TITLE:
Comparison of Machine Learning Regression Methods to Simulate NO3 Flux in Soil Solution under Potato Crops
AUTHORS:
J. G. Fortin, A. Morais, F. Anctil, L. E. Parent
KEYWORDS:
Machine Learning Regression; Nitrate Leaching; Suction Lysimeter; Potato Cropping System
JOURNAL NAME:
Applied Mathematics,
Vol.5 No.5,
March
24,
2014
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.