Forest-based methods and ensemble model output statistics for rainfall ensemble forecasting
This work addresses the problem of accurate rainfall forecasting for meteorological applications, particularly for extreme events, representing an incremental improvement over existing ensemble post-processing methods.
The authors tackled the challenge of improving rainfall ensemble forecasts for both low precipitation and extreme events by developing hybrid statistical post-processing methods based on Quantile Regression Forests and Gradient Forests with a parametric extension for heavy-tailed distributions. Their methods, applied to daily forecasts over France from 2012 to 2015, provided calibrated predictive distributions and competed favorably with state-of-the-art techniques, showing added value for heavy rainfall forecasting.
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{é}t{é}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.