A Comparison of Three Learning Methods to Predict N2O Fluxes and N Leaching

Abstract

The environmental costs of intensive farming activities are often under-estimated or not included into the rural development plans, even though they play an important role in addressing future society¿s needs. This paper focus on the use of statistical learning methods to predict the N2O emissions and N leaching under several conservative scenarios, in order to provide an alternative approach to deterministic models at macro-scale. To that aim, three learning methods, namely neural networks (multilayer perceptrons), SVM and random forests, are compared and provide accurate solutions.