Abstract
New statistical modelling methods, such as neural networks (NNs), allow us to take a step further in the understanding of complex relations in aquatic ecosystems. In this paper the results from the analysis of macro-invertebrate communities in a complex riverine environment are presented. We attempted to explain observed changes in species composition and abundance with neural network modelling methods and compared the results to linear regression. The NN method used is an improved form of the RF5 algorithm, developed to effectively discover numeric laws from data. RF5 uses Product Unit Networks (PUNs), which are in effect multivariate non-discrete power functions. The data set consisted of a 10-year time series of monthly samples of macro-invertebrates on artificial substrates in the rivers Rhine and Meuse in the Netherlands. During this period the invertebrate community has largely changed coinciding with the␣invasion of Ponto-Caspian crustaceans. We used physical–chemical data and data on the abundance of the invasive taxa Corophium curvispinum and Dikerogammarus villosis to explain the observed changes in the resident invertebrate community. The analyses showed temperature, abundance of invasive taxa and peak discharges as important factors. Comparison of the results from NN modelling to linear regression revealed that the factors temperature and abundance of Dikerogammarus villosis explained equally well in both cases. Only the neural network was able to use information on peak discharge and timing of the peak in the previous winter to improve model performances. Neural networks are known to yield excellent modelling results, a drawback however is their lack of transparency or their ‘black box’ character. The use of relatively easy interpretable (white box) PUNs allows us to investigate the extracted relations in more detail and can enhance our understanding of ecosystem functioning. Our results show that peak discharges might be an important factor structuring invertebrate communities in rivers and hint on the existence of interacting effects from invasive species and discharge peaks. They finally show the value of biological data sets that are collected over a long period and in a highly standardised way.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bij de Vaate A. 2003. Degradation and recovery of the freshwater fauna in the lower sections of the rivers Rhine and Meuse. Thesis, Wageningen University. Wageningen, The Netherlands
Bij de Vaate A, Jazdzewski K, Ketelaars HAM, Gollasch S, van der Velde G (2002) Geographical patterns in range extension of Ponto-Caspian macro-invertebrate species in Europe. Canadian Journal of Fisheries and Aquatic Sciences 59: 1159–1174
Brosse S, Giraudel JL, Lek S (2001) Utilisation of non-supervised neural networks and principal component analysis to study fish assemblages. Ecological Modelling 146: 159–166
Brosse S, Guégan JF, Tourenq JN, Lek S (1999) The use of artificial neural network to assess fish community structure in a mesotrophic lake. Ecological Modelling 120: 299–311
Cereghino R, Giraudel J L, Compin A (2001) Spatial analysis of stream invertebrates distribution in the Adour-Garonne drainage basin (France), using Kohonen self organizing maps. Ecological Modelling 146: 167–180
Dick JTA, Platvoet D (2000) Invading predatory crustacean Dikerogammarus villosis eliminates both native and exotic species. Proceedings of the Royal Society of London B 267: 977–983
Directive 2000/60/EC. Official Journal of the European Communities, L327. (22 December 2000, pp. 1–72).
Fausch KD, Taniguchi Y, Nakano S, Grossman GD, Townsend CR (2001) Flood disturbance regimes influence rainbow trout invasion success among five Holarctic regions. Ecological Applications 11: 1438–1455
Gevrey M, Dimopoulos L, Lek S (2003) Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecological Modelling 160(3): 249–264
Giraudel JL, Lek S (2001) A comparison of self-organizing map algorithm and some conventional statistical methods for ecological community ordination. Ecological Modelling 146(1–3): 329–339
Guégan JF, Lek S, Oberdorff T (1998) Energy availability and habitat heterogeneity predict global riverine fish diversity. Nature 391: 382–384
Ibarra A, Gevrey M, Park Y-S, Lin P, Lek S (2003) Modelling the composition of fish guilds in the Garonne basin (France) with a backpropagation network: an aid to decision-making. Ecological Modelling 160(3): 281–290
