Post-processing Multi-Model Medium-Term Precipitation Forecasts Using Convolutional Neural Networks
This work addresses post-processing of medium-term precipitation forecasts for meteorology, but it is incremental as it builds on existing methods without achieving better results with CNNs.
The study tackled the problem of improving precipitation forecast post-processing by using convolutional neural networks (CNNs) to combine and transform input forecast images into probabilistic outputs, but found that CNNs did not outperform regularized logistic regression, while combining global low-resolution and regional high-resolution weather model forecasts improved performance.
The goal of this study was to improve the post-processing of precipitation forecasts using convolutional neural networks (CNNs). Instead of post-processing forecasts on a per-pixel basis, as is usually done when employing machine learning in meteorological post-processing, input forecast images were combined and transformed into probabilistic output forecast images using fully convolutional neural networks. CNNs did not outperform regularized logistic regression. Additionally, an ablation analysis was performed. Combining input forecasts from a global low-resolution weather model and a regional high-resolution weather model improved performance over either one.