Machine Learning-Based Front Detection in Central Europe

On Solar Radiation Prediction for the East–Central European Region

The aim of this paper is to present the results of the Weather Research and Forecasting (WRF) model of solar radiation for moderate climatic zones. This analysis covered the area of northeastern Germany. Due to very unfavorable solar energy conditions in this region for at least 1/3 of the year, we decided to select the dates with the most representative conditions: passing warm fronts, cold fronts, and occluded fronts (two cases each). As the reference, two cloudless conditions during high-pressure situations were chosen. Two different shortwave radiation schemes—Rapid Radiative Transfer Model for general circulation model (RRTMG) and Dudhia—were tested. The obtained results were compared with in situ data measured at Deutscher Wetterdienst (DWD) stations and then with European Medium-Range Weather Forecast reanalysis (ERA5) data. The results showed that for high-pressure situations, the mean correlations with measured data were above 90%. The Dudhia scheme, in addition to the expected good results for the high-pressure situation, showed better results than RRTMG for the warm and cold fronts as well. The forecast using the RRTMG scheme gave the best results for the occluded front, which were also better than those of the ERA5 model.

Machine Learning in Weather Prediction and Climate Analyses—Applications and Perspectives

In this paper, we performed an analysis of the 500 most relevant scientific articles published since 2018, concerning machine learning methods in the field of climate and numerical weather prediction using the Google Scholar search engine. The most common topics of interest in the abstracts were identified, and some of them examined in detail: in numerical weather prediction research—photovoltaic and wind energy, atmospheric physics and processes; in climate research—parametrizations, extreme events, and climate change. With the created database, it was also possible to extract the most commonly examined meteorological fields (wind, precipitation, temperature, pressure, and radiation), methods (Deep Learning, Random Forest, Artificial Neural Networks, Support Vector Machine, and XGBoost), and countries (China, USA, Australia, India, and Germany) in these topics. Performing critical reviews of the literature, authors are trying to predict the future research direction of these fields, with the main conclusion being that machine learning methods will be a key feature in future weather forecasting.