Skip to content

Distribution-based sensitivity analysis from a generic input-output sample

Research output: Contribution to journalArticle

Standard

Distribution-based sensitivity analysis from a generic input-output sample. / Pianosi, Francesca; Wagener, Thorsten.

In: Environmental Modelling and Software, Vol. 108, 10.2018, p. 197-207.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Pianosi, Francesca ; Wagener, Thorsten. / Distribution-based sensitivity analysis from a generic input-output sample. In: Environmental Modelling and Software. 2018 ; Vol. 108. pp. 197-207.

Bibtex

@article{a4ecc09722a14e2bb07f2643357ad7e7,
title = "Distribution-based sensitivity analysis from a generic input-output sample",
abstract = "In a previous paper we introduced a distribution-based method for Global Sensitivity Analysis (GSA), called PAWN, which uses cumulative distribution functions of model outputs to assess their sensitivity to the model's uncertain input factors. Over the last three years, PAWN has been employed in the environmental modelling field as a useful alternative or complement to more established variance-based methods. However, a major limitation of PAWN up to now was the need for a tailored sampling strategy to approximate the sensitivity indices. Furthermore, this strategy required three tuning parameters whose optimal choice was rather unclear. In this paper, we present an alternative approximation procedure that tackles both issues and makes PAWN applicable to a generic sample of inputs and outputs while requiring only one tuning parameter. The new implementation therefore allows the user to estimate PAWN indices as complementary metrics in multi-method GSA applications without additional computational cost.",
keywords = "Distribution-based methods, Global sensitivity analysis, Moment-independent methods, Multi-method GSA",
author = "Francesca Pianosi and Thorsten Wagener",
year = "2018",
month = "10",
doi = "10.1016/j.envsoft.2018.07.019",
language = "English",
volume = "108",
pages = "197--207",
journal = "Environmental Modelling and Software",
issn = "1364-8152",
publisher = "Elsevier Science",

}

RIS - suitable for import to EndNote

TY - JOUR

T1 - Distribution-based sensitivity analysis from a generic input-output sample

AU - Pianosi, Francesca

AU - Wagener, Thorsten

PY - 2018/10

Y1 - 2018/10

N2 - In a previous paper we introduced a distribution-based method for Global Sensitivity Analysis (GSA), called PAWN, which uses cumulative distribution functions of model outputs to assess their sensitivity to the model's uncertain input factors. Over the last three years, PAWN has been employed in the environmental modelling field as a useful alternative or complement to more established variance-based methods. However, a major limitation of PAWN up to now was the need for a tailored sampling strategy to approximate the sensitivity indices. Furthermore, this strategy required three tuning parameters whose optimal choice was rather unclear. In this paper, we present an alternative approximation procedure that tackles both issues and makes PAWN applicable to a generic sample of inputs and outputs while requiring only one tuning parameter. The new implementation therefore allows the user to estimate PAWN indices as complementary metrics in multi-method GSA applications without additional computational cost.

AB - In a previous paper we introduced a distribution-based method for Global Sensitivity Analysis (GSA), called PAWN, which uses cumulative distribution functions of model outputs to assess their sensitivity to the model's uncertain input factors. Over the last three years, PAWN has been employed in the environmental modelling field as a useful alternative or complement to more established variance-based methods. However, a major limitation of PAWN up to now was the need for a tailored sampling strategy to approximate the sensitivity indices. Furthermore, this strategy required three tuning parameters whose optimal choice was rather unclear. In this paper, we present an alternative approximation procedure that tackles both issues and makes PAWN applicable to a generic sample of inputs and outputs while requiring only one tuning parameter. The new implementation therefore allows the user to estimate PAWN indices as complementary metrics in multi-method GSA applications without additional computational cost.

KW - Distribution-based methods

KW - Global sensitivity analysis

KW - Moment-independent methods

KW - Multi-method GSA

UR - http://www.scopus.com/inward/record.url?scp=85051119871&partnerID=8YFLogxK

U2 - 10.1016/j.envsoft.2018.07.019

DO - 10.1016/j.envsoft.2018.07.019

M3 - Article

VL - 108

SP - 197

EP - 207

JO - Environmental Modelling and Software

JF - Environmental Modelling and Software

SN - 1364-8152

ER -