Application of classification trees-J۴۸ to model the presence of roach (Rutilus rutilus) in rivers

In the present study, classification trees (CTs-J۴۸ algorithm) were used to study the occurrence of roach in rivers in Flanders (Belgium). The presence/absence of roach was modelled based on a set of river characteristics. The predictive performance of the CTs models was assessed based on the percentage of Correctly Classified Instances (CCI) and Cohen\'s kappa statistics. To find the best model performance, a ۳-fold cross validation techniques was applied on the dataset. The effect of Pruning Confidence Factors (PCFs) was examined on the reliability and model complexity. Based on the obtained results, the induced model could predict well the presence/absence of roach in the rivers. The highest overall means of two model performances showed that the models were reliable. When analyzing the ecological relevance of CTs, it seemed that the structural-habitat variables were more the main predictors than the water quality ones to predict the occurrence of roach in rivers. In particular, the distance from the source and width contributed more to the prediction of roach while among water quality variables, only electric conductivity was relatively important in this regard.     REFERENCES  Belpaire, C., Smolders, R., Vanden Auweele, 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. Brabrand, A. (۱۹۸۵) Food of roach, Rutilus rutilus and ide, Leuciscus idus: significance of diet shift for interspecific competition in omnivorous fishes. Oecologia. ۶۶, ۴۶۱-۴۶۷. Brabrand, A. and Faafeng, B. (۱۹۹۴) Habitat shift in roach, Rutilus rutilus induced by the introduction of pikeperch, Stizostedion lucioperca. Limnologie. ۲۵, ۲۱-۲۳. Breine, J., Simoens, I., Goethals, P.L.M., Quataert, P., Ercken, D., Chris, V. L. and Belpaire, C. (۲۰۰۴) A fish-based index of biotic integrity for upstream brooks in Flanders (Belgium). Hydrobiologia. ۵۲۲, ۱۳۳-۱۴۸. Breiman, L., Friedman, J., Olshen, R. and Stone, C. (۱۹۸۴) Classification and Regression Trees. Wadsworth, Pacific Grove, CA, USA. Brosse, S. and Lek, S. (۲۰۰۰) Modelling roach, Rutilus rutilus microhabitat using linear and nonlinear techniques. Freshwater. Bio. ۴۴, ۳۴-۴۱. Cohen, J. (۱۹۶۰) A coefficient of agreement for nominal scales. Educ. Psychol. Meas. ۲۰ (۱), ۳۷-۴۶. Copp, G. H. (۱۹۹۰) Shifts in the microhabitat of larval and juvenile the roach, Rutilus rutilus L. in a floodplain channel. J. Fish Biol. ۳۶, ۶۸۳-۶۹۲. Copp, G. H. (۱۹۹۲) An empirical model for predicting microhabitat of ۰+ juvenile fishes in a lowland river catchment. Oecologia. ۹۱, ۳۳۸-۳۴۵. Dakou, E., Goethals, P.L.M., D’heygere, T., Dedecker, A.P., Gabriels, W. and De Pauw, N. (۲۰۰۶) Development of artificial neural network models predicting macroinvertebrate taxa in the river Axios (Northern Greece). Annales de Limnologie, Ann. Limnol., Int. J. Lim. ۴۲, ۲۴۱- ۲۵۰. Dakou, E., D'heygere, T., Dedecker, A.P., Goethals, P.L.M., LazaridouDimitriadou, M. and De Pauw, N., (۲۰۰۷) Decision tree