Advertisement

Predicting Landscapes from Environmental Conditions Using Generative Networks

  • Christian Requena-MesaEmail author
  • Markus Reichstein
  • Miguel Mahecha
  • Basil Kraft
  • Joachim Denzler
Conference paper
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11824)

Abstract

Landscapes are meaningful ecological units that strongly depend on the environmental conditions. Such dependencies between landscapes and the environment have been noted since the beginning of Earth sciences and cast into conceptual models describing the interdependencies of climate, geology, vegetation and geomorphology. Here, we ask whether landscapes, as seen from space, can be statistically predicted from pertinent environmental conditions. To this end we adapted a deep learning generative model in order to establish the relationship between the environmental conditions and the view of landscapes from the Sentinel-2 satellite. We trained a conditional generative adversarial network to generate multispectral imagery given a set of climatic, terrain and anthropogenic predictors. The generated imagery of the landscapes share many characteristics with the real one. Results based on landscape patch metrics, indicative of landscape composition and structure, show that the proposed generative model creates landscapes that are more similar to the targets than the baseline models while overall reflectance and vegetation cover are predicted better. We demonstrate that for many purposes the generated landscapes behave as real with immediate application for global change studies. We envision the application of machine learning as a tool to forecast the effects of climate change on the spatial features of landscapes, while we assess its limitations and breaking points.

This is a preview of subscription content, log in to check access.

Supplementary material

480714_1_En_14_MOESM1_ESM.pdf (2.3 mb)
Supplementary material 1 (pdf 2401 KB)

