Improving precipitation forecasts using extreme quantile regression

TL;DR

This paper introduces a nonparametric regression approach using extreme value theory to improve the accuracy of extreme precipitation forecasts, demonstrating superior performance over existing methods on simulated and real data.

Contribution

It develops a novel estimator for extreme quantiles based on local linear quantile regression and extrapolation, with proven consistency and asymptotic normality.

Findings

Estimator outperforms linear quantile methods in simulations

Provides more accurate extreme precipitation predictions in Dutch data

Shows improved predictive skill over ensemble forecasts

Abstract

Aiming to estimate extreme precipitation forecast quantiles, we propose a nonparametric regression model that features a constant extreme value index. Using local linear quantile regression and an extrapolation technique from extreme value theory, we develop an estimator for conditional quantiles corresponding to extreme high probability levels. We establish uniform consistency and asymptotic normality of the estimators. In a simulation study, we examine the performance of our estimator on finite samples in comparison with a method assuming linear quantiles. On a precipitation data set in the Netherlands, these estimators have greater predictive skill compared to the upper member of ensemble forecasts provided by a numerical weather prediction model.