Advertisement

A Deep Learning Approach to Species Distribution Modelling

  • Christophe Botella
  • Alexis Joly
  • Pierre Bonnet
  • Pascal Monestiez
  • François Munoz
Chapter
Part of the Multimedia Systems and Applications book series (MMSA)

Abstract

Species distribution models (SDM) are widely used for ecological research and conservation purposes. Given a set of species occurrence, the aim is to infer its spatial distribution over a given territory. Because of the limited number of occurrences of specimens, this is usually achieved through environmental niche modeling approaches, i.e. by predicting the distribution in the geographic space on the basis of a mathematical representation of their known distribution in environmental space (= realized ecological niche). The environment is in most cases represented by climate data (such as temperature, and precipitation), but other variables such as soil type or land cover can also be used. In this paper, we propose a deep learning approach to the problem in order to improve the predictive effectiveness. Non-linear prediction models have been of interest for SDM for more than a decade but our study is the first one bringing empirical evidence that deep, convolutional and multilabel models might participate to resolve the limitations of SDM. Indeed, the main challenge is that the realized ecological niche is often very different from the theoretical fundamental niche, due to environment perturbation history, species propagation constraints and biotic interactions. Thus, the realized abundance in the environmental feature space can have a very irregular shape that can be difficult to capture with classical models. Deep neural networks on the other side, have been shown to be able to learn complex non-linear transformations in a wide variety of domains. Moreover, spatial patterns in environmental variables often contains useful information for species distribution but are usually not considered in classical models. Our study shows empirically how convolutional neural networks efficiently use this information and improve prediction performance.

