Abstract
A binary classification model is trained by random forest using data from 41 stations in Norway to predict the precipitation in a given hour. The predictors consist of results from radar nowcasts and numerical weather predictions. The results demonstrate that the random forest model can improve the precipitation predictions by the radar nowcasts and the numerical weather predictions. This study clarifies whether certain potential factors related to model training can influence the predictive skill of the random forest method. The results indicate that enforcing a balanced prediction by resampling the training datasets or lowering the threshold probability for classification cannot improve the predictive skill of the random forest model. The study reveals that the predictive skill of the