Hydrobiologia

, Volume 670, Issue 1, pp 165–188 | Cite as

Fish distribution predictions from different points of view: comparing associative neural networks, geostatistics and regression models

  • A. Palialexis
  • S. Georgakarakos
  • I. Karakassis
  • K. Lika
  • V. D. Valavanis
ECOSYSTEMS AND SUSTAINABILITY

Abstract

Accurate prediction of species distributions based on sampling and environmental data is essential for further scientific analysis, such as stock assessment, detection of abundance fluctuation due to climate change or overexploitation, and to underpin management and legislation processes. The evolution of computer science and statistics has allowed the development of sophisticated and well-established modelling techniques as well as a variety of promising innovative approaches for modelling species distribution. The appropriate selection of modelling approach is crucial to the quality of predictions about species distribution. In this study, modelling techniques based on different approaches are compared and evaluated in relation to their predictive performance, utilizing fish density acoustic data. Generalized additive models and mixed models amongst the regression models, associative neural networks (ANNs) and artificial neural networks ensemble amongst the artificial neural networks and ordinary kriging amongst the geostatistical techniques are applied and evaluated. A verification dataset is used for estimating the predictive performance of these models. A combination of outputs from the different models is applied for prediction optimization to exploit the ability of each model to explain certain aspects of variation in species acoustic density. Neural networks and especially ANNs appear to provide more accurate results in fitting the training dataset while generalized additive models appear more flexible in predicting the verification dataset. The efficiency of each technique in relation to certain sampling and output strategies is also discussed.

Keywords

Species distribution predictions Habitat modelling Models comparison Geostatistics 