References

  1. 1.
    Allen, M.R., et al.: IPCC fifth assessment synthesis report-climate change 2014 synthesis report (2014)Google Scholar
  2. 2.
    Brando, V.E., Dekker, A.G.: Satellite hyperspectral remote sensing for estimating estuarine and coastal water quality. IEEE Trans. Geosci. Remote Sens. 41(6), 1378–1387 (2003)CrossRefGoogle Scholar
  3. 3.
    Bunce, R.G.H., Barr, C., Clarke, R., Howard, D., Lane, A.: Land classification for strategic ecological survey. J. Environ. Manage. 47(1), 37–60 (1996)CrossRefGoogle Scholar
  4. 4.
    Cardille, J.A., Turner, M.G.: Understanding landscape metrics. In: Gergel, S.E., Turner, M.G. (eds.) Learning Landscape Ecology, pp. 45–63. Springer, New York (2017).  https://doi.org/10.1007/978-1-4939-6374-4_4CrossRefGoogle Scholar
  5. 5.
    Cushman, S.A., McGarigal, K., Neel, M.C.: Parsimony in landscape metrics: strength, universality, and consistency. Ecol. Ind. 8(5), 691–703 (2008)CrossRefGoogle Scholar
  6. 6.
    Forman, R.T.: Some general principles of landscape and regional ecology. Landscape Ecol. 10(3), 133–142 (1995)CrossRefGoogle Scholar
  7. 7.
    Fox, J., Vogler, J.B.: Land-use and land-cover change in montane mainland southeast asia. Environ. Manag. 36(3), 394–403 (2005)CrossRefGoogle Scholar
  8. 8.
    Franklin, S., Dickson, E., Hansen, M., Farr, D., Moskal, L.: Quantification of landscape change from satellite remote sensing. Forestry Chronicle 76(6), 877–886 (2000)CrossRefGoogle Scholar
  9. 9.
    Getzin, S., Wiegand, K., Schöning, I.: Assessing biodiversity in forests using very high-resolution images and unmanned aerial vehicles. Methods Ecol. Evol. 3(2), 397–404 (2012)CrossRefGoogle Scholar
  10. 10.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in neural information processing systems, pp. 2672–2680 (2014)Google Scholar
  11. 11.
    Groom, G., Mücher, C., Ihse, M., Wrbka, T.: Remote sensing in landscape ecology: experiences and perspectives in a european context. Landscape Ecol. 21(3), 391–408 (2006)CrossRefGoogle Scholar
  12. 12.
    Haase, G., Richter, H.: Current trends in landscape research. GeoJournal 7(2), 107–119 (1983)CrossRefGoogle Scholar
  13. 13.
    Hartmann, J., Moosdorf, N.: The new global lithological map database GLiM: a representation of rock properties at the Earth surface. Geochemistry, Geophysics, Geosystems, 13(12) (2012)Google Scholar
  14. 14.
    Hijmans, R.J., Cameron, S., Parra, J., Jones, P., Jarvis, A., Richardson, K.: WorldClim-Global Climate Data. Free Climate Data for Ecological Modeling and GIS (2015)Google Scholar
  15. 15.
    Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv preprint (2017)Google Scholar
  16. 16.
    Jarvis, A., Reuter, H.I., Nelson, A., Guevara, E.: Hole-filled srtm for the globe version, 4 (2008)Google Scholar
  17. 17.
    Jun, C., Ban, Y., Li, S.: China: open access to Earth land-cover map. Nature 514(7523), 434 (2014)CrossRefGoogle Scholar
  18. 18.
    Kerr, J.T., Ostrovsky, M.: From space to species: ecological applications for remote sensing. Trends Ecol. Evol. 18(6), 299–305 (2003)CrossRefGoogle Scholar
  19. 19.
    Klijn, J.: Hierarchical concepts in landscape ecology and its underlying disciplines. DLO winand staring centre report 100, (1995)Google Scholar
  20. 20.
    Langfelder, P., Horvath, S.: Fast R functions for robust correlations and hierarchical clustering. J. Stat. Softw. 46(11), i11 (2012)CrossRefGoogle Scholar
  21. 21.
    McGarigal, K., Cushman, S.A., Neel, M.C., Ene, E.: FRAGSTATS v4: Spatial Pattern Analysis Program for Categorical and Continuous Maps. University of Massachusettes, Amherst, MA. http://www.umass.edu/landeco/research/fragstats/fragstats.html (2007) (2012). https://doi.org/citeulike-article-id:287784
  22. 22.
    Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
  23. 23.
    Mücher, C.A., Klijn, J.A., Wascher, D.M., Schaminée, J.H.: A new european landscape classification (lanmap): a transparent, flexible and user-oriented methodology to distinguish landscapes. Ecol. Ind. 10(1), 87–103 (2010)CrossRefGoogle Scholar
  24. 24.
    Newton, A.C., et al.: Remote sensing and the future of landscape ecology. Prog. Phys. Geogr. 33(4), 528–546 (2009)CrossRefGoogle Scholar
  25. 25.
    Otterman, J.: Anthropogenic impact on the albedo of the earth. Climatic Change 1(2), 137–155 (1977)CrossRefGoogle Scholar
  26. 26.
    Roberts, D.R., et al.: Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography 40(8), 913–929 (2017)CrossRefGoogle Scholar
  27. 27.
    Simmons, M., Cullinan, V., Thomas, J.: Satellite imagery as a tool to evaluate ecological scale. Landscape Ecol. 7(2), 77–85 (1992)CrossRefGoogle Scholar
  28. 28.
    Uuemaa, E., Antrop, M., Roosaare, J., Marja, R., Mander, Ü.: Landscape metrics and indices: an overview of their use in landscape research. Living Rev. Landscape Res. 3(1), 1–28 (2009)Google Scholar
  29. 29.
    Wilcox, R.R.: Robust generalizations of classical test reliability and cronbach’s alpha. Br. J. Math. Stat. Psychol. 45(2), 239–254 (1992)CrossRefGoogle Scholar
  30. 30.
    Zachos, J., Pagani, M., Sloan, L., Thomas, E., Billups, K.: Trends, rhythms, and aberrations in global climate 65 ma to present. Science 292(5517), 686–693 (2001)CrossRefGoogle Scholar
  31. 31.
    Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–595 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Climate Informatics, Institute of Data ScienceGerman Aerospace CenterJenaGermany
  2. 2.Computer Vision Group, Friedrich-Schiller-UniversitätJenaGermany
  3. 3.Max-Planck-Institute for BiogeochemistryJenaGermany
  4. 4.Michael Stifel Center Jena for Data-Driven and Simulation ScienceJenaGermany

Personalised recommendations

Cite paper

Buy options