Emulated Multivariate Global Sensitivity Analysis for Complex Computer Models Applied to Agricultural Simulators

Abstract

Complex mechanistic computer models often produce functional or multivariate output. Sensitivity analysis can be used to determine what input parameters are responsible for uncertainty in the output. Much of the literature around sensitivity analysis has focused on univariate output. Recent advances have been made in sensitivity analysis for multivariate output. However, these methods often depend on a significant number of model runs and may still be computationally intensive for practical purposes. Emulators have been a proven method for reducing the required number of model runs for univariate sensitivity analysis, with some recent development for multivariate computer models. We propose the use of generalized additive models and random forests combined with a principal component analysis for emulation for a multivariate sensitivity analysis. We demonstrate our method using a complex agricultural simulators. Supplementary materials accompanying this paper appear online.