Jaarsma NG, De Boer SM, Townsend CR, Thompson RM, Edwards ED (1998) Characterising food webs in two New Zealand streams. New Zealand Journal of Marine and Freshwater Research 32: 271–286
Lancaster J (1996) Scaling the effects of predation and disturbance in a patchy environment. Oecologia 107: 321–331
Lek S, Delacoste M, Baran P, Dimopoulos I, Lauga J, Aulagnier S (1996) Application of neural networks to modelling nonlinear relationships in ecology. Ecol. Model. 90: 39–52
Moody J. and Utans J. 1992. Principled architecture selection for neural networks: Application to corporate bond rating prediction. In: Moody J.E., Hanson S.J. and Lippmann R.P. (eds), Advances in Neural Information Processing Systems, (4), pp. 683–690
Mulholland PJ, Steinman AD, Palumbo AV, Flum T, DeAngelis DL (1991) Influence of nutrients and grazing on the response of stream periphyton communities to a scour disturbance. J. N. Am. Benthol. Soc. 10: 127–142
Olden JD, Jackson DA (2001) Fish-habitat relationships in lakes: Gaining predictive and explanatory insight using artificial neural networks. Transactions of the American Fisheries Society 130: 878–897
Olden JD, Jackson DA (2002) Illuminating the “black box”: Understanding variable contributions in artificial neural networks. Ecological Modelling 154: 135–150
Oost E.M., Ten Hagen S. and Schulze F.H. (2002). Extracting multivariate power functions from complex data sets. In: Proceedings of the Belgian-Dutch AI Conference (BNAIC-02)
Park Y-S, Céréghino R, Compin A, Lek S (2003a) Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters. Ecological Modelling 160(3): 265–280
Park Y-S, Verdonschot PFM, Chon T-S, Lek S (2003b) Patterning and predicting aquatic macroinvertebrate diversities using artificial neural network. Water Research 37(8): 1749–1758
Reyjol Y, Lim P, Belaud P, Lek S (2001) Modelling of microhabitat used by fishes in natural and regulated flows in the Garonne river (France). Ecological Modelling 146(1–3): 131–142
Saito K. and Nakano R. 1997a. Law discovery using neural networks. Proceedings of the 15th Int. Joint Conference on Artificial Intelligence (IJCAI-97), pp. 1078–1083, San Francisco
Saito K. and Nakano R. 1997b. Numeric law discovery using neural networks. Proceedings of the 4th Int. Conference on Neural Information Processing (ICONIP-97), pp. 843–846
Ter Braak CJF, Smilauer P (1998) CANOCO Reference Manual and User’s Guide to Canoco for Windows (version 4). Centre for Biometry, Wageningen The Netherlands
Ter Braak CJF, Smilauer P (1999) CANOCO for Windows (version 4.02) - a FORTRAN program for canonical community ordination. Centre for Biometry, Wageningen The Netherlands
Townsend CR, Riley R (1999) Assessment of river health: accounting for perturbation pathways in physical and ecological space. Freshwater Biology 41: 393–405
Townsend CR, Scarsbrook MR, Dolédec S (1997) The intermediate disturbance hypothesis, refugia and biodiversity in streams. Limnology and Oceanography 42: 938–949
Townsend CR, Thompson RM, McIntosh AR, Kilroy C, Edwards E, Scarsbrook MR (1998) Disturbance, resource supply and food-web architecture in streams. Ecology Letters 1: 200–209
Van den Brink FWB, van der Velde G, Bij de Vaate A (1993) Ecological aspects, explosive range extension and impact of a mass invader, Corophium curvispinum Sars, 1895 (Crustacea, Amphipoda), in the Lower Rhine (The Netherlands). Oecologia 93: 224–232
Van der Velde G, Paffen BGP, Van den Brink FWB, Bij de Vaate A, Jenner HA (1994) Decline of zebra mussel populations in the Rhine: Comparison between two mass invaders “(Dreissena polymorpha and Corophium curvispinum)". Naturwissenschaften 81(1): 32–34
Van Tongeren O (1986) “FLEXCLUS, an interactive flexible cluster program”. Acta bot. Neerl. 35: 137–142
Wootton JT, Parker MS, Power ME (1996) The effect of disturbance on river food webs. Science 273: 1558–1560
Acknowledgements
We thank two anonymous reviewers for their constructive remarks on our original manuscript, this has greatly improved our paper. Funding for this project was largely provided by Witteveen+Bos consulting engineers.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jaarsma, N.G., Bergman, M., Schulze, F.H. et al. Macro-invertebrates in a dynamic river environment: analysis of time series from artificial substrates, using a ‘white box’ neural network modelling method. Aquat Ecol 41, 413–425 (2007). https://doi.org/10.1007/s10452-005-9016-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10452-005-9016-0