Gaussian Process-Based Sensitivity Analysis and Bayesian Model Calibration with GPMSA

Gattiker, James R.; Myers, Kary; Williams, Brian J.; Higdon, Dave; Carzolio, Marcos; Hoegh, Andrew

doi:10.1007/978-3-319-12385-1_58

Cited by 5 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under this parameterization, ρ wik gives the correlation between w i (θ) and w i (θ ) when the input conditions θ and θ are identical, except for a difference of half the prior range of the kth component. More details about the covariance function can be found in (Gattiker et al, 2016). If we restrict to the m input settings used for the ensemble we can define, w i = (w i (θ * 1 ), .…”

Section: Discussionmentioning

confidence: 99%

“…This, along with the prior specification outlined above gives the posterior distribution for the unknown parameters. This distribution is sampled via MCMC in GPMSA, which can also produce draws from the posterior predictive distribution for the emulator and the epidemic curves (Higdon et al, 2008;Gattiker et al, 2016).…”

Section: Discussionmentioning

confidence: 99%

“…for each input setting, and 3) a collection of observations giving the cumulative log counts for the first 20 weeks of the epidemic. Our choice of using GPMSA was motivated by its use in the Ebola Challenge, as well as its inclusion of various nugget parameters to better account for the estimation error of the quantiles (Gattiker et al, 2016). An outline of the model formulation encoded in GPMSA is given in the next subsection.…”

Section: Defining Quantiles and Preprocessingmentioning

confidence: 99%

“…The basic implementation in GPMSA (Gattiker et al, 2016) models the observation vector y as an additive combination of the computational model η(θ, α) at the best setting for the parameters, a systematic model discrepancy term δ, and observation error :…”

Section: Bayesian Model Formulationmentioning

confidence: 99%

“…We also embed this new emulation approach within a Bayesian computer model calibration framework (Kennedy and O'Hagan, 2001;Higdon et al, 2008) to take on a challenging problem in characterizing epidemic behavior, using an ABM that models interaction and contact at the individual level. This statistical modeling is implemented in the software of GPMSA (Gattiker et al, 2016), taking advantage of thoughtful preprocessing of the epidemic observations and the simulation output.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Calibrating a Stochastic, Agent-Based Model Using Quantile-Based Emulation

Fadikar¹,

Higdon²,

Chen³

et al. 2018

SIAM/ASA J. Uncertainty Quantification

Self Cite

View full text Add to dashboard Cite

In a number of cases, the Quantile Gaussian Process (QGP) has proven effective in emulating stochastic, univariate computer model output (Plumlee and Tuo, 2014). In this paper, we develop an approach that uses this emulation approach within a Bayesian model calibration framework to calibrate an agent-based model of an epidemic. In addition, this approach is extended to handle the multivariate nature of the model output, which gives a time series of the count of infected individuals. The basic modeling approach is adapted from Higdon et al. (2008), using a basis representation to capture the multivariate model output. The approach is motivated with an example taken from the 2015 Ebola Challenge workshop which simulated an ebola epidemic to evaluate methodology. of realizations can be averaged, preprocessed, or accounted for in the estimation scheme for the emulator. In other cases the distribution of computer model outcomes (at a given input setting) can be described by its mean and variance. One strategy is to model the output distribution as normal, conditional on the mean and variance and use a Gaussian process (GP) to model the mean and variance as a function of the inputs (Henderson et al., 2009;Marrel et al., 2012). Adapting similar strategies to non-Gaussian distributions has also been carried out -see Reich et al. (2012) for an example of modeling the exposure distribution as a mixture of normals, using a formulation that depends on space, time, and individual-level covariates.An alternative is the quantile kriging approach described in Plumlee and Tuo (2014). Here quantiles of the output distribution are estimated from the collection of realizations produced at each input setting. A GP is then fit to the augmented input space consisting of the original inputs combined with the quantile estimates. Once fit to the model output, this results in a GP whose realizations give continuous, univariate distributions at each input setting.In this paper we extend the quantile-kriging emulator to handle functional, stochastic computer model output. We also embed this new emulation approach within a Bayesian computer model calibration framework (Kennedy and O'Hagan, 2001;Higdon et al., 2008) to take on a challenging problem in characterizing epidemic behavior, using an ABM that models interaction and contact at the individual level. This statistical modeling is implemented in the software of GPMSA (Gattiker et al., 2016), taking advantage of thoughtful preprocessing of the epidemic observations and the simulation output. The Ebola Challenge ProblemThe 2015 ebola challenge problem (ebola-challenge.org) was organized by the Research and Policy for Infectious Disease Dynamics (RAPIDD) program at the National Institutes for Health (NIH). Its goal is to motivate the development, assessment, and comparison of different approaches for modeling, predicting, and managing infectious disease epidemics.The challenge involved multiple scenarios for the nation of Liberia, each simulating an epidemic patterned after the Ebola outbrea...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Defining Quantiles and Preprocessingmentioning

