Abstract
Abstract. Convection-permitting weather forecasting models allow for prediction of rainfall events with increasing levels of detail. However, the high resolutions used can create problems and introduce the so-called “double penalty” problem when attempting to verify the forecast accuracy. Post-processing within an ensemble prediction system can help to overcome these issues. In this paper, two new up-scaling algorithms based on Machine Learning and Statistical approaches are proposed and tested. The aim of these tools is to enhance the skill and value of the forecasts and to provide a better tool for forecasters to predict severe weather.
Highlights
Since the dawn of Numerical Weather Prediction (NWP), the increasing need for accurate prediction has grown as fast as advances in technology and modern high-performance computing (Bauer et al, 2015)
It can be seen that Irish Regional Ensemble Prediction System (IREPS) succeeded in capturing the main areas of rainfall but that some discrepancies existed in terms of the location of individual convective cells
Two neighbourhood approaches for convective-permitting models based on a statistical postprocessing and a machine learning technique were proposed
Summary
Since the dawn of Numerical Weather Prediction (NWP), the increasing need for accurate prediction has grown as fast as advances in technology and modern high-performance computing (Bauer et al, 2015). Tree-based ensemble methods have recently been successfully applied to improve the skill of low visibility conditions in an operational meso-scale model (Bari and Ouagabi, 2020), while Krasnopolsky and Lin (2012) demonstrated how machine learning algorithms can decrease the bias for low and high rainfall. Up-scaling methods will be applied to a number of rainfall cases, using forecasts from the operational ensemble system in use at Met Éireann, the Irish national meteorological service. This system, along with the cases and observational data, will be introduced, with the upscaling techniques described in Sect.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have