Comparison of Machine Learning Regression Methods to Simulate NO₃ Flux in Soil Solution under Potato Crops

J. G. Fortin, A. Morais, F. Anctil, L. E. Parent

Department of Civil and Water Engineering, Université Laval, Québec, Canada.
Department of Soils and Agrifood Engineering, Université Laval, Québec, Canada.

DOI: 10.4236/am.2014.55079                

Abstract

Nitrate (NO₃) leaching is a major issue in sandy soils intensively cropped to potato. Modelling could test the effect of management practices on nitrate leaching, particularly with regard to optimal N application rates. The NO₃ concentration in the soil solution is well known for its local heterogeneity and hence represents a major challenge for modeling. The objective of this 2-year-study was to evaluate machine learning regression methods to simulate seasonal NO₃ concentration dynamics in suction lysimeters in potato plots receiving different N application rates. Four machine learning function approximation methods were compared: multiple linear regressions, multivariate adaptive regression splines, multiple-layer perceptrons, and least squares support vector machines. Input candidates were chosen for known relationships with NO3 concentration. The best regression model was obtained with a 6-inputs least squares support vector machine combining cumulative rainfall, cumulative temperature, day of the year, N fertilisation rate, soil texture, and depth.

Keywords

Machine Learning Regression; Nitrate Leaching; Suction Lysimeter; Potato Cropping System