confidence: 99%

Section: Bayesian Model Formulationmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Calibrating a Stochastic, Agent-Based Model Using Quantile-Based Emulation

Fadikar¹,

Higdon²,

Chen³

et al. 2018

SIAM/ASA J. Uncertainty Quantification

Self Cite

View full text Add to dashboard Cite

show abstract

Comparing emulation methods for a high‐resolution storm surge model

et al. 2023

View full text Add to dashboard Cite

Realistic simulations of complex systems are fundamental for climate and environmental studies. Large computer systems are often not sufficient to run sophisticated computational models for large numbers of different input settings. Statistical surrogate models, or emulators, are key tools enabling fast exploration of the simulator input space. Gaussian processes have become standard for computer simulator emulation. However, they require careful implementation to scale appropriately, motivating alternative methods more recently introduced. We present a comparison study of surrogates of the Sea, Lake, and Overland Surges from Hurricanes (SLOSH) simulator-the simulator of choice for government agencies-using four emulation approaches: BASS; BART; SEPIA; and RobustGaSP. SEPIA and RobustGaSP use Gaussian processes, BASS implements adaptive splines, and BART is based on ensembles of regression trees. We describe the four models and compare them in terms of computation time and predictive metrics. These surrogates use proven and distinct methodologies, are available through accessible software, and quantify prediction uncertainty. Our data cover millions of response values. We find that SEPIA and RobustGaSP provide exceptional predictive power, but cannot scale to emulate experiments as large as the one considered in this paper as effectively as BASS and BART.

show abstract

Scalable Epidemiological Workflows to Support COVID-19 Planning and Response

Machi

Bhattacharya

Hoops

et al. 2021

Preprint

View full text Add to dashboard Cite

The COVID-19 global outbreak represents the most significant epidemic event since the 1918 influenza pandemic. Simulations have played a crucial role in supporting COVID-19 planning and response efforts. Developing scalable workflows to provide policymakers quick responses to important questions pertaining to logistics, resource allocation, epidemic forecasts and intervention analysis remains a challenging computational problem. In this work, we present scalable high performance computing-enabled workflows for COVID-19 pandemic planning and response. The scalability of our methodology allows us to run fine-grained simulations daily, and to generate county-level forecasts and other counter-factual analysis for each of the 50 states (and DC), 3140 counties across the USA. Our workflows use a hybrid cloud/cluster system utilizing a combination of local and remote cluster computing facilities, and using over 20,000 CPU cores running for 6--9 hours every day to meet this objective. Our state (Virginia), state hospital network, our university, the DOD and the CDC use our models to guide their COVID-19 planning and response efforts. We began executing these pipelines March 25, 2020, and have delivered and briefed weekly updates to these stakeholders for over 30 weeks without interruption.

show abstract

Gaussian Process-Based Sensitivity Analysis and Bayesian Model Calibration with GPMSA

Cited by 5 publications

References 4 publications

Calibrating a Stochastic, Agent-Based Model Using Quantile-Based Emulation

Calibrating a Stochastic, Agent-Based Model Using Quantile-Based Emulation

Comparing emulation methods for a high‐resolution storm surge model

Scalable Epidemiological Workflows to Support COVID-19 Planning and Response

Contact Info

Product

Resources

About