Neural networks for extreme quantile regression with an application to forecasting of flood risk

DOI10.1214/24-aoas1907MaRDI QIDQ6665468

Sebastian Engelke, Olivier C. Pasche

Publication date: 17 January 2025

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

zbMATH Keywords

predictionrecurrent neural networkextreme value theorymachine learninggeneralized Pareto distribution

Mathematics Subject Classification ID

Applications of statistics (62Pxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distribution-Free Predictive Inference For Regression
• Extremes on river networks
• Generalized random forests
• Residual life time at great age
• Statistical inference using extreme order statistics
• Limiting forms of the frequency distribution of the largest or smallest member of a sample.
• Kernel estimators of extreme level curves
• Stacked regressions
• A horse race between the block maxima method and the peak-over-threshold approach
• Improving precipitation forecasts using extreme quantile regression
• Extremal quantile regression
• 10.1162/153244303768966139
• Regression Quantiles
• Estimation of High Conditional Quantiles for Heavy-Tailed Distributions
• Graphical Models for Extremes
• Generalized Additive Models for Exceedances of High Thresholds With an Application to Return Level Estimation for U.S. Wind Gusts
• Generalized Additive Modelling of Sample Extremes
• Gradient boosting with extreme-value theory for wildfire prediction
• Regional extreme value index estimation and a test of tail homogeneity
• Gradient boosting for extreme quantile regression
• Extreme Quantile Estimation for Autoregressive Models

This page was built for publication: Neural networks for extreme quantile regression with an application to forecasting of flood risk