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Li, H., Parent, L.-E., Karam, A. and Tremblay, C. (2003) Efficiency of Soil and Fertilizer Nitrogen of a Sod-Potato System in the Humid, Acid and Cool Environment. Plant and Soil, 251, 23-26. http://dx.doi.org/10.1023/A:1022983830986
[2]	Cambouris, A.N., Zebarth, B.J., Nolin, M.C. and Laverdière, M.R. (2008) Apparent Fertilizer Nitrogen Recovery and Residual Soil Nitrate under Continuous Potato Cropping: Effect of N Fertilization Rate and Timing. Canadian Journal of Soil Science, 88, 813-825. http://dx.doi.org/10.4141/CJSS07107
[3]	Jiang, Y., Zebarth, B.J., Somers, G.H., MacLeod, J.A. and Savard, M.M. (2012) Nitrate Leaching from Potato Production in Eastern Canada. In: He, Z., Larkin, R.P. and Honeycutt, C.W., Eds., Sustainable Potato Production: Global Case Studies, Springer, The Netherlands, 233-250. http://dx.doi.org/10.1007/978-94-007-4104-1_13
[4]	Lord, E.I. and Shepherd, M.A. (1993) Development in the Use of Porous Ceramic Cum for Measuring Nitrate Leaching. Journal of Soil Science, 44, 435-449. http://dx.doi.org/10.1111/j.1365-2389.1993.tb00466.x
[5]	Fortin, J.G., Bolinder, M.A., Anctil, F., Katterer, T., Andrén, O. and Parent, L.-E. (2011) Effects of Climatic Data Low-Pass Filtering on the ICBM Temperatureand Moisture-Based Soil Biological Activity Factors in a Cool and Humid Climate. Ecological Modelling, 222, 3050-3060. http://dx.doi.org/10.1016/j.ecolmodel.2011.06.011
[6]	Sheldrick, B.H. and Wang, C. (1993) Particle Size Analysis. In: Carter, M.R., Ed., Soil Sampling and Methods of Analysis, Lewis Publishers, Boca Raton, 499-517.
[7]	Rosner, B. (2006) Fundamentals of Biostatistics. Duxbury Press, Boston, 6th Edition.
[8]	Friedman, J.H. and Roosen, C.B. (1995) An Introduction to Multivariate Adaptive Regression Splines. Statistical Methods in Medical Research, 4, 197-217. http://dx.doi.org/10.1177/096228029500400303
[9]	Friedman, J.H. (1991) Multivariate Adaptive Regression Splines. Annals of Statistics, 19, 1-141. http://dx.doi.org/10.1214/aos/1176347963
[10]	García Nieto, P.J., Martínez Torres, J., de Cos Juez, F.J. and Sánchez Lasheras, F. (2012) Using Multivariate Adaptive Regression Splines and Multilayer Perceptron Networks to Evaluate Paper Manufactured Using Eucalyptus globulus. Applied Mathematics and Computation, 219, 755-763. http://dx.doi.org/10.1016/j.amc.2012.07.001
[11]	Vapnik, V. (1998) Statistical Learning Theory. Wiley-Interscience, New York.
[12]	Chou, S.M., Lee, T.S., Shao, Y.E. and Chen, I.F. (2004) Mining the Breast Cancer Pattern Using Artificial Neural Networks and Multivariate Adaptive Regression Splines. Expert Systems with Applications, 27, 133-142. http://dx.doi.org/10.1016/j.eswa.2003.12.013
[13]	Jekabsons, G. (2013) ARESLab: Adaptive Regression Splines Toolbox for Matlab/Octave. http://www.cs.rtu.lv/jekabsons/
[14]	Yonaba, H., Anctil, F. and Fortin, V. (2010) Comparing Sigmoid Transfer Functions for Neural Network Multistep Ahead Streamflow Forecasting. Journal of Hydrologic Engineering, 15, 275-283. http://dx.doi.org/10.1061/(ASCE)HE.1943-5584.0000188
[15]	Wolpert, D.H. (1992) Stacked Generalisation. Neural Network, 5, 241-259. http://dx.doi.org/10.1016/S0893-6080(05)80023-1
[16]	Asefa, T., Kemblowski, M.W., Urroz, G., McKee, M. and Khalil, A. (2004) Support Vectors-Based Groundwater Head Observation Networks Design. Water Resources Research, 40, W11509. http://dx.doi.org/10.1029/2004WR003304
[17]	Wang, W.J., Xu, Z.B., Lu, W.Z. and Zhang, X.Y. (2003) Determination of the Spread Parameter in the Gaussian Kernel for Classification and Regression. Neurocomputing, 55, 643-663. http://dx.doi.org/10.1016/S0925-2312(02)00632-X
[18]	Pelckmans, K., Suykens, J.A.K., Van Gestel, T., De Brabranter, J., Lukas, L., Hamers, B., De Moor, B. and Vandewalle, J. (2003) LS-SVMlab Toolbox User’s Guide, Version 1.5. ESAT-SCD-SISTA Technical Report 02-14. http://www.esat.kuleuven.ac.be/sista/lssvmlab/
[19]	Kohonen, T. (1982) Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics, 43, 59-69. http://dx.doi.org/10.1007/BF00337288
[20]	Fortin, J.G., Bolinder, M.A., Anctil, F., Katterer, T., Andrén, O. and Parent, L.E. (2011) Effects of Climatic Data Low-Pass Filtering on the ICBM Temperatureand Moisture-Based Soil Biological Activity Factors in a Cool and Humid Climate. Ecological Modelling, 222, 3050-3060. http://dx.doi.org/10.1016/j.ecolmodel.2011.06.011
[21]	Nash, J.E. and Sutcliffe, J.V. (1970) River Flow Forecasting through Conceptual Models: A Discussion of Principles. Journal of Hydrology, 10, 282-290. http://dx.doi.org/10.1016/0022-1694(70)90255-6
[22]	Sharifi, M., Zebarth, B.J., Hajabbasi, M.A. and Kalbasi, M. (2005) Dry Matter and Nitrogen Accumulation and Root Morphological Characteristics of Two Clonal Selections of “Russet Norkotah” Potato as Affected by Nitrogen Fertilization. Journal of Plant Nutrition, 28, 2243-2253. http://dx.doi.org/10.1080/01904160500323552
[23]	Gasser, M.O. (2000) Transformation et Transfert de L’azote dans les Sols Sableux Cultivés en Pomme de Terre. Ph.D. Thesis, Université Laval, Ste-Foy.
[24]	Gasser, M.O., Caron, J., Lagacé, R. and Laverdière, M.R. (2003) Predicting Nitrate Leaching under Potato Crops Using Transfer Functions. Journal of Environmental Quality, 32, 1464-1473. http://dx.doi.org/10.2134/jeq2003.1464