Forest-based methods and ensemble model output statistics for rainfall ensemble forecasting

TL;DR

This paper introduces hybrid forest-based statistical post-processing methods to improve the calibration and skill of rainfall ensemble forecasts, especially for heavy rainfall events, using data from France's PEARP system.

Contribution

It develops and applies novel hybrid Quantile Regression Forest and Gradient Forest methods with heavy-tailed extensions for rainfall forecast calibration.

Findings

Hybrid forest methods outperform traditional techniques.

Enhanced heavy rainfall prediction accuracy.

Good overall calibration and skill in ensemble forecasts.

Abstract

Rainfall ensemble forecasts have to be skillful for both low precipitation and extreme events. We present statistical post-processing methods based on Quantile Regression Forests (QRF) and Gradient Forests (GF) with a parametric extension for heavy-tailed distributions. Our goal is to improve ensemble quality for all types of precipitation events, heavy-tailed included, subject to a good overall performance. Our hybrid proposed methods are applied to daily 51-h forecasts of 6-h accumulated precipitation from 2012 to 2015 over France using the M{\'e}t{\'e}o-France ensemble prediction system called PEARP. They provide calibrated pre-dictive distributions and compete favourably with state-of-the-art methods like Analogs method or Ensemble Model Output Statistics. In particular, hybrid forest-based procedures appear to bring an added value to the forecast of heavy rainfall.