OpenTURNS: A Python package for uncertainty quantification
Abstract
OpenTURNS (www.openturns.org) is an open-source Python package for probabilistic modeling, uncertainty quantification (UQ), and machine learning. It provides a unified interface, granting users access to a comprehensive set of state-of-the-art algorithms and modeling tools. The library is supported by extensive, regularly updated, easy to read documentation, including introductory examples, various use cases, tutorials, and user guides, enhancing its accessibility. OpenTURNS integrates seamlessly with NumPy, Pandas, and other scientific Python packages, allowing users to develop UQ workflows and generate reproducible results. Its modular architecture enables both newcomers and advanced users to access reliable, well-tested methods for uncertainty propagation, sensitivity analysis, and reliability assessment. Its active community provides additional support and resources through a Discourse forum (OpenTURNS’s Forum, 2020) and a website. Stable releases are published on a semiannual basis, and the library is distributed through Conda, pip, and Debian repositories and available on Linux, Windows, and macOS.
Related
- QuantileMix: A Python package for quantile g-computation
- RC Prediction: A Python Package for Parameter-Aware Reservoir Computing
- Adaptive Uncertainty Quantification on Simplicial Complexes with Conformalized Simplicial Neural Networks
- Subjective Risk Decomposition: A New View for Uncertainty Quantification
- Bagged Martingale Posteriors: Calibrated Uncertainty Quantification for Predictive Resampling
BibTeX
@article{baudin2026openturns,
title = {{OpenTURNS: A Python package for uncertainty quantification}},
author = {Michaël Baudin and Anne Dutfoy and Régis Lebrun and Julien Schueller and Sofiane Haddad and Loïc Brevault and Mathieu Balesdent and Julien Pelamatti and Joseph Muré},
journal = {Journal of Open Source Software},
year = {2026},
month = sep,
doi = {10.21105/joss.10484},
url = {https://hal.science/hal-05763165v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - OpenTURNS: A Python package for uncertainty quantification
AU - Michaël Baudin
AU - Anne Dutfoy
AU - Régis Lebrun
AU - Julien Schueller
AU - Sofiane Haddad
AU - Loïc Brevault
AU - Mathieu Balesdent
AU - Julien Pelamatti
AU - Joseph Muré
PY - 2026
DA - 2026/09/02
JO - Journal of Open Source Software
DO - 10.21105/joss.10484
UR - https://hal.science/hal-05763165v1
AB - OpenTURNS (www.openturns.org) is an open-source Python package for probabilistic modeling, uncertainty quantification (UQ), and machine learning. It provides a unified interface, granting users access to a comprehensive set of state-of-the-art algorithms and modeling tools. The library is supported by extensive, regularly updated, easy to read documentation, including introductory examples, various use cases, tutorials, and user guides, enhancing its accessibility. OpenTURNS integrates seamlessly with NumPy, Pandas, and other scientific Python packages, allowing users to develop UQ workflows and generate reproducible results. Its modular architecture enables both newcomers and advanced users to access reliable, well-tested methods for uncertainty propagation, sensitivity analysis, and reliability assessment. Its active community provides additional support and resources through a Discourse forum (OpenTURNS’s Forum, 2020) and a website. Stable releases are published on a semiannual basis, and the library is distributed through Conda, pip, and Debian repositories and available on Linux, Windows, and macOS.
SN - 1942-3926
ER -