models for prediction of macroinvertebrate taxa in the river Axios (Northern Greece). Aquat. Ecol. ۴۱,۳۹۹-۴۱۱. Dedecker, A.P., Goethas P.L.M., Gabriels, W. and De Pauw, N. (۲۰۰۲) Comparison of Artificial Neural Network (ANN) model developments methods for prediction of macroinvertebrates communities in the Zwalm river basin in Flanders, Belgium. The ScientificWorldJo. ۲, ۹۶-۱۰۴. D’heygere, T., Goethals, P. L. M. and De Pauw, N. (۲۰۰۳) Use of genetic algorithms to select input variables in decision tree models for the prediction of benthic macroinverteberates. Ecol. Model. ۱۶۰, ۲۹۱-۳۰۰. D’heygere, T., Goethals, P. L. M. and De Pauw, N. (۲۰۰۶) Genetic algorithms for optimization of predictive ecosystems models based on decision trees and neural networks. Ecol. Model. ۱۹۵, ۲۰-۲۹. Dzeroski, S., Grobovic, J. and Walley, W.J. (۱۹۹۷) Machine learning applications in biological classification of river water quality, pp.۴۲۹-۴۴۸. In: Michalski, R.S., Bratko, I. & Kubat, M. Machine learning data mining: methods and applications. John Wiley and Sons Ltd., New York. Eklov, P. (۱۹۹۷) Effects of habitat complexity and prey abundance on the spatial and temporal distributions of perch, Perca fluviatilis and pike, Esox lucius. Can. J. Fish. Aquat. Sci. ۵۴, ۱۵۲۰- ۱۵۳۱. Fielding, A.H. and Bell, J.F. (۱۹۹۷) A review of methods for the assessment of prediction errors in conservation presence/absence models. Environ. Conserv. ۲۴, ۳۸-۴۹. Garner, P. (۱۹۹۵) Suitability indices for Zarkami ۱۹۷ juvenile ۰+ roach, Rutilus rutilus (L.) using point abundance sampling data. Regul. River. ۱۰, ۹۹-۱۰۴. Goethals, P.L.M. and De Pauw, N. (۲۰۰۱) Development of a concept for integrated ecological river assessment in Flanders, Belgium. J. Limnol. ۶۰, ۷-۱۶. Goethals, P. L. M. (۲۰۰۵) Data driven development of predictive ecological models for benthic macroinvertebrates in rivers. PhD thesis. University of Ghent, ۳۷۷ p. Goethals, P.L.M., Dedecker, A.P., Gabriels, W., Lek, S. and De Pauw, N. (۲۰۰۷) Applications of artificial neural networks predicting macroinvertebrates in freshwaters. Aquat. Ecol. ۴۱, ۴۹۱-۵۰۸. Horppila, J. (۱۹۹۴) The diet and growth of roach, Rutilus rutilus (L.)) in Lake Vesijarvi and possible changes in the course of biomanipulation. Hydrobiologia. ۲۹۴, ۳۵-۴۱. Kahl, U., Dorner, H., Radke, R.J., Wagner, A. and Benndorf, J. (۲۰۰۱) The roach population in the hypertrophic Bautzen Reservoir: structure, diet and impact on Daphnia galeata. Limnologica. ۳۱: ۶۱-۶۸. Kahl, U. and Radke, R. J. (۲۰۰۶) Habitat and food resource use of perch and roach in a deep mesotrophic reservoir: enough space to avoid competition? Ecol. Freshw. Fish. ۱۵, ۴۸-۵۶. Jackson, D.A. and Harvey, H.H. (۱۹۹۷) Qualitative and quantitative sampling of lake fish communities. Can. J. Fish. Aquat. Sci. ۵۴, ۲۸۰۷-۲۸۱۳. Johansson, L. and Persson, L. (۱۹۸۶) The fish community of temperate, eutrophic lakes. In: Riemann, M.B.S. ed. Carbon dynamics of eutrophic, temperate lakes: the structure and functions of the pelagic environment. Amsterdam: Elsevier, pp. ۲۳۷-۲۶۶. Lawton, J. (۱۹۹۶) Patterns in ecology. Oikos. ۷۵, ۱۴۵-۱۴۷. Hoang, T.H., Lock, K., Mouton, A. and Goethals, P. L.M. (۲۰۱۰) Application of classification trees and support vector machines to model the presence of macroinvertebrates in rivers in Vietnam. Ecol. Inform. ۵, ۱۴۰-۱۴۶. Manel, S., Dias, J.M., Buckton, S.T. and Ormerod, S. J. (۱۹۹۹) Alternatives methods for predicting species distribution: an illustration with Hialayan river birds. J. Appl. Ecol. ۳۶,۷۳۴-۷۴۷. 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 modelling fish species distributions. Freshwater Biol. ۴۷, ۱۹۷۶- ۱۹۹۵. Quinlan, J.R. (۱۹۸۶) Induction of decision trees. Mach.Learn. ۱, ۸۱-۱۰۶. Quinlan, J.R. (۱۹۹۳) C۴.۵: Programs for machine learning. Morgan Kaufmann, San Francisco, USA. Persson, L. and Greenberg, L.A. (۱۹۹۰) Juvenile competitive bottlenecks- the perch, Perca fluviatilis- roach, Rutilus rutilus interaction. Ecology. ۷۱, ۴۴-۵۶. Persson, L. (۱۹۸۳) Effects of intraspecific and interspecific competition on dynamics and size structure of a perch, Perca fluviatilis and a roach, Rutilus rutilus population. Oikos. ۴۱,۱۲۶-۱۳۲. Poizat G. and Pont D. (۱۹۹۶) Multi-scale approach to species-habitat relationships: juvenile fish in a large river section. Freshwater Biol. ۳۶, ۶۱۱- ۶۲۲. Ricciardi, A. and Rasmussen, J.B. (۱۹۹۹) Extinction rates of North American freshwater fauna. Conserv. Biol. ۱۳, ۱۲۲۰-۱۲۲۲. Rossier, O., Castella, E. and Lachavanne, J.B. (۱۹۹۶) Influence of submerged aquatic vegetation on size class distribution of perch, Perca fluviatilis and roach, Rutilus rutilus in the littoral zone of Lake Geneva (Switzerland). Aquat. Sci. ۵۸, ۱-۱۴. Schoener, T. (۱۹۷۴) Resource partitioning in ecological communities. Science. ۱۸۵, ۲۷-۳۹. Schulze, T., Dörner, H., Hölker, F. and Mehner, T. (۲۰۰۶) Determinants of habitat use in large roach. J. Fish Biol. ۶۹, ۱۱۳۶-۱۱۵۰.  Sharma, C.M. and Borgstrøm, R. (۲۰۰۸) Shift in density, habitat use, and diet of perch and roach: An effect changed predation pressure after manipulation of pike. Fish. Res. ۹۱, ۹۸-۱۰۶. Skov, C., Berg, S., Jacobsen, L. and Jepsen, N. (۲۰۰۲) Habitat use and foraging ۱۹۸ The occurrence of the roach in the rivers success of ۰+ Pike, Esox lucius (L.) in experimental ponds related to prey fish, water transparency and light intensity. Ecol. Freshw. Fish. ۱۱, ۶۵-۷۳. Vinni, M., Horppila, J., Olin, M., Ruuhijarvi, J. and Nyberg, K., (۲۰۰۰) The food, growth and abundance of five co-existing cyprinids in lake basins of different morphometry and water quality. Aquat. Ecol. ۳۴, ۴۲۱-۴۳۱. Werner, E.E., Hall, D.J., Laughlin, D.R., Wagner, D.J., Wilsmann, L.A. and Funk, F.C. (۱۹۷۷) Habitat partitioning in a freshwater fish community. J. Fish.Res.Board.Can. ۳۴, ۳۶۰-۳۷۰. Witten, J.H. and Frank, E. (۲۰۰۰) Data mining: practical machine learning tools and techniques with Java implementations, Morgan Kaufman publishers, San Francisco. ۳۶۹ p.

Keywords:

Ecological modelling , Classification trees (J۴۸) , Occurrence , Roach , River basins , Flanders