Bayesian Analysis of Extreme Precipitation Events and Forecasting Return Levels

TL;DR

This paper applies a Bayesian approach to analyze extreme rainfall data, providing probabilistic assessments and improved forecasting of future extreme precipitation events, with implications for infrastructure planning.

Contribution

It introduces a Bayesian methodology for estimating extreme precipitation return levels, offering credible intervals and more accurate risk assessments compared to traditional methods.

Findings

Current return levels may underestimate actual precipitation risk.

Bayesian analysis yields credible intervals for extreme event estimates.

Application to Long Island data demonstrates improved risk assessment.

Abstract

In this study, we examine a Bayesian approach to analyze extreme daily rainfall amounts and forecast return-levels. Estimating the probability of occurrence and quantiles of future extreme events is important in many applications, including civil engineering and the design of public infrastructure. In contrast to traditional analysis, which use point estimates to accomplish this goal, the Bayesian method utilizes the complete posterior density derived from the observations. The Bayesian approach offers the benefit of well defined credible (confidence) intervals, improved forecasting, and the ability to defend rigorous probabilistic assessments. We illustrate the Bayesian approach using extreme precipitation data from Long Island, NY, USA and show that current return levels, or precipitation risk, may be understated.