March 2022 Fast inference for time-varying quantiles via flexible dynamic models with application to the characterization of atmospheric rivers
Raquel Barata, Raquel Prado, Bruno Sansó
Author Affiliations +
Ann. Appl. Stat. 16(1): 247-271 (March 2022). DOI: 10.1214/21-AOAS1497

Abstract

Atmospheric rivers (ARs) are elongated regions of water vapor in the atmosphere that play a key role in global water cycles, particularly in western U.S. precipitation. The primary component of many AR detection schemes is the thresholding of the integrated water vapor transport (IVT) magnitude at a single quantile over time. Utilizing a recently developed family of parametric distributions for quantile regression, this paper develops a flexible dynamic quantile linear model (exDQLM) which enables versatile, structured, and informative estimation of the IVT quantile threshold. A simulation study illustrates our exDQLM to be more robust than the standard Bayesian parametric quantile regression approach for nonstandard distributions, performing better in both quantile estimation and predictive accuracy. In addition to a Markov chain Monte Carlo (MCMC) algorithm, we develop an efficient importance sampling variational Bayes (ISVB) algorithm for fast approximate Bayesian inference which is found to produce comparable results to the MCMC in a fraction of the computation time. Further, we develop a transfer function extension to our exDQLM as a method for quantifying nonlinear relationships between a quantile of a climatological response and an input. The utility of our transfer function exDQLM is demonstrated in capturing both the immediate and lagged effects of El Niño Southern Oscillation Longitude Index on the estimation of the 0.85 quantile IVT.

Funding Statement

The third author acknowledges the National Science Foundation award DMS-1513076 for partially funding this research.

Acknowledgments

The authors wish to thank Bin Guan and Duane Waliser at NASA Jet Propulsion Laboratory for sharing their IVT and AR datasets. The AR database is available at https://ucla.app.box.com/v/ARcatalog, and the ERA5 dataset is avaliable at https://cds.climate.copernicus.eu. We also thank Christina Patricola at Lawrence Berkeley National Laboratory for helpful conversation about the ELI. The ELI is available at https://portal.nersc.gov/archive/home/projects/cascade/www/ELI.

Citation

Download Citation

Raquel Barata. Raquel Prado. Bruno Sansó. "Fast inference for time-varying quantiles via flexible dynamic models with application to the characterization of atmospheric rivers." Ann. Appl. Stat. 16 (1) 247 - 271, March 2022. https://doi.org/10.1214/21-AOAS1497

Information

Received: 1 November 2020; Revised: 1 June 2021; Published: March 2022
First available in Project Euclid: 28 March 2022

MathSciNet: MR4400509
zbMATH: 1498.62280
Digital Object Identifier: 10.1214/21-AOAS1497

Keywords: asymmetric Laplace , atmospheric river , Dynamic quantile regression , variational Bayes

Rights: Copyright © 2022 Institute of Mathematical Statistics

Vol.16 • No. 1 • March 2022
Back to Top