Derivative-based global sensitivity analysis for models with high-dimensional inputs and functional outputs

2019/02/12 by Cleaves, Helen L., Alexanderian, Alen, Guy, Hayley +2
#62H99 #65C20 #65C50 #65D15 #Computation (stat.CO) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1902.04630

Abstract

We present a framework for derivative-based global sensitivity analysis (GSA) for models with high-dimensional input parameters and functional outputs. We combine ideas from derivative-based GSA, random field representation via Karhunen--Loève expansions, and adjoint-based gradient computation to provide a scalable computational framework for computing the proposed derivative-based GSA measures. We illustrate the strategy for a nonlinear ODE model of cholera epidemics and for elliptic PDEs with application examples from geosciences and biotransport.

Related

• Gradient-enhanced global sensitivity analysis with Poincaré chaos expansions
• Derivative-based Shapley value for global sensitivity analysis and machine learning explainability
• Computing derivative-based global sensitivity measures using polynomial chaos expansions
• Global sensitivity analysis for models described by stochastic differential equations
• Extremum Sensitivity Analysis with Polynomial Monte Carlo Filtering