Use of classification tree methods to study the habitat requirements of tench (Tinca tinca) (L., ۱۷۵۸)

Classification trees (J۴۸) were induced to predict the habitat requirements of tench (Tinca tinca). ۳۰۶ datasets were used for the given fish during ۸ years in the river basins in Flanders (Belgium). The input variables consisted of the structural-habitat (width, depth, gradient slope and distance from the source) and physic chemical (pH, dissolved oxygen, water temperature and electric conductivity), and the output ones were the abundance and presence/absence of tench. To find the best performance model, a three-fold cross validation was applied on the entire dataset. In order to evaluate the model stability, the dataset were remixed in ۵ times, obtaining in total ۱۵ different model training and validation events. The effect of pruning on the reliability and model complexity was tested in each subset. The performance evaluation was based on a combination of the number of Correctly Classified Instances (CCI) and Kappa statistic. The results showed that the predictive performance evaluation was suitable, confirming the reliability of classification trees methods. The overall average of CCI and Kappa for the prediction of tench was obtained ۷۵.۸% and ۰.۵۳. When analyzing the ecological relevance of classification trees, it seemed that the structural-habitat variables were important predictors compared to physic chemical variables.   REFERENCES Belpaire, C., Smolders, R., Vanden A.I., Ercken, D., Breine, J., Van Thuyne, G. and Ollevier, F. (۲۰۰۰) An Index of Biotic Integrity characterizing fish populations and the ecological quality of Flandrian water bodies, Hydrobiologia. ۴۳۴, ۱۷-۳۳. Breiman, L., Friedman, J.H., Olshen, R.A. and Stone, C.J. (۱۹۸۴) Classification and regression trees, Pacific Grove, Wadsworth. Brosse, S., Guegan, J.F., Tourenq, J.N. and Lek, S. (۱۹۹۹) The use of artificial neural network to assess fish abundance and spatial occupancy in the littoral zone of a mesotrophic lake, Ecol. Mod. ۱۲۰, ۲۹۹-۳۱۱. Casselman, J.M. and Lewis, C.A. (۱۹۹۶) Habitat requirements of northern pike (Esox lucius L.), Canadian J. Fish. Aqu. Sci., ۵۳, ۱۶۱-۱۷۴. Cohen, J. (۱۹۶۰). A coefficient of agreement for nominal scales. Edu. Psych. Meas. ۲۰, ۳۷-۴۶. Dakou, E., Goethals, P.L.M., D’heygere, T., Dedecker, A.P., Gabriels, W. and De Pauw, N. (۲۰۰۶a) Development of artificial neural network models predicting macroinvertebrate taxa in the river Axios (Northern Greece), Animal Limnology. ۵, ۱۰-۱۷. Dakou, E., D’heygere, T., Dedecker, A.P., Goethals, P.L.M., Gabriels, W. Lazaridou, M. and De Pauw, N. (۲۰۰۶b) Decision tree models for prediction of macroinvertebrate taxa in the river Axios (Northern Greece), Aquatic Ecology. ۴۱, ۳۹۹-۴۱۱. D’heygere, T., Goethals, P. and De Pauw, N. (۲۰۰۳) Use of genetic algorithms to select input variables in decision tree models for the prediction of benthic macroinverteberates, Ecological modeling. ۱۶۰, ۲۹۱-۳۰۰. Dedecker, A.P., Goethals, P.L.M., Gabriels, W. and De Pauw, N. (۲۰۰۲) Comparison of Artificial Neural Network (ANN) model development methods for prediction of macroinvertebrates communities in the Zwalm river basin in Flanders, Belgium, Sci. World J. ۲, ۹۶- ۱۰۴. Donnely, R.E., Caffrey, J.M. and Tierney, D.M. (۱۹۹۸) Movement of bream (Abramis brama (L.)), rudd X bream hybrid, tench, Tinca tinca (L.) and pike, Esox lucius in an Irish canal habitat, Hydro. ۳۷۱-۳۷۲, ۳۰۵-۳۰۸. Faraway, J. and