Bayesian uncertainty quantification for ...
Type de document :
Compte-rendu et recension critique d'ouvrage: Autre communication scientifique (congrès sans actes - poster - séminaire...)
Titre :
Bayesian uncertainty quantification for anaerobic digestion models
Auteur(s) :
Picard-Weibel, Antoine [Auteur]
Centre International de Recherche Sur l'Eau et l'Environnement [Suez] [CIRSEE]
Capson-Tojo, Gabriel [Auteur]
Laboratoire de Biotechnologie de l'Environnement [Narbonne] [LBE]
Guedj, Benjamin [Auteur]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
Inria Lille - Nord Europe
The Inria London Programme [Inria-London]
MOdel for Data Analysis and Learning [MODAL]
Moscoviz, Roman [Auteur]
Centre International de Recherche Sur l'Eau et l'Environnement [Suez] [CIRSEE]
Centre International de Recherche Sur l'Eau et l'Environnement [Suez] [CIRSEE]
Capson-Tojo, Gabriel [Auteur]
Laboratoire de Biotechnologie de l'Environnement [Narbonne] [LBE]
Guedj, Benjamin [Auteur]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
Inria Lille - Nord Europe
The Inria London Programme [Inria-London]
MOdel for Data Analysis and Learning [MODAL]
Moscoviz, Roman [Auteur]
Centre International de Recherche Sur l'Eau et l'Environnement [Suez] [CIRSEE]
Titre de la revue :
Bioresource technology
Pagination :
130147
Éditeur :
Elsevier
Date de publication :
2024-02
ISSN :
0960-8524
Mot(s)-clé(s) en anglais :
Biochemical reaction networks Computational model Predictive power Confidence regions Bayesian Uncertainty Quantification for Anaerobic Digestion models
Biochemical reaction networks
Computational model
Predictive power
Confidence regions Bayesian Uncertainty Quantification for Anaerobic Digestion models
Biochemical reaction networks Computational model Predictive power Confidence regions
Confidence regions
Biochemical reaction networks
Computational model
Predictive power
Confidence regions Bayesian Uncertainty Quantification for Anaerobic Digestion models
Biochemical reaction networks Computational model Predictive power Confidence regions
Confidence regions
Discipline(s) HAL :
Sciences de l'ingénieur [physics]
Résumé en anglais : [en]
Uncertainty quantification is critical for ensuring adequate predictive power of computational models used in biology. Focusing on two anaerobic digestion models, this article introduces a novel generalized Bayesian ...
Lire la suite >Uncertainty quantification is critical for ensuring adequate predictive power of computational models used in biology. Focusing on two anaerobic digestion models, this article introduces a novel generalized Bayesian procedure, called VarBUQ, ensuring a correct tradeoff between flexibility and computational cost. A benchmark against three existing methods (Fisher’s information, bootstrapping and Beale’s criteria) was conducted using synthetic data. This Bayesian procedure offered a good compromise between fitting ability and confidence estimation, while the other methods proved to be repeatedly overconfident. The method’s performances notably benefitted from inductive bias brought by the prior distribution, although it requires careful construction. This article advocates for more systematic consideration of uncertainty for anaerobic digestion models and showcases a new, computationally efficient Bayesian method. To facilitate future implementations, a Python package called ‘aduq’ is made available.Lire moins >
Lire la suite >Uncertainty quantification is critical for ensuring adequate predictive power of computational models used in biology. Focusing on two anaerobic digestion models, this article introduces a novel generalized Bayesian procedure, called VarBUQ, ensuring a correct tradeoff between flexibility and computational cost. A benchmark against three existing methods (Fisher’s information, bootstrapping and Beale’s criteria) was conducted using synthetic data. This Bayesian procedure offered a good compromise between fitting ability and confidence estimation, while the other methods proved to be repeatedly overconfident. The method’s performances notably benefitted from inductive bias brought by the prior distribution, although it requires careful construction. This article advocates for more systematic consideration of uncertainty for anaerobic digestion models and showcases a new, computationally efficient Bayesian method. To facilitate future implementations, a Python package called ‘aduq’ is made available.Lire moins >
Langue :
Anglais
Vulgarisation :
Non
Collections :
Source :
Fichiers
- document
- Accès libre
- Accéder au document
- main_rev.pdf
- Accès libre
- Accéder au document