decapoda and Stomatopoda from Turkey and Balkans.Zool. Verhan, 47: 1-67.

Kindong, R., Wu, F., Tian, S., Zhu, J., Dai, X., Wang, J., & Dai, L. (2020). Biological parameters estimate for the sickle pomfret (Taractichthys steindachneri) in the west-central and eastern Pacific Ocean.

Luan, J., Zhang, C., Xu, B., Xue, Y., & Ren, Y. (2018). Modelling the spatial distribution of three Portunidae crabs in Haizhou Bay, China. PloS one, 13(11), e0207457.

Marun, S. (2016). Some biological characteristics of Lessepsian crab Charybdis longicollis Leene, 1938 (Portunidae: Decapoda) in Iskenderun Bay. Graduate Thesis, Iskenderun Technical University, Institute of Engineering and Science, Department of Fisheries, Iskenderun/Hatay, (In Turkish).

Mildenberger, T. K., Taylor, M. H., & Wolff, M. (2017). TropFishR: an R package for fisheries analysis with length-frequency data. Methods in Ecology and Evolution, 8(11), 1520-1527.

Özcan E (2019). Artıfıcıal Neural Networks (A New Statıstıcal Approach) Method In Length-Weıght Relatıonshıps Of Alburnus mossulensıs In Murat Rıver (Palu-Elazığ) Turkey. Applied Ecology And Envıronmental Research,17(5), 10253-10266.

Ozcan, T., Katagan, T. and Kocatas, A. 2005. Brachyuran crabs from Iskenderun Bay. Crustaceana, 78(2): 237-244.

Pauly D 1980 On the interrelationships between natural mortality, growth parameters and mean environmental temperature in 175 fishstocks J. Cons. Int. Explor. Mer. 39 175–92

Pauly, D., & David, N. (1981). ELEFAN I, a BASIC program for the objective extraction of growth parameters from length-frequency datal (Vol. 28).

Pauly, D., & Greenberg, A. (2013). ELEFAN in R: A new tool for length frequency analysis. In Fisheries Centre Research Reports (Vol. 21).

Pauly, D., & Morgan, G. R. (1987). Length-based methods in fisheries research. In ICLARM Conference Proceedings 13.

Peter, E. E., & Precious, E. E. (2018). Skill comparison of multiple-linear regression model and artificial neural network model in seasonal rainfall prediction-North East Nigeria.Asian Research Journal of Mathematics, 1-10.

Petersen, C. G. J. (1891). Eine Methode zur Bestimmung des Alters under Wushses der Fische. Mitteilungen der Deutch Seefischerei, 11, 226-235.

Pitcher, T. J. (2002). A bumpy old road: size‐based methods in fisheries assessment. Handbook of Fish Biology and Fisheries: Fisheries, 2, 189-210.

Priddy K L, Keller P E (2005). Artificial neural networks: an introduction (Vol. 68). SPIE press.

Ricker W E (1975). Computation and interpretation of biological statistics of fish populations. Bulletin of the Fisheries Research Board of Canada 191, 1–382

Schwamborn, R., & Moraes-Costa, D. F. (2019). Growth and mortality of endangered land crabs (Cardisoma guanhumi) assessed through tagging with PITs and novel bootstrapped methods. arXiv preprint arXiv:1909.03311.

Sor, R., Park, Y. S., Boets, P., Goethals, P. L., & Lek, S. (2017). Effects of species prevalence on the performance of predictive models. Ecological Modelling, 354, 11-19.

Sun L, Xiao H, Li S, Yang D (2009). Forecasting Fish Stock Recruitment and PlANNsing Optimal Harvesting Strategies by Using Neural Network.JCP,4(11), 1075-1082.

Tirelli, T., Favaro, L., Gamba, M., & Pessani, D. (2011). Performance comparison among multivariate and data mining approaches to model presence/absence of Austropotamobius pallipes complex in Piedmont (North Western Italy). Comptes rendus biologies, 334(10), 695-704.

Türeli Bilen C, Kokcu P, Ibrikci T (2011). Application of artificial neural networks (ANNs) for weight predictions of blue crabs (Callinectes sapidus Rathbun, 1896) using predictor variables. Mediterranean Marine Science,12(2), 439-446

Von Bertalanffy L (1938). A quantitative theory of organic growth (inquiries on growth laws. II). Human Biology 10, 181–213.

Wang, K., Zhang, C., Xu, B., Xue, Y., & Ren, Y. (2020). Selecting optimal bin size to account for growth variability in Electronic LEngth Frequency ANalysis (ELEFAN). Fisheries Research, 225, 105474.

Yu, R., Leung, P., & Bienfang, P. (2006). Predicting shrimp growth: artificial neural network versus nonlinear regression models. Aquacultural Engineering, 34(1), 26-32.

Zhang, Z., Capinha, C., Weterings, R., McLay, C. L., Xi, D., Lü, H., & Yu, L. (2019). Ensemble forecasting of the global potential distribution of the invasive Chinese mitten crab, Eriocheir sinensis. Hydrobiologia, 826(1), 367-377.


  • There are currently no refbacks.