Chatfield, C. (۱۹۹۸) Time series forecasting with neural network: a comparative study using airline data, Appl. Stat., ۴۷ (۲), ۲۳۱-۲۵۰. Fielding, A.H. and Bell, J.F. (۱۹۹۷). A review method for the assessment of prediction errors in conservation presence and absence model, Env. Cons. ۲۴, ۳۸-۴۹. Gaston, K.J. and Blackburn, T.M. (۱۹۹۹) A critique for macroecology, Oikos. ۸۴, ۳۵۳-۳۶۸. Goethals, P.L.M., Dedcker, A., Gabriels, W. and De Pauw, N. (۲۰۰۲) Development and application of predictive river ecosystem models based on classification trees and artificial neural networks. Ecological informatics, Understanding ecology by biologically inspired computation. (ed. Recknagel), Springer, Berlin: ۴۳۲ p. Goethals, P. L. M. (۲۰۰۵) Data driven development of predictive ecological models for benthic macroinvertebrates in rivers. PhD thesis, Ghent University, Belgium, ۳۷۷ p. Gonzalez, G., Maze, R.A., Dominguez, J. and Pena, J. C. (۲۰۰۰) Trophic ecology of Tinca Tinca in two different habitats in North-West of Spain, Cybium. ۲۴, ۱۲۳-۱۳۸. Gray, R.H. and Daule, D.D. (۲۰۰۱) Some life history characteristics of cyprinids in the Handford reach, mid-Columbia River, North. Sci. ۷۵, ۱۲۲-۱۳۶. Grenouillet, G.l., Pont, D. and Seip, K.L. (۲۰۰۲) Abundance and species richness as a function of food resources and vegetation structure: juvenile fish assemblages in rivers, Ecography. ۲۵, ۶۴۱-۶۵۰. Harig, A.L. and Bain, M.B. (۱۹۹۸) Defining and restoring biological integrity in wilderness Lakes, Ecol. Appl. Sci. ۸, ۷۱-۸۷. Kaastra, I. and Boyd, M. S. (۱۹۹۵) Forecasting future trading volume using neural networks, Journal of Future Markets. ۱۵, ۹۵۳-۹۷۰. Kerle, F., Zollner, F., Kappus, B., Marx, W. and Giesecke, J. (۲۰۰۱) Fish habitat and vegetation modelling in floodplains with CASIMIR. CFR project report ۱۳, IWS, University of Stuttgart, ۷۵ p. Manel, S., Williams, H.C. and Ormerod, S.J. (۲۰۰۱) Evaluating presence-absence models in Ecology: the need to account for prevalence, J. Appl. Ecol. ۳۸, ۹۲۱-۹۳۱. Olden, J.D. and Jackson, D.A. (۲۰۰۲) A comparison of statistical approaches for modeling fish species distributions, Freshwater Biol. ۴۷, ۱۹۷۶-۱۹۹۵. Quinlan, J.R. (۱۹۸۶) Induction of decision trees, Mach. Lear. ۱(۱), ۸۱-۱۰۶. Quinlan, J.R. (۱۹۹۳) C۴.۵: program for machine learning. Morgan Kaufmann publishers, San Francisco, ۳۰۲ p. Pereze Regadera, J.J., Gallardo, J.M., Ceballos, E.G. and Garcia, J.C.E. (۱۹۹۴) Model development for determination of final preferenda in freshwater species application in tench (Tinca tinca). Polish Arch. Hyd. ۴۲, ۲۷-۳۴. Ricciardi, A. & Rasmussen J.B. (۱۹۹۹) Extinction rates of North American freshwater fauna, Cons. Biol. ۱۳, ۱۲۲۰- ۱۲۲۲. Richter, B.D., Braun, D.P., Mendelson, M.A. and Master, L.L. (۱۹۹۷) Threats to imperiled freshwater fauna, Cons. Biol. ۱۱, ۱۰۸۱-۱۰۹۳. Rowe, D.K. (۲۰۰۴) Potential effects of tench (Tinca tinca) in New Zealand freshwater ecosystems, NIWA Project: BOP۰۴۲۲۱. Vainikka, (۲۰۰۳) Tench, Tinca tinca L. www.cc.jyu.fi/~ansvain/suutari/inde x.html Yilmaz, F. (۲۰۰۲) Reproductive biology of the tench (Tinca tinca) (L., ۱۷۵۸) inhabiting Porsuk Dam Lake (Kutahya, Turkey). Fish. Res. ۵۵, ۳۱۳- ۳۱۷. Witten, J.H., and Frank, E. (۲۰۰۰) Data mining: practical machine learning tools and techniques with Java implementations, San Francisco: Morgan Kaufman Publishers, ۳۶۹ p.

کلیدواژه ها:

tench (Tinca tinca) ، classification tree models (J۴۸) ، physical ، chemical variables ، structural ، habitat variables ، Flanders river basins