Title: Comparing emulation methods for a high‐resolution storm surge model

Journal Article · · EnvironMetrics (London)
DOI: https://doi.org/10.1002/env.2796 · OSTI ID:1924561
 [1];  [2];  [3];  [3];  [3]
  1. Department of Statistics University of California Santa Cruz Santa Cruz California USA, Statistical Sciences Group Los Alamos National Laboratory Los Alamos New Mexico USA
  2. Department of Statistics University of California Santa Cruz Santa Cruz California USA
  3. Statistical Sciences Group Los Alamos National Laboratory Los Alamos New Mexico USA

Abstract 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.

Sponsoring Organization:
USDOE
OSTI ID:
1924561
Journal Information:
EnvironMetrics (London), Journal Name: EnvironMetrics (London) Journal Issue: 3 Vol. 34; ISSN 1180-4009
Publisher:
Wiley Blackwell (John Wiley & Sons)Copyright Statement
Country of Publication:
United Kingdom
Language:
English

References (38)

Probabilistic 21st and 22nd century sea-level projections at a global network of tide-gauge sites: KOPP ET AL. journal August 2014
Deep Uncertainty Surrounding Coastal Flood Risk Projections: A Case Study for New Orleans: PROBABILISTIC PROJECTIONS OF FLOOD RISK journal October 2017
Global sensitivity analysis for models with spatially dependent outputs journal November 2010
A comparison of statistical emulation methodologies for multi‐wave calibration of environmental models journal September 2016
Multivariate probabilistic forecasting using ensemble Bayesian model averaging and copulas: Multivariate Probabilistic Forecasting Using Ensemble BMA and Copulas
  • Möller, Annette; Lenkoski, Alex; Thorarinsdottir, Thordis L.
  • Quarterly Journal of the Royal Meteorological Society, Vol. 139, Issue 673 https://doi.org/10.1002/qj.2009
journal September 2012
Functional Data Analysis book January 1997
The Design and Analysis of Computer Experiments book January 2018
The effects of natural structure on estimated tropical cyclone surge extremes journal May 2017
An objective and efficient method for estimating probabilistic coastal inundation hazards journal October 2019
Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates journal February 2001
A comprehensive sensitivity analysis of the WRF model for air quality applications over the Iberian Peninsula journal December 2008
Comparison of Gaussian process modeling software journal April 2018
Probabilistic forecasting in day-ahead electricity markets: Simulating peak and off-peak prices journal October 2020
Bayesian emulation of complex multi-output and dynamic computer models journal March 2010
Quadrature-based approach for the efficient evaluation of surge hazard journal January 2010
Feasibility study of PRA for critical infrastructure risk analysis journal August 2021
An Evaluation of the Ocean and Sea Ice Climate of E3SM Using MPAS and Interannual CORE‐II Forcing journal May 2019
Inferring Atmospheric Release Characteristics in a Large Computer Experiment Using Bayesian Adaptive Splines journal January 2019
Optimal orthogonal-array-based latin hypercubes journal June 2003
Parallel Bayesian Additive Regression Trees journal June 2014
Local Gaussian Process Approximation for Large Computer Experiments journal April 2015
Reversible jump Markov chain Monte Carlo computation and Bayesian model determination journal January 1995
Modeling Heterogeneous Treatment Effects in Survey Experiments with Bayesian Additive Regression Trees journal September 2012
Landmark-Warped Emulators for Models with Misaligned Functional Response journal January 2022
Climate Risk Management journal May 2021
Statistical Models of Holland Pressure Profile Parameter and Radius to Maximum Winds of Hurricanes from Flight-Level Pressure and H*Wind Data journal October 2008
A Statistical Deterministic Approach to Hurricane Risk Assessment journal March 2006
Variable Selection for Gaussian Process Models in Computer Experiments journal November 2006
Strictly Proper Scoring Rules, Prediction, and Estimation journal March 2007
Computer Model Calibration Using High-Dimensional Output journal June 2008
Bayesian Treed Gaussian Process Models With an Application to Computer Modeling journal September 2008
Multivariate Adaptive Regression Splines journal March 1991
Design and Analysis of Computer Experiments journal November 1989
Differential Constraints for the Probability Density Function of Stochastic Solutions to the wave Equation journal January 2012
BASS : An R Package for Fitting and Performing Sensitivity Analysis of Bayesian Adaptive Spline Surfaces journal January 2020
Nonparametric Machine Learning and Efficient Computation with Bayesian Additive Regression Trees: The BART R Package journal January 2021
Orthogonal Array-Based Latin Hypercubes journal December 1993
Application of Bayesian Additive Regression Trees for Estimating Daily Concentrations of PM2.5 Components journal November 2020