Stefano Tarantola
Institute for the Protection and Security of the Citizen
StatisticsEconometricsUncertainty analysisMathematicsComputer science
What is this?
Publications 106
#1Thierry A. MaraH-Index: 14
#2Stefano TarantolaH-Index: 45
#1Samuele Lo PianoH-Index: 1
#2Federico FerrettiH-Index: 2
Last. Andrea SaltelliH-Index: 52
view all 6 authors...
ABSTRACTSensitivity analysis is an essential tool in the development of robust models for engineering, physical sciences, economics and policy-making, but typically requires running the model a large number of times in order to estimate sensitivity measures. While statistical emulators allow sensitivity analysis even on complex models, they only perform well with a moderately low number of model inputs: in higher dimensional problems they tend to require a restrictively high number of model runs...
1 CitationsSource
#1E. PisoniH-Index: 1
#2D. AlbrechtH-Index: 1
Last. P. ThunisH-Index: 1
view all 6 authors...
Abstract Air quality has significantly improved in Europe over the past few decades. Nonetheless we still find high concentrations in measurements mainly in specific regions or cities. This dimensional shift, from EU-wide to hot-spot exceedances, calls for a novel approach to regional air quality management (to complement EU-wide existing policies). The SHERPA (Screening for High Emission Reduction Potentials on Air quality) modelling tool was developed in this context. It provides an additional...
10 CitationsSource
Several methods are proposed in the literature to perform the global sensitivity analysis of computer models with independent inputs. Only a few allow for treating the case of dependent inputs. In the present work, we investigate how to compute variance-based sensitivity indices with the Fourier amplitude sensitivity test. This can be achieved with the help of the inverse Rosenblatt transformation or the inverse Nataf transformation. We illustrate so on two distinct benchmarks. As compared to th...
4 CitationsSource
#1Tommaso Locatelli (INRA: Institut national de la recherche agronomique)H-Index: 3
#2Stefano TarantolaH-Index: 45
Last. Genevieve Patenaude (Edin.: University of Edinburgh)H-Index: 5
view all 4 authors...
We submitted the semi-empirical, process-based wind-risk model ForestGALES to a variance-based sensitivity analysis using the method of Sobo for correlated variables proposed by Kucherenko etal. (2012). Our results show that ForestGALES is able to simulate very effectively the dynamics of wind damage to forest stands, as the model architecture reflects the significant influence of tree height, stocking density, dbh, and size of an upwind gap, on the calculations of the critical wind speeds of da...
9 CitationsSource
#1Federico FerrettiH-Index: 2
#2Andrea Saltelli (University of Bergen)H-Index: 52
Last. Stefano TarantolaH-Index: 45
view all 3 authors...
Abstract The majority of published sensitivity analyses (SAs) are either local or one factor-at-a-time (OAT) analyses, relying on unjustified assumptions of model linearity and additivity. Global approaches to sensitivity analyses (GSA) which would obviate these shortcomings, are applied by a minority of researchers. By reviewing the academic literature on SA, we here present a bibliometric analysis of the trends of different SA practices in last decade. The review has been conducted both on som...
52 CitationsSource
This paper addresses the issue of performing global sensitivity analysis of model output with dependent inputs. First, we define variance-based sensitivity indices that allow for distinguishing the independent contributions of the inputs to the response variance from their mutual dependent contributions. Then, two sampling strategies are proposed for their non-parametric, numerical estimation. This approach allows us to estimate the sensitivity indices not only for individual inputs but also for...
30 CitationsSource
#1Sergei Kucherenko (Imperial College London)H-Index: 20
#2B. Delpuech (Imperial College London)H-Index: 1
Last. Stefano TarantolaH-Index: 45
view all 4 authors...
Abstract Global sensitivity analysis is widely used in many areas of science, biology, sociology and policy planning. The variance-based methods also known as Sobol׳ sensitivity indices has become the method of choice among practitioners due to its efficiency and ease of interpretation. For complex practical problems, estimation of Sobol׳ sensitivity indices generally requires a large number of function evaluations to achieve reasonable convergence. To improve the efficiency of the Monte Carlo e...
16 CitationsSource
#1Emanuele Borgonovo (Bocconi University)H-Index: 26
#2Stefano TarantolaH-Index: 45
Last. Max D. Morris (Iowa State University)H-Index: 20
view all 4 authors...
type="main" xml:id="rssb12052-abs-0001"> Monotonic transformations are widely employed in statistics and data analysis. In computer experiments they are often used to gain accuracy in the estimation of global sensitivity statistics. However, one faces the question of interpreting results that are obtained on the transformed data back on the original data. The situation is even more complex in computer experiments, because transformations alter the model input–output mapping and distort the estim...
45 CitationsSource