Spatial Variable Importance Assessment for Yield Prediction in Precision Agriculture

  • Georg Ruß
  • Alexander Brenning
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6065)


Precision Agriculture applies state-of-the-art GPS technology in connection with site-specific, sensor-based crop management. It can also be described as a data-driven approach to agriculture, which is strongly connected with a number of data mining problems. One of those is also an inherently important task in agriculture: yield prediction. Given a yield prediction model, which of the predictor variables are the important ones?

In the past, a number of approaches have been proposed towards this problem. For yield prediction, a broad variety of regression models for non-spatial data can be adapted for spatial data using a novel spatial cross-validation technique. Since this procedure is at the core of variable importance assessment, it will be briefly introduced here. Given this spatial yield prediction model, a novel approach towards assessing a variable’s importance will be presented. It essentially consists of picking each of the predictor variables, one at a time, permutating its values in the test set and observing the deviation of the model’s RMSE. This article uses two real-world data sets from precision agriculture and evaluates the above procedure.


Precision Agriculture Spatial Data Mining Regression Spatial Cross-Validation Variable Importance 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, pp. 144–152. ACM Press, New York (1992)CrossRefGoogle Scholar
  2. 2.
    Breiman, L.: Bagging predictors. Technical report, Department of Statistics, Univ. of California, Berkeley (1994)Google Scholar
  3. 3.
    Breiman, L.: Random forests. Machine Learning, 45(1):5–32 (2001)Google Scholar
  4. 4.
    Brenning, A.: Spatial prediction models for landslide hazards: review, comparison and evaluation. Natural Hazards and Earth System Science 5(6), 853–862 (2005)CrossRefGoogle Scholar
  5. 5.
    Brenning, A., Itzerott, S.: Comparing classifiers for crop identification based on multitemporal landsat tm/etm data. In: Proceedings of the 2nd workshop of the EARSeL Special Interest Group Remote Sensing of Land Use and Land Cover, September 2006, pp. 64–71 (2006)Google Scholar
  6. 6.
    Brenning, A., Lausen, B.: Estimating error rates in the classification of paired organs. Statistics in Medicine 27(22), 4515–4531 (2008)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Brenning, A., Piotraschke, H., Leithold, P.: Geostatistical analysis of on-farm trials in precision agriculture. In: Ortiz, J.M., Emery, X. (eds.) GEOSTATS 2008, Proceedings of the Eighth International Geostatistics Congress, December 12, vol. 2, pp. 1131–1136 (2008)Google Scholar
  8. 8.
    Bühlmann, P.: Bootstraps for time series. Statistical Science 17, 52–72 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Cressie, N.A.C.: Statistics for Spatial Data. Wiley, New York (1993)Google Scholar
  10. 10.
    Crone, S.F., Lessmann, S., Pietsch, S.: Forecasting with computational intelligence - an evaluation of support vector regression and artificial neural networks for time series prediction. In: International Joint Conference on Neural Networks, IJCNN 2006, pp. 3159–3166 (2006)Google Scholar
  11. 11.
    Dash, M., Liu, H.: Feature selection for classification. Intelligent Data Analysis 1, 131–156 (1997)CrossRefGoogle Scholar
  12. 12.
    Huang, C., Yang, L., Wylie, B., Homer, C.: A strategy for estimating tree canopy density using landsat 7 etm+ and high resolution images over large areas. In: Proceedings of the Third International Conference on Geospatial Information in Agriculture and Forestry (2001)Google Scholar
  13. 13.
    Knudby, A., Brenning, A., LeDrew, E.: New approaches to modelling fish-habitat relationships. Ecological Modelling 221, 503–511 (2010)CrossRefGoogle Scholar
  14. 14.
    Langley, P.: Selection of relevant features in machine learning. In: Proceedings of the AAAI Fall symposium on relevance, pp. 140–144. AAAI Press, Menlo Park (1994)Google Scholar
  15. 15.
    Leathwick, J.R., Elith, J., Francis, M.P., Hastie, T., Taylor, P.: Variation in demersal fish species richness in the oceans surrounding new zealand: an analysis using boosted regression trees. Marine Ecology Progress 321, 267–281 (2006)CrossRefGoogle Scholar
  16. 16.
    Lobell, D.B., Ortiz-Monasterio, J.I., Asner, G.P., Naylor, R.L., Falcon, W.P.: Combining field surveys, remote sensing, and regression trees to understand yield variations in an irrigated wheat landscape. Agronomy Journal 97, 241–249 (2005)Google Scholar
  17. 17.
    Pozdnoukhov, A., Foresti, L., Kanevski, M.: Data-driven topo-climatic mapping with machine learning methods. Natural Hazards 50(3), 497–518 (2009)Google Scholar
  18. 18.
    R Development Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2009), ISBN 3-900051-07-0Google Scholar
  19. 19.
    Ruß, G.: Data mining of agricultural yield data: A comparison of regression models. In: Perner, P. (ed.) Advances in Data Mining. Applications and Theoretical Aspects. LNCS, vol. 5633, pp. 24–37. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  20. 20.
    Ruß, G., Brenning, A.: Data mining in precision agriculture: Management of spatial information. In: Proceedings of IPMU 2010. Springer, Heidelberg (submitted for review 2010)Google Scholar
  21. 21.
    Ruß, G., Kruse, R., Schneider, M., Wagner, P.: Estimation of neural network parameters for wheat yield prediction. In: Bramer, M. (ed.) Proceedings of AI in Theory and Practice II, IFIP 2008, July 2008, vol. 276, pp. 109–118. Springer, Heidelberg (2008)Google Scholar
  22. 22.
    Ruß, G., Kruse, R., Schneider, M., Wagner, P.: Optimizing wheat yield prediction using different topologies of neural networks. In: Verdegay, J., Ojeda-Aciego, M., Magdalena, L. (eds.) Proceedings of IPMU 2008, June 2008, pp. 576–582. University of Málaga (2008)Google Scholar
  23. 23.
    Ruß, G., Kruse, R., Wagner, P., Schneider, M.: Data mining with neural networks for wheat yield prediction. In: Perner, P. (ed.) ICDM 2008. LNCS (LNAI), vol. 5077, pp. 47–56. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  24. 24.
    Stein, M.L.: Interpolation of Spatial Data: Some Theory for Kriging, June 1999. Springer Series in Statistics. Springer, Heidelberg (1999)zbMATHGoogle Scholar
  25. 25.
    Strobl, C., Boulesteix, A.-L., Kneib, T., Augustin, T., Zeileis, A.: Conditional variable importance for random forests. BMC Bioinformatics 9(1), 307 (2008)CrossRefGoogle Scholar
  26. 26.
    Strobl, C., Boulesteix, A.-L., Zeileis, A., Hothorn, T.: Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics 8(1), 25 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Georg Ruß
    • 1
  • Alexander Brenning
    • 2
  1. 1.Otto-von-Guericke-Universität MagdeburgGermany
  2. 2.University of WaterlooCanada

Personalised recommendations