Work

Statistical Postprocessing of Wind Speed Forecasts Using Convolutional Neural Networks

Year: 2021

Type: article

Abstract: Current statistical postprocessing methods for probabilistic weather forecasting are not capable of using full spatial patterns from the numerical weather prediction (NWP) model. In this paper, we incorporate spatial wind speed information by using convolutional neural networks (CNNs) and obtain probabilistic wind speed forecasts in the Netherlands for 48 h ahead, based on KNMI’s deterministic HARMONIE-AROME NWP model. The probabilistic forecasts from the CNNs are shown to have higher Brier skill scores for medium to higher wind speeds, as well as a better continuous ranked probability score (CRPS) and logarithmic score, than the forecasts from fully connected neural networks and quantile regression forests. As a secondary result, we have compared the CNNs using three different density estimation methods [quantized softmax (QS), kernel mixture networks, and fitting a truncated normal distribution], and found the probabilistic forecasts based on the QS method to be best.

Source: Monthly Weather Review

DOI: 10.1175/mwr-d-20-0219.1

Authors: Simon Veldkamp, Kirien Whan, Sjoerd Dirksen, Maurice Schmeits

Institutions: Royal Netherlands Meteorological Institute, Utrecht University

Language: English

Topic: Meteorological Phenomena and Simulations

Subfield: Atmospheric Science

Field: Earth and Planetary Sciences

Domain: Physical Sciences

SDG: Climate action

Open Access status: green

Funder: Deutsche Forschungsgemeinschaft