References

  1. Agostini, V. N. & A. Bakun, 2002. ‘Ocean triads’ in the Mediterranean Sea: physical mechanisms potentially structuring reproductive habitat suitability (with example application to European anchovy, Engraulis encrasicolus). Fisheries Oceanography 11: 129–142.CrossRefGoogle Scholar
  2. Akaike, H., 1974. A new look at the statistical model identification. IEEE Transactions on Automatic Control 19: 716–723.CrossRefGoogle Scholar
  3. Bishop, M., 1995. Neural Networks for Pattern Recognition. Oxford University Press, Oxford.Google Scholar
  4. Bodholt, H., H. Nes & H. Solli, 1989. A new echo sounder system. Proceedings of the Institute of Acoustics (UK) 11(3): 123–130.Google Scholar
  5. Boyce, M. S., P. R. Vernier, S. E. Nielsen & F. K. A. Schmiegelow, 2002. Evaluating resource selection functions. Ecological Modelling 157: 281–300.CrossRefGoogle Scholar
  6. Chen, I. C., P. F. Lee & W. N. Tzeng, 2005. Distribution of albacore (Thunnus alalunga) in the Indian Ocean and its relation to environmental factors. Fisheries Oceanography 14: 71–80.CrossRefGoogle Scholar
  7. Cleveland, W. S., 1994. The Elements of Graphing Data. Hobart Press, Summit. ISBN:0-9634884-1-4.Google Scholar
  8. Elith, J. & J. R. Leathwick, 2009. Species distribution models: ecological explanation and prediction across space and time. Annual Review of Ecology, Evolution, and Systematics 40: 677–697.CrossRefGoogle Scholar
  9. Elith, J., C. H. Graham, R. P. Anderson, M. Dudik, S. Ferrier, A. Guisan, R. J. Hijmans, F. Huettmann, J. R. Leathwick, A. Lehmann, J. Li, L. G. Lohmann, B. A. Loiselle, G. Manion, C. Moritz, M. Nakamura, Y. Nakazawa, J. M. C. Overton, A. T. Peterson, S. J. Phillips, K. S. Richardson, R. Scachetti-Pereira, R. E. Schapire, J. Soberon, S. Williams, M. S. Wisz & N. E. Zimmermann, 2006. Novel methods improve prediction of species’ distributions from occurrence data. Ecography 29: 129–151.CrossRefGoogle Scholar
  10. Fiedler, P. C. & H. J. Bernard, 1987. Tuna aggregation and feeding near fronts observed in satellite imagery. Continental Shelf Research 7: 871–881.CrossRefGoogle Scholar
  11. Georgakarakos, S. & D. Kitsiou, 2008. Mapping abundance distribution of small pelagic species applying hydroacoustics and co-kriging techniques. Hydrobiologia 612(1): 155–169.CrossRefGoogle Scholar
  12. Giannoulaki, M., A. Machias & N. Tsimenides, 1999. Ambient luminance and vertical migration of the sardine Sardina pilchardus. Marine Ecology Progress Series 178: 29–38.CrossRefGoogle Scholar
  13. Giannoulaki, M., V. D. Valavanis, A. Palialexis, K. Tsagarakis, A. Machias, S. Somarakis & C. Papaconstantinou, 2008. Modelling the presence of anchovy Engraulis encrasicolus in the Aegean Sea during early summer, based on satellite environmental data. Hydrobiologia 612(1): 225–240.CrossRefGoogle Scholar
  14. Guisan, A. & N. E. Zimmermann, 2000. Predictive habitat distribution models in ecology. Ecological Modelling 135: 147–186.CrossRefGoogle Scholar
  15. Guisan, A., J. Edwards, C. Thomas & T. Hastie, 2002. Generalized linear and generalized additive models in studies of species distributions: setting the scene. Ecological Modelling 157: 89–100.CrossRefGoogle Scholar
  16. Hastie, T. & R. Tibshirani, 1990. Generalized Additive Models. Chapman & Hall, London.Google Scholar
  17. Hastie, T., R. Tibshirani & J. Friedman, 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. Springer, Berlin.Google Scholar
  18. Haykin, S., 1994. Neural Networks: A Comprehensive Foundation. Macmillan, New York.Google Scholar
  19. Isaaks, E. H. & R. M. Srivastava, 1989. Applied Geostatistics. Oxford University Press, New York.Google Scholar
  20. Keitt, T. H., O. N. Bjornstad, P. M. Dixon & S. Citron-Pousty, 2002. Accounting for spatial pattern when modelling organism–environment interactions. Ecography 25: 616–625.CrossRefGoogle Scholar
  21. Kourafalou, V. & K. Tsiaras, 2007. A nested circulation model for the North Aegean Sea. Ocean Science 3: 1–16.CrossRefGoogle Scholar
  22. Laurs, R. M., P. C. Fiedler & D. R. Montgomery, 1984. Albacore tuna catch distributions relative to environmental features observed from satellites. Deep-Sea Research 31: 1085–1099.CrossRefGoogle Scholar
