A comparison of eight metamodeling techniques for the simulation of N2O fluxes and N leaching from corn crops

Abstract

The environmental costs of intensive farming activities are often underestimated or not traded by the market, even though they play an important role in addressing future society's needs. The estimation of nitrogen (N) dynamics is thus an important issue which demands detailed simulation based methods and their integrated use to correctly represent complex and nonlinear interactions into cropping systems. To calculate the N 2 O flux and N leaching from European arable lands, a modeling framework has been developed by linking the CAPRI agro-economic dataset with the DNDC-EUROPE bio-geo-chemical model. But, despite the great power of modern calculators, their use at continental scale is often too computationally costly. By comparing several statistical methods this paper aims to design a metamodel able to approximate the expensive code of the detailed modeling approach, devising the best compromise between estimation performance and simulation speed. We describe the use of two parametric (linear) models and six nonparametric approaches: two methods based on splines (ACOSSO and SDR), one method based on kriging (DACE), a neural networks method (multilayer perceptron, MLP), SVM and a bagging method (random forest, RF). This analysis shows that, as long as few data are available to train the model, splines approaches lead to best results, while when the size of training dataset increases, SVM and RF provide faster and more accurate solutions.

Emulation of Leaf, Canopy and Atmosphere Radiative Transfer Models for Fast Global Sensitivity Analysis

“…Various emulators based on statistical learning have already been developed in the climate and environmental modeling community for the last few years (e.g., [22,35,36,[39][40][41][42][43]). These emulators have in common that they were developed from adaptive, flexible nonparametric regression algorithms, typically within the family of machine learning regression algorithms (MLRAs) [44].…”

Evaluating four nitrous oxide emission algorithms in response to N rate on an irrigated corn field

“…Studies have shown mixed model performance in simulating N 2 O emissions under different climate and management conditions (Frolking et al, 1998;Li et al, 2005;Villa-Vialaneix et al, 2012;Vogeler et al, 2013). Comparisons of the different N 2 O emission algorithms can improve our understanding of N 2 O emissions.…”

Investigating the influence of geometrical traits on light interception efficiency of apple trees: A modelling study with MAppleT

“…Among meta-modelling approaches [30,31], two were investigated: a multiple polynomial linear metamodel (PLMM, Faivre, unpublished) and a generalized additive model (GAM; Woods, 2006). The first meta-model, PLMM, aims at modelling the simulated STAR variable as a linear combination of cross-product of polynomial functions of maximum degree between the different MAppleT parameters (eq.…”