Autocalibration of Environmental Process Models Using a PAC Learning Hypothesis - Environmental Software Systems: Frameworks of eEnvironment Access content directly
Conference Papers Year : 2011

Autocalibration of Environmental Process Models Using a PAC Learning Hypothesis

David Swayne
  • Function : Author
  • PersonId : 1013667

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.
Fichier principal
Vignette du fichier
978-3-642-22285-6_57_Chapter.pdf (170.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01569184 , version 1 (26-07-2017)

Licence

Attribution

Identifiers

Cite

Markiyan Sloboda, David Swayne. Autocalibration of Environmental Process Models Using a PAC Learning Hypothesis. 9th International Symposium on Environmental Software Systems (ISESS), Jun 2011, Brno, Czech Republic. pp.528-534, ⟨10.1007/978-3-642-22285-6_57⟩. ⟨hal-01569184⟩
34 View
85 Download

Altmetric

Share

Gmail Facebook X LinkedIn More