  23. Lawrence, S., A. C. Tsoi & A. D. Back, 1996. Function approximation with neural networks and local methods: bias, variance and smoothness. Australian Conference on Neural Networks. Australian National University: 16–21.Google Scholar
  24. Lehmann, A., C. Overton & J. R. Leathwick, 2002. GRASP: generalized regression analysis and spatial prediction. Ecological Modelling 157: 189–207.CrossRefGoogle Scholar
  25. Levins, R., 1966. The strategy of model building in population ecology. American Scientist 54: 421–431.Google Scholar
  26. MacLennan, D. N., P. G. Fernandes & J. Dalen, 2002. A consistent approach to definitions and symbols in fisheries acoustics. ICES Journal of Marine Science 59: 365–369.CrossRefGoogle Scholar
  27. Matheron, G., 1971. The Theory of Regionalized Variables and its Applications. Ecole Nationale Supérieure des Mines de Paris, Fontainebleau.Google Scholar
  28. Michie, D., D. J. Spiegelhalter & C. Taylor, 1994. Machine Learning, Neural and Statistical Classification. Prentice Hall, Englewood Cliffs.Google Scholar
  29. Moisen, G. G. & T. S. Frescino, 2002. Comparing five modelling techniques for predicting forest characteristics. Ecological Modelling 157: 209–225.CrossRefGoogle Scholar
  30. Moran, P. A. P., 1950. Notes on continuous stochastic phenomena. Biometrika 37: 17–23.PubMedGoogle Scholar
  31. Motos, L., A. Uriarte & V. Valéncia, 1996. The spawning environment of the Bay Biscay anchovy (Engraulis encrasicolus L.). Scientia Marina 60: 117–140.Google Scholar
  32. Palialexis, A., S. Georgakarakos, K. Lika & V. D. Valavanis, 2009. Use of GIS, remote sensing and regression models for the identification and forecast of small pelagic fish distribution. Proceedings of the Second International Conference on Environmental Management, Engineering, Planning and Economics (CEMEPE 09), June 21–26, Mykonos, Greece.Google Scholar
  33. Palomera, I., M. P. Olivar, J. Salat, A. Sabates, M. Coll, A. Garcia & B. Morales-Nin, 2007. Small pelagic in the NW Mediterranean Sea: an ecological review. Progress in Oceanography 74: 377–396.CrossRefGoogle Scholar
  34. Pearce, J. & S. Ferrier, 2000. Evaluating the predictive performance of habitat models developed using logistic regression. Ecological Modelling 133: 225–245.CrossRefGoogle Scholar
  35. Petitgas, P., 2001. Geostatistics in fisheries survey design and stock assessment: models, variances and applications. Fish and Fisheries 2: 231–249.CrossRefGoogle Scholar
  36. Potts, J. M. & J. Elith, 2006. Comparing species abundance models. Ecological Modelling 199: 153–163.CrossRefGoogle Scholar
  37. Poulos, S. E., G. T. Chronis, M. B. Collins & V. Lykousis, 2000. Thermaikos Gulf Coastal System, NW Aegean Sea: an overview of water/sediment fluxes in relation to air-land-ocean interactions and human activities. Journal of Marine Systems 25: 47–76.CrossRefGoogle Scholar
  38. R Development Core Team, 2005. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria [available on internet at http://www.Rproject.org].
  39. Redfern, J. V., M. C. Ferguson, E. A. Becker, K. D. Hyrenbach, C. Good, J. Barlow, K. Kaschner, M. F. Baumgartner, K. A. Forney, L. T. Ballance, P. Fauchald, P. Halpin, T. Hamazaki, A. J. Pershing, S. S. Qian, A. Read, S. B. Reilly, L. Torres & F. Werner, 2006. Techniques for cetacean–habitat modeling: a review. Marine Ecology Progress Series 310: 271–295.CrossRefGoogle Scholar
  40. Richards, C. L., B. C. Carstens & L. Knowles, 2007. Distribution modelling and statistical phylogeography: an integrative framework for generating and testing alternative biogeographical hypotheses. Journal of Biogeography 34: 1833–1845.CrossRefGoogle Scholar
  41. Ripley, B. D., 1996. Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge.Google Scholar
  42. Sabates, A., M. P. Olivar, J. Salat, I. Palomera & F. Alemany, 2007. Physical and biological processes controlling the distribution of fish larvae in the NW Mediterranean. Progress in Oceanography 74: 355–376.CrossRefGoogle Scholar
  43. Schismenou, E., M. Giannoulaki, V. D. Valavanis & S. Somarakis, 2008. Modeling and predicting potential spawning habitat of anchovy (Engraulis encrasicolus) and round sardinella (Sardinella aurita) based on satellite environmental information. Hydrobiologia 612(1): 201–214.CrossRefGoogle Scholar
  44. Schröder, B., 2008. Challenges of species distribution modeling belowground. Journal of Plant Nutrition and Soil Science 171: 325–337.CrossRefGoogle Scholar