References

  1. 1.
    Hutchinson, G. (1957). Concluding remarks. Cold spring harbor symposium on quantitative biology. 22, 415–427.CrossRefGoogle Scholar
  2. 2.
    Hastie, T. & Tibshirani, R. (1986). Generalized Additive Models. Statistical Science, 1(3), 297–318.CrossRefGoogle Scholar
  3. 3.
    Friedman, J. (1991). Multivariate adaptive regression splines. The annals of statistics, 1–67.MathSciNetCrossRefGoogle Scholar
  4. 4.
    Phillips, S., Dudik, M., Schapire, R. (2004). A maximum entropy approach to species distribution modeling. Proceedings of the twenty-first international conference on Machine learning, 83.Google Scholar
  5. 5.
    Phillips, S., Anderson, R. & Schapire, R. (2006). Maximum entropy modeling of species geographic distributions. Ecological modelling, 190(3), 231–259.CrossRefGoogle Scholar
  6. 6.
    Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep Learning. MIT Press.Google Scholar
  7. 7.
    Krizhevsky, A., Sutskever, I. & Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 1097–1105.Google Scholar
  8. 8.
    Lek, S., Delacoste, M., Baran, P., Dimopoulos, I., Lauga, J. & Aulagnier, S. (1996). Application of neural networks to modelling nonlinear relationships in ecology. Ecological modelling, 90(1), 39–52.CrossRefGoogle Scholar
  9. 9.
    Thuiller, W. (2003). BIOMOD–optimizing predictions of species distributions and projecting potential future shifts under global change. Global change biology, 9(10), 1353–1362.CrossRefGoogle Scholar
  10. 10.
    Leathwick, J.R. Elith, J. & Hastie, T. (2006). Comparative performance of generalized additive models and multivariate adaptive regression splines for statistical modelling of species distributions. Ecological modelling, 199(2), 188–196.CrossRefGoogle Scholar
  11. 11.
    LeCun, Y. & others. (1989). Generalization and network design strategies. Connectionism in perspective, 143–155.Google Scholar
  12. 12.
    Ward, G., Hastie, T., Barry, S., Elith, J. & Leathwick, J. (2009). Presence-only data and the EM algorithm. Biometrics, 65(2), 554–563.MathSciNetCrossRefGoogle Scholar
  13. 13.
    Berman, M., & Turner, T. R. (1992). Approximating point process likelihoods with GLIM. Applied Statistics, 31–38.CrossRefGoogle Scholar
  14. 14.
    P Anderson, R., Dudk, M., Ferrier, S., Guisan, A., J Hijmans, R., Huettmann, F., …& A Loiselle, B. (2006). Novel methods improve prediction of species’ distributions from occurrence data. Ecography, 29(2), 129–151.CrossRefGoogle Scholar
  15. 15.
    Phillips, S. & Dudik, M. (2008). Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation. Ecography, 31(2), 161–175.CrossRefGoogle Scholar
  16. 16.
    Fithian, W., & Hastie, T. (2013). Finite-sample equivalence in statistical models for presence-only data. The annals of applied statistics.7,4,1917.MathSciNetCrossRefGoogle Scholar
  17. 17.
    Phillips, S. Anderson, R., Dudik, M. Schapire, R. & Blair, M. (2017). Opening the black box: an open-source release of Maxent. Ecography.CrossRefGoogle Scholar
  18. 18.
    Rumelhart, D., Hinton, G. & Williams, R. and others (1988). Learning representations by back-propagating errors. Cognitive modeling, 5(3).Google Scholar
  19. 19.
    Nair, V. & Hinton, G. (2010). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th international conference on machine learning (ICML-10), 807–814.Google Scholar
  20. 20.
    Ioffe, S. & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. International Conference on Machine Learning. 448–456.Google Scholar
  21. 21.
    Dutrève, B. & Robert, S. (2016). INPN - Données flore des CBN agrégées par la FCBN. Version 1.1. SPN - Service du Patrimoine naturel, Muséum national d’Histoire naturelle, Paris. Occurrence Dataset  https://doi.org/10.15468/omae84 accessed via GBIF.org on 2017-08-30.
  22. 22.
    Karger, D. N., Conrad, O., Bohner, J., Kawohl, T., Kreft, H., Soria-Auza, R.W. & Kessler, M. (2016). Climatologies at high resolution for the earth’s land surface areas. arXiv preprint arXiv:1607.00217.Google Scholar
  23. 23.
    Karger, D. N., Conrad, O., Bohner, J., Kawohl, T., Kreft, H., Soria-Auza, R.W. & Kessler, M. (2016). CHELSEA climatologies at high resolution for the earth’s land surface areas (Version 1.1).Google Scholar
  24. 24.
    Zomer, R., Bossio, D., Trabucco, A., Yuanjie, L., Gupta, D. & Singh, V. (2007). Trees and water: smallholder agroforestry on irrigated lands in Northern India.Google Scholar
  25. 25.
    Zomer, R., Trabucco, A., Bossio, D. & Verchot, L. (2008). Climate change mitigation: A spatial analysis of global land suitability for clean development mechanism afforestation and reforestation. Agriculture, ecosystems & environment, 126(1), 67–80.CrossRefGoogle Scholar
  26. 26.
    Panagos, P. (2006). The European soil database. GEO: connexion, 5(7), 32–33.Google Scholar
  27. 27.
    Panagos, P., Van Liedekerke, M., Jones, A., Montanarella, L. (2012). European Soil Data Centre: Response to European policy support and public data requirements. Land Use Policy, 29(2),329–338.CrossRefGoogle Scholar
  28. 28.
    Van Liedekerke, M. Jones, A. & Panagos, P. (2006). ESDBv2 Raster Library-a set of rasters derived from the European Soil Database distribution v2. 0. European Commission and the European Soil Bureau Network, CDROM, EUR, 19945.Google Scholar
  29. 29.
    Chen, T., Li, M., Li, Y., Lin, M., Wang, N., Wang, M., …& Zhang, Z. (2015). Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274.Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Christophe Botella
    • 1
    • 2
    • 3
    • 4
  • Alexis Joly
    • 5
  • Pierre Bonnet
    • 3
    • 6
  • Pascal Monestiez
    • 4
  • François Munoz
    • 7
  1. 1.INRIA Sophia-Antipolis - ZENITH Team, LIRMM - UMR 5506 - CC 477MontpellierFrance
  2. 2.INRA, UMR AMAPMontpellierFrance
  3. 3.AMAP, Univ Montpellier, CIRAD, CNRS, INRA, IRDMontpellierFrance
  4. 4.BioSP, INRA, Site AgroparcAvignonFrance
  5. 5.Inria ZENITH TeamMontpellierFrance
  6. 6.CIRAD, UMR AMAPMontpellierFrance
  7. 7.Université Grenoble AlpesSaint-Martin-d’HèresFrance

Personalised recommendations