Global Sensitivity Analysis of environmental models: Convergence and validation

By Fanny Sarrazin, Francesca Pianosi, Thorsten Wagener. Environmental Modelling & Software, 2016

328 citations recorded by the source corpus.

We address two critical choices in Global Sensitivity Analysis (GSA): the choice of the sample size and of the threshold for the identification of insensitive input factors. Guidance to assist users with those two choices is still insufficient. We aim at filling this gap. Firstly, we define criteria to quantify the convergence of sensitivity indices, of ranking and of screening, based on a bootstrap approach. Secondly, we investigate the screening threshold with a quantitative validation procedure for screening results. We apply the proposed methodologies to three hydrological models with varying complexity utilizing three widely-used GSA methods (RSA, Morris, Sobol'). We demonstrate that convergence of screening and ranking can be reached before sensitivity estimates stabilize. Convergence dynamics appear to be case-dependent, which suggests that "fit-for-all" rules for sample sizes should not be used. Other modellers can easily adopt our criteria and procedures for a wide range of GSA methods and cases. We propose criteria to measure the convergence for screening, ranking and indices.We investigate the screening threshold with a quantitative validation procedure.We test those procedures for three widely-used GSA methods.Screening/ranking convergence can be reached before sensitivity indices stabilize.Convergence dynamics are case-dependent, which precludes generic rules.

Subfields: Environmental Engineering, Ocean Engineering, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/8b3f3042ca22ed50004cf3f27c3f08599a629052

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Environmental Engineering

1. Saman Razavi
2. Qingyun Duan
3. Joseph H. A. Guillaume
4. Anthony J. Jakeman
5. Holger R. Maier
6. John D. Jakeman
7. Andrea Saltelli
8. Hoshin V. Gupta

In Ocean Engineering

1. Holger R. Maier
2. Andrea Saltelli
3. Anthony J. Jakeman
4. Qingyun Duan
5. Hoshin V. Gupta
6. Saman Razavi
7. Jasper A. Vrugt
8. Thorsten Wagener

In Statistics and Probability

1. Bertrand Iooss
2. Clémentine Prieur
3. Emanuele Borgonovo
4. Stefano Tarantola
5. Elmar Plischke
6. Andrea Saltelli
7. Hoshin V. Gupta
8. Qingyun Duan

Citations in the corpus

• The Future of Sensitivity Analysis: An essential discipline for systems modeling and policy support (2020, positive): “Recently developed convergence criteria (e.g., Sarrazin et al., 2016; Sheikholeslami et al., 2020) and stopping criteria (see, e.g., Gilquin et al., 2020; Rugama et al., 2018) can be useful in this regard.”