  45. Shepherd, A. J., 1997. Second-Order Methods for Neural Networks. Springer-Verlag, London: 145.Google Scholar
  46. Somarakis, S., P. Drakopoulos & V. Filippou, 2002. Distribution and abundance of larval fishes in the northern Aegean Sea-Eastern Mediterranean—in relation to early summer oceanographic conditions. Journal of Plankton Research 24: 339–357.CrossRefGoogle Scholar
  47. Tetko, I. V., 2002a. Associative neural network. Neural Processing Letters 16: 187–199.CrossRefGoogle Scholar
  48. Tetko, I. V., 2002b. Neural network studies. 4. Introduction to associative neural networks. Journal of Chemical Information in Computer Science 42: 717–728.Google Scholar
  49. Tetko, I. V. & V. Y. Tanchuk, 2002. Application of associative neural networks for prediction of lipophilicity in ALOGPS 2.1 program. Journal of Chemical Information in Computer Science 42: 1136–1145.Google Scholar
  50. Tetko, I. V., D. J. Livingstone & A. I. Luik, 1995. Neural network studies. 1. Comparison of overfitting and overtraining. Journal of Chemical Information in Computer Science 35: 826–833.Google Scholar
  51. Tetko, I. V., I. Sushko, A. K. Pandey, H. Zhu, A. Tropsha, E. Papa, T. Oberg, R. Todeschini, D. Fourches & A. Varnek, 2008. Critical assessment of QSAR models of environmental toxicity against Tetrahymena pyriformis: focusing on applicability domain and overfitting by variable selection. Journal of Chemical Information and Modeling 48(9): 1733–1746.PubMedCrossRefGoogle Scholar
  52. Tsagarakis, K., A. Machias, S. Somarakis, M. Giannoulaki, A. Palialexis & V. D. Valavanis, 2008. Habitat discrimination of juvenile sardines in the Aegean Sea using remotely sensed environmental data. Hydrobiologia 612(1): 215–223.CrossRefGoogle Scholar
  53. Tsimenides, N., G. Bazigos, S. Georgakarakos & A. Kapantagakis, 1992. Distribution of acoustic pelagic fish populations in the northern Aegean Sea. Proceedings of the 1st World Fisheries Congress 5: 33–42.Google Scholar
  54. Valavanis, V. D., 2002. Geographic Information Systems in Oceanography and Fisheries. Taylor & Francis, London: 240.Google Scholar
  55. Valavanis, V. D., Kapantagakis, A., Katara, I., Palialexis, A. 2004. Critical regions: A GIS-based model of marine productivity hotspots. Aquatic Sciences 66(1): 139–148.Google Scholar
  56. Valavanis, V. D., Katara, I., Palialexis, A. 2005. Marine GIS: Identification of mesoscale oceanic thermal fronts. International Journal of Geographical Information Science 19(10): 1131–1147.Google Scholar
  57. Valavanis, V. D., G. J. Pierce, A. F. Zuur, A. Palialexis, A. Saveliev, I. Katara & J. Wang, 2008. Modelling of essential fish habitat based on remote sensing, spatial analysis and GIS. Hydrobiologia 612(1): 5–20.CrossRefGoogle Scholar
  58. Walline, P. D., 2007. Geostatistical simulations of eastern Bering Sea walleye pollock spatial distributions, to estimate sampling precision. ICES Journal of Marine Science 64: 559–569.Google Scholar
  59. Ware, D. M. & R. E. Thomson, 2005. Bottom-up ecosystem trophic dynamics determine fish production in the Northeast Pacific. Science 308: 1280–1285.PubMedCrossRefGoogle Scholar
  60. Wood, S. N., 2006. Generalized Additive Models: An Introduction with R. CRC Press, London.Google Scholar
  61. Wood, S. N. & N. H. Augustin, 2002. GAMs with integrated model selection using penalized regression splines and applications to environmental modelling. Ecological Modelling 157: 157–177.CrossRefGoogle Scholar
  62. Zuur, A. F., E. N. Ieno & G. M. Smith, 2007. Analysing Ecological Data. Springer Series: Statistics for Biology and Health. Springer, New York.Google Scholar
  63. Zuur, A. F., E. N. Ieno & C. S. Elphick, 2010. A protocol for data exploration to avoiding common statistical problems. Methods in Ecology and Evolution 1: 3–14.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2011

Authors and Affiliations

  • A. Palialexis
    • 1
    • 2
  • S. Georgakarakos
    • 3
  • I. Karakassis
    • 1
  • K. Lika
    • 1
  • V. D. Valavanis
    • 2
  1. 1.Department of BiologyUniversity of CreteHeraklion, CreteGreece
  2. 2.Marine GIS Lab, Hellenic Centre for Marine ResearchHeraklion, CreteGreece
  3. 3.Department of Marine SciencesUniversity of the AegeanMytilini, LesvosGreece

Personalised recommendations