Abstract
In the context of water resources planning and management, the prediction of fish distribution related to habitat characteristics is fundamental for the definition of environmental flows and habitat restoration measures. In particular, threatened and endemic fish species should be the targets of biodiversity safeguard and wildlife conservation actions. The recently developed meso-scale habitat model (MesoHABSIM) can provide solutions in this sense by using multivariate statistical techniques to predict fish species distribution and to define habitat suitability criteria. In this research, Random Forests (RF) and Logistic Regressions (LR) models were used to predict the distribution of bullhead (Cottus gobio) as a function of habitat conditions. In ten reference streams of the Alps (NW Italy), 95 mesohabitats were sampled for hydro-morphologic and biological parameters, and RF and LR were used to distinguish between absence/presence and presence/abundance of fish. The obtained models were compared on the basis of their performances (model accuracy, sensitivity, specificity, Cohen’s kappa and area under ROC curve). Results indicate that RF outperformed LR, for both absence/presence (RF: 84 % accuracy, k = 0.58 and AUC = 0.88; LR: 78 % accuracy, k = 0.54 and AUC = 0.85) and presence/abundance models (RF: 79 % accuracy, k = 0.57 and AUC = 0.87; LR: 69 % accuracy, k = 0.43 and AUC = 0.81). The most important variables, selected in each model, are discussed and compared to the available literature. Lastly, results from models’ application in regulated sites are presented to show the possible use of RF in predicting habitat availability for fish in Alpine streams.
Similar content being viewed by others
References
Abrahamsson C, Johansson J, Sparén A, Lindgren F (2003) Comparison of different variable selection methods conducted on NIR transmission measurements on intact tablets. Chemometrics Intellig Lab Syst 69:3–12
Acreman MC, Ferguson AJD (2010) Environmental flows and the European water framework directive. Freshwat Biol 55:32–48
Ahmadi-Nedushan B, St-Hilaire A, Bérubé M, Robichaud É, Thiémonge N, Bobée B (2006) A review of statistical methods for the evaluation of aquatic habitat suitability for instream flow assessment. River Res Appl 22:503–523
Bain MB, Knight JG (1996) Classifying stream habitat using fish community analysis. In: Leclerc MCH, Valentin S, Boudreau A, Cote Z (eds) Ecohydraulics 2000. 2nd International Symposium on Habitat Hydraulics, INRS-Eau, Quebec City, pp 107–117
Borsányi P, Alfredsen K, Harby A, Ugedal O, Borsányi CKL (2003) A meso-scale habitat classification method for production modelling of atlantic salmon in Norway
Breiman L (2001) Random forest. Mach Learn 45:5–32
Breiman L, Friedman JH, Olshen R, Stone CJ (1984) Classification and regression trees. Wadsworth and Brooks, Monterey
Buisson L, Thuiller W, Casajus N, Lek S, Grenouillet G (2010) Uncertainty in ensemble forecasting of species distribution. Global Change Biol 16:1145–1157
Carter MG, Copp GH, Szomlai V (2004) Seasonal abundance and microhabitat use of bullhead Cottus gobio and accompanying fish species in the River Avon (Hampshire), and implications for conservation. Aquatic Conserv 14:395–412
Cheng L, Lek S, Lek-Ang S, Li Z (2012) Predicting fish assemblages and diversity in shallow lakes in the Yangtze River basin. Limnologica 42:127–136
Ciuffardi L, Bassani I (2005) Segnalazione del successo riproduttivo della Lampreda di mare (Petromyzon marinus) in Provincia della Spezia. Biologia ambientale 19:15–16
Comoglio C, Prato EP, Ferri M, Gianaroli M (2007) A case study of river rehabilitation for fish in northern Italy: the Panaro river project. Am J Environ Sci 3:85–92
Cowx IG, Harvey JP (2000) Monitoring the bullhead, Cottus gobio. Conserving Natura (2000) Rivers. English Nature Peterborough, UK
Crivelli AJ (1996) The freshwater fish endemic to the Mediterranean region. An action plan for their conservation. Tour du Valat Publication
Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88:2783–2792
Davey AJH, Hawkins SJ, Turner GF, Doncaster CP (2005) Size-dependent microhabitat use and intraspecific competition in Cottus gobio. J Fish Biol 67:428–443
Drew CA, Wiersma Y, Huettmann F (2011) Predictive species and habitat modeling in Landscape ecology: concepts and applications. Springer, New York
Evans J, Cushman S (2009) Gradient modeling of conifer species using random forests. Landscape Ecol 24:673–683
Filipe AF, Cowx IG, Collares-pereira MJ (2002) Spatial modelling of freshwater fish in semi-arid river systems: a tool for conservation. River Res Appl 18:123–136
Fox J (2007) Polycor: polychoric and polyserial correlations. R package version 0.7-5, http://CRAN.R-project.org/package=polycor. Accessed 3 April 2010
Franklin J (2010) Mapping species distributions: spatial inference and prediction. Cambridge University Press, New York
Frissell C, Liss W, Warren C, Hurley M (1986) A hierarchical framework for stream habitat classification: viewing streams in a watershed context. Environ Manage 10:199–214
Gandolfi G, Zenurian S, Torricelli P, Marconato A (1991) I pesci delle acque interne italiane—Italian inland water fishes. Ministero dell’Ambiente, Istituto Poligrafico e Zecca dello Stato, Roma
Gosselin M, Petts G, Maddock I (2010) Mesohabitat use by bullhead (Cottus gobio). Hydrobiologia 652:299–310
Gosselin MP, Maddock I, Petts G (2012) Mesohabitat use by brown trout (Salmo trutta) in a small groundwater-dominated stream. River Res Appl 28:390–401
Grenouillet G, Buisson L, Casajus N, Lek S (2011) Ensemble modelling of species distribution: the effects of geographical and environmental ranges. Ecography 34:9–17
Hauer C, Unfer G, Tritthart M, Formann E, Habersack H (2010) Variability of mesohabitat characteristics in riffle-pool reaches: testing an integrative evaluation concept (FGC) for MEM-application. River Res Appl. doi:10.1002/rra.1357
Hayer CA, Wall SS, Berry CR Jr (2008) Evaluation of predicted fish distribution models for rare fish species in South Dakota. N Am J Fish Manage 28:1259–1269
Hooten MB (2011) The state of spatial and spatio-temporal statistical modeling. In: Drew C, Wiersma Y, Huettmann F (eds) Predictive species and habitat modeling in landscape ecology. Springer, New York, pp 29–41
Hosmer DW, Lemeshow S (2000) Applied Logistic Regression, 2nd edn. John Wiley & Sons, Inc., New York
Jewitt GPW, Weeks DC, Heritage GL, Gorgens AHM (2001) Modelling abiotic-biotic links in the rivers of the Kruger National Park Mpumulanga South Africa. In: Acreman M, Jewitt GPW (eds) Hydro-ecology: linking hydrology and aquatic ecology. Proceedings of Workshop HW2 held at Birmingham UK July 1999 IAHS Press, Wallingford, pp 77–90
Jiménez-Valverde A, Lobo JM (2007) Threshold criteria for conversion of probability of species presence to either–or presence–absence. Acta Oecol 31:361–369
Kampichler C, Wieland R, Calmé S, Weissenberger H, Arriaga-Weiss S (2010) Classification in conservation biology: a comparison of five machine-learning methods. Ecol Inform 5:441–450
Kemp JL, Harper DM, Crosa GA (1999) Use of ‘functional habitats’ to link ecology with morphology and hydrology in river rehabilitation. Aquat Conserv: Mar Freshwat Ecosyst 9:159–178
Knaepkens G, Bruyndoncx L, Bervoets L, Eens M (2002) The presence of artificial stones predicts the occurrence of the European bullhead (Cottus gobio) in a regulated lowland river in Flanders (Belgium). Ecol Freshwat Fish 11:203–206
Knaepkens G, Baekelandt K, Eens M (2006) Fish pass effectiveness for bullhead (Cottus gobio), perch (Perca fluviatilis) and roach (Rutilus rutilus) in a regulated lowland river. Ecol Freshwat Fish 15:20–29
Kuhn M (2008) Building predictive models in R using the caret package. J Stat Soft. http://www.jstatsoft.org/v28/i05/paper. Accessed 22 November 2008
Langford TE, Hawkins SJ (1997) The distribution and abundance of three fish in relation to timber debris and mesohabitats in a lowland forest stream during autumn and winter. Limnetica 13:93–102
Legalle M, Mastrorillo S, Santoul F, Céréghino R (2005a) Ontogenetic microhabitat shifts in the bullhead, Cottus gobio L., in a fast flowing stream. Internat Rev Hydrobiol 90:310–321
Legalle M, Santoul F, Figuerola J, Mastrorillo S, Céréghino R (2005b) Factors influencing the spatial distribution patterns of the bullhead (Cottus gobio L., Teleostei Cottidae): a multi-scale study. Biodivers Conserv 14:1319–1344
Liaw A, Wiener M (2002) Classification and regression by Random forest. R News 2:18–22
Liu C, Berry PM, Dawson TP, Pearson RG (2005) Selecting thresholds of occurrence in the prediction of species distributions. Ecography 28:385–393
Manel S, Williams HC, Ormerod SJ (2001) Evaluating presence–absence models in ecology: the need to account for prevalence. J Appl Ecol 38:921–931
Markovic D, Freyhof J, Wolter C (2012) Where are all the fish: potential of biogeographical maps to project current and future distribution patterns of freshwater species. PLoS ONE 7:e40530
Marmion M, Parviainen M, Luoto M, Heikkinen RK, Thuiller W (2009) Evaluation of consensus methods in predictive species distribution modelling. Divers Distrib 15:59–69
Meador M, McIntyre J, Pollock K (2003) Assessing the efficacy of single-pass backpack electrofishing to characterize fish community structure. Trans Am Fish Soc 132:39–46
Melcher AH, Lautsch E, Schmutz S (2012) Non-parametric methods—Tree and P-CFA—for the ecological evaluation and assessment of suitable aquatic habitats: a contribution to fish psychology. Psych Test Ass Mod 54:293–306
Mouton AM, Schneider M, Depestele J, Goethals PLM, De Pauw N (2007) Fish habitat modelling as a tool for river management. Ecol Eng 29:305–315
Mouton AM, De Baets B, Goethals PLM (2010) Ecological relevance of performance criteria for species distribution models. Ecol Model 221:1995–2002
Mouton AM, Alcaraz-Hernández JD, De Baets B, Goethals PLM, Martínez-Capel F (2011) Data-driven fuzzy habitat suitability models for brown trout in Spanish Mediterranean rivers. Environ Model Software 26:615–622
Murphy MA, Evans JS, Storfer A (2010) Quantifying Bufo boreas connectivity in Yellowstone National Park with landscape genetics. Ecology 91:252–261
Olden JD, Jackson DA (2002) A comparison of statistical approaches for modelling fish species distributions. Freshwat Biol 47:1976–1995
Olden JD, Jackson DA, Peres-Neto PR (2002) Predictive models of fish species distributions: a note on proper validation and chance predictions. Trans Am Fish Soc 131:329–336
Parasiewicz P (2001) MesoHABSIM: a concept for application of instream flow models in river restoration planning. Fisheries 26:6–13
Parasiewicz P (2007) The MesoHABSIM model revisited. River Res Appl 23:893–903
Parasiewicz P, Rogers J, Legros J, Wirth M (2007) Assessment and restoration of instream habitat of the Eightmile River in Connecticut: Developing a MesoHABSIM model. Report 62, p 65
Parasiewicz P, Nestler J, Poff NL, Goodwin A (2008) Virtual reference river: a model for scientific discovery and reconciliation. In: Alonso MS, Rubio IM (eds) Ecological management: new research. Nova Science Publishers, Inc., New York, pp 189–198
Parasiewicz P, Castelli E, Rogers JN, Plunkett E (2012a) Multiplex modeling of physical habitat for endangered freshwater mussels. Ecol Modell 228:10
Parasiewicz P, Ryan K, Vezza P, Comoglio C, Ballestero T, Rogers JN (2012b) Use of quantitative habitat models for establishing performance metrics in river restoration planning. Ecohydrology. doi:10.1002/eco.1350
Pearce J, Ferrier S (2000) Evaluating the predictive performance of habitat models developed using logistic regression. Ecol Model 133:225–245
Pini Prato E, Comoglio C, Calles O (2011) A simple management tool for planning the restoration of river longitudinal connectivity at watershed level: priority indices for fish passes. J Appl Ichthyol 27:73–79
Randin CF, Dirnböck T, Dullinger S, Zimmermann NE, Zappa M, Guisan A (2006) Are niche-based species distribution models transferable in space? J Biogeogr 33:1689–1703
Regione Piemonte (2010) Proposta di piano regionale per la tutela e la conservazione degli ambienti e della fauna acquatica e l’esercizio della pesca. Regione Pimonte, Torino
Regione Piemonte (2007) Piano di Tutela delle Acque–Regional Water Protection Plan, Volume D.C.R. n. 117-10731. Torino, Italia
Regione Valle d’Aosta (2008) Progetto di sperimentazione del DMV del gruppo C.V.A. Caratterizzazione Dora Baltea. Monografia 2008, Aosta, Italia
Reunanen J (2003) Overfitting in making comparisons between variable selection methods. J Mach Learn Res 3:1371–1382
Roussel JM, Bardonnet A (1996) Differences in habitat use by day and night for brown trout (Salmo trutta) and sculpin (Cottus gobio) in a natural brook: multivariate and multi-scale analyses. Cybium 20:45–53
Sakamoto Y (1994) Categorical data analysis by AIC. In: Bozdogan H (ed) Proceedings of the first US/Japan conference on the frontiers of statistical modeling: an informational approach. Kluwer Academic Publishers, Dordrecht, pp 255–269
Siroky DS (2009) Navigating random forests and related advances in algorithmic modeling. Stat Surveys 3:147–163
Stehman SV (1997) Selecting and interpreting measures of thematic classification accuracy. Remote Sens Environ 62:77–89
Steyerberg EW, Harrell FE Jr, Borsboom GJJM, Eijkemans MJC, Vergouwe Y, Habbema JDF (2001) Internal validation of predictive models: efficiency of some procedures for logistic regression analysis. J Clin Epidemiol 54:774–781
Thomas JA, Bovee KD (1993) Application and testing of a procedure to evaluate transferability of habitat suitability criteria. Regul Rivers: Res Manage 8:285–294
Tirelli T, Pozzi L, Pessani D (2009) Use of different approaches to model presence/absence of Salmo marmoratus in Piedmont (Northwestern Italy). Ecol Inform 4:234–242
Tomlinson ML, Perrow (2003) Ecology of the bullhead. Conserving Natura 2000 Rivers Ecology. English Nature, Peterborough
Van Liefferinge C, Seeuws P, Meire P, Verheyen RF (2005) Microhabitat use and preferences of the endangered Cottus gobio in the River Voer, Belgium. J Fish Biol 67:897–909
Vaughan IP, Ormerod SJ (2005) The continuing challenges of testing species distribution models. J Appl Ecol 42:720–730
Vezza P, Comoglio C, Rosso M, Viglione A (2010) Low flows regionalization in north-western Italy. Water Resour Manage 24(14):4049–4074
Vezza P, Parasiewicz P, Rosso M, Comoglio C (2012a) Defining minimum environmental flows at regional scale: application of mesoscale habitat models and catchments classification. River Res Appl 28:675–792
Vezza P, Parasiewicz P, Spairani M, Comoglio C (2012b) Meso-scale habitat modelling in Alpine high gradient streams. In: Mader H, Kraml J (eds) Proceeding of the 9th Eco-hydraulics Symposium ISE 2012. Austria, Vienna
Vezza P, Parasiewicz P, Spairani M, Comoglio C (2013) Habitat modelling in high gradient streams: the meso-scale approach and application. Ecol Appl In press
Wells BJ, Yu C, Koroukian S, Kattan MW (2011) Comparison of variable selection methods for the generation of parsimonious prediction models for use in clinical practice. In: SMDM (ed) Proceedings of the 33rd Annual Meeting of the Society for Medical Decision Making. SMDM, Chicago
Xu L, Zhang W-J (2001) Comparison of different methods for variable selection. Anal Chim Acta 446:475–481
Zerunian S (2002a) Condannati all’estinzione? Biodiversità, biologia, minacce e strategie di conservazione dei Pesci d’acqua dolce indigeni in Italia. Edagricole, Bologna
Zerunian S (2002b) Iconography of Italian inland water Fishes. Tipolitografia FG—Savignano s/P (Mo), Roma
Zerunian S (2007) Problematiche di conservazione dei Pesci d’acqua dolce italiani. Biologia Ambientale 21:49–55
Acknowledgments
The presented research was developed in the framework of the HolRiverMed project (275577—FP7-PEOPLE-2010-IEF, Marie Curie Actions) and in collaboration with the Regional Consortium for Fisheries Management in the Aosta Valley (Consorzio Regionale Tutela Pesca - Valle d’Aosta). The data collection was funded by the Regione Piemonte (C61 Project—CIPE 2004) and through the dams monitoring program of Compagnia Valdostana delle Acque (CVA S.p.a.).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Vezza, P., Parasiewicz, P., Calles, O. et al. Modelling habitat requirements of bullhead (Cottus gobio) in Alpine streams. Aquat Sci 76, 1–15 (2014). https://doi.org/10.1007/s00027-013-0306-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00027-013-0306-7