An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models
In recent years, interest in the Bayesian approach for the calibration of hydrological and environmental simulation (HES) models has been growing. To extract useful information on unknown parameters produced in a Bayesian calibration, it is often necessary to rely on samples drawn from the posterior...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Language: | Inglés |
| Published: |
American Geophysical Union
2009
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10568/162205 |
| _version_ | 1855521731933896704 |
|---|---|
| author | Xie, Hua Eheart, J. Wayland Chen, Yuguo Bailey, Barbara A. |
| author_browse | Bailey, Barbara A. Chen, Yuguo Eheart, J. Wayland Xie, Hua |
| author_facet | Xie, Hua Eheart, J. Wayland Chen, Yuguo Bailey, Barbara A. |
| author_sort | Xie, Hua |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | In recent years, interest in the Bayesian approach for the calibration of hydrological and environmental simulation (HES) models has been growing. To extract useful information on unknown parameters produced in a Bayesian calibration, it is often necessary to rely on samples drawn from the posterior distribution. Sampling a posterior distribution requires a large number of evaluations of the simulation model, and the total computational costs could be prohibitively high when the simulation model is computationally expensive. A new computing strategy is proposed in this paper to alleviate this computational difficulty by making better use of the information generated in a costly run of the HES model by using multiple evaluations of the posterior density in the less computationally expensive subspace of error model parameters. A multiple‐try Markov chain Monte Carlo (MCMC) algorithm is designed to implement this idea and is benchmarked with the Metropolis‐Hastings algorithm, a basic recipe for MCMC sampling. The results show that the proposed strategy has potential for improving the computational efficiency of posterior sampling and easing its implementation in the Bayesian calibration of computationally expensive HES models. |
| format | Journal Article |
| id | CGSpace162205 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2009 |
| publishDateRange | 2009 |
| publishDateSort | 2009 |
| publisher | American Geophysical Union |
| publisherStr | American Geophysical Union |
| record_format | dspace |
| spelling | CGSpace1622052024-11-21T10:01:43Z An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models Xie, Hua Eheart, J. Wayland Chen, Yuguo Bailey, Barbara A. Bayesian theory calibration models In recent years, interest in the Bayesian approach for the calibration of hydrological and environmental simulation (HES) models has been growing. To extract useful information on unknown parameters produced in a Bayesian calibration, it is often necessary to rely on samples drawn from the posterior distribution. Sampling a posterior distribution requires a large number of evaluations of the simulation model, and the total computational costs could be prohibitively high when the simulation model is computationally expensive. A new computing strategy is proposed in this paper to alleviate this computational difficulty by making better use of the information generated in a costly run of the HES model by using multiple evaluations of the posterior density in the less computationally expensive subspace of error model parameters. A multiple‐try Markov chain Monte Carlo (MCMC) algorithm is designed to implement this idea and is benchmarked with the Metropolis‐Hastings algorithm, a basic recipe for MCMC sampling. The results show that the proposed strategy has potential for improving the computational efficiency of posterior sampling and easing its implementation in the Bayesian calibration of computationally expensive HES models. 2009-06 2024-11-21T10:01:42Z 2024-11-21T10:01:42Z Journal Article https://hdl.handle.net/10568/162205 en Limited Access American Geophysical Union Xie, Hua; Eheart, J. Wayland; Chen, Yuguo; Bailey, Barbara A. 2009. An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models. Water Resources Research Water Resources Research 45: W06419 |
| spellingShingle | Bayesian theory calibration models Xie, Hua Eheart, J. Wayland Chen, Yuguo Bailey, Barbara A. An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models |
| title | An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models |
| title_full | An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models |
| title_fullStr | An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models |
| title_full_unstemmed | An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models |
| title_short | An approach for improving the sampling efficiency in the Bayesian calibration of computationally expensive simulation models |
| title_sort | approach for improving the sampling efficiency in the bayesian calibration of computationally expensive simulation models |
| topic | Bayesian theory calibration models |
| url | https://hdl.handle.net/10568/162205 |
| work_keys_str_mv | AT xiehua anapproachforimprovingthesamplingefficiencyinthebayesiancalibrationofcomputationallyexpensivesimulationmodels AT eheartjwayland anapproachforimprovingthesamplingefficiencyinthebayesiancalibrationofcomputationallyexpensivesimulationmodels AT chenyuguo anapproachforimprovingthesamplingefficiencyinthebayesiancalibrationofcomputationallyexpensivesimulationmodels AT baileybarbaraa anapproachforimprovingthesamplingefficiencyinthebayesiancalibrationofcomputationallyexpensivesimulationmodels AT xiehua approachforimprovingthesamplingefficiencyinthebayesiancalibrationofcomputationallyexpensivesimulationmodels AT eheartjwayland approachforimprovingthesamplingefficiencyinthebayesiancalibrationofcomputationallyexpensivesimulationmodels AT chenyuguo approachforimprovingthesamplingefficiencyinthebayesiancalibrationofcomputationallyexpensivesimulationmodels AT baileybarbaraa approachforimprovingthesamplingefficiencyinthebayesiancalibrationofcomputationallyexpensivesimulationmodels |