Autocalibration of Environmental Process Models Using a PAC Learning Hypothesis

Abstract : Using the probably approximately correct (PAC) learning hypothesis, we have conducted experiments using clustered computers, high-performance workstations and ad-hoc grids of personal computers, to develop an analytical model for, and demonstrate asymptotic convergence of simple parallel search in the parameter space of complex environmental models such as the Soil and Water Assessment Tool (SWAT). SWAT calibration for hydrological flow, N and P is, for our test cases, superior to current genetic algorithms, as well as to SWAT-CUP, a multi-paradigm calibration solver and to its components. With more complex models, there is no current alternative to our approach in a realizable wall-clock time.
Type de document :
Communication dans un congrès
Jiří Hřebíček; Gerald Schimak; Ralf Denzer. 9th International Symposium on Environmental Software Systems (ISESS), Jun 2011, Brno, Czech Republic. Springer, IFIP Advances in Information and Communication Technology, AICT-359, pp.528-534, 2011, Environmental Software Systems. Frameworks of eEnvironment. 〈10.1007/978-3-642-22285-6_57〉
Liste complète des métadonnées

Littérature citée [5 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01569184
Contributeur : Hal Ifip <>
Soumis le : mercredi 26 juillet 2017 - 14:05:40
Dernière modification le : mercredi 26 juillet 2017 - 14:11:28

Fichier

978-3-642-22285-6_57_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Markiyan Sloboda, David Swayne. Autocalibration of Environmental Process Models Using a PAC Learning Hypothesis. Jiří Hřebíček; Gerald Schimak; Ralf Denzer. 9th International Symposium on Environmental Software Systems (ISESS), Jun 2011, Brno, Czech Republic. Springer, IFIP Advances in Information and Communication Technology, AICT-359, pp.528-534, 2011, Environmental Software Systems. Frameworks of eEnvironment. 〈10.1007/978-3-642-22285-6_57〉. 〈hal-01569184〉

Partager

Métriques

Consultations de la notice

26

Téléchargements de fichiers

15