EUVIMEDEUVIMED entdecken
Crossref

A Python Package for Distance-Based Generalized Sensitivity Analysis (DGSA)

Jihui Ding, Céline Scheidt, Peng Li, David Zhen Yin, Jef Caers

Journal of Open Research Software · 06.07.2026 · 14

DOI: 10.5334/jors.697 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Open Research Software, erschienen am 06.07.2026. Verfasst von Jihui Ding und 4 weiteren Autor:innen. Die Arbeit nennt 6 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Distance-based Generalized Sensitivity Analysis (DGSA) is a global sensitivity analysis method that quantifies single parameter sensitivities as well as two-way parameter interactions. One of the main advantages is that it can provide sensitivity analyses where the amount of model evaluation needed is limited, compared to other methods. A Python package is implemented to compute both single parameter and conditional parameter sensitivities using two types of sensitivity measures. Sensitivity results can be visualized using Pareto plots and heatmaps with a perceptually uniform colormap. The source code is stored in a GitHub repository and includes an example dataset to illustrate its usage. This tool helps provide more complete and deeper insights into parameter sensitivity analysis.

Zitieren

APA

Ding, J., Scheidt, C., Li, P., Yin, D. Z., & Caers, J. (2026). A Python Package for Distance-Based Generalized Sensitivity Analysis (DGSA). Journal of Open Research Software, 14. https://doi.org/10.5334/jors.697

Vancouver

Ding J, Scheidt C, Li P, Yin DZ, Caers J. A Python Package for Distance-Based Generalized Sensitivity Analysis (DGSA). Journal of Open Research Software. 2026;14. doi:10.5334/jors.697

BibTeX
@article{Ding2026,
  author = {Ding, Jihui and Scheidt, Céline and Li, Peng and Yin, David Zhen and Caers, Jef},
  title = {A Python Package for Distance-Based Generalized Sensitivity Analysis (DGSA)},
  journal = {Journal of Open Research Software},
  year = {2026},
  volume = {14},
  doi = {10.5334/jors.697}
}
Kostenlos starten →