Abstract
The goal of the present work is twofold. First, we use the modified random walk Markov Chain Monte Carlo (MCMC) method introduced by [1] to sample from the posterior distribution that arises from Bayesian data assimilation in a groundwater model. Second, we use these samples to evaluate the performance of standard ad hoc Gaussian approximations of the posterior. We use a synthetic experiment to show that our MCMC implementation converges faster than the standard random walk MCMC. In addition, we design a controlled experiment to evaluate the performance of standard Gaussian approximations of the posterior. More precisely, we use our MCMC characterization of the posterior to compare the uncertainty quantification properties of the ensemble Kalman filter (EnKF), randomized maximum likelihood (RML) and maximum a posterior (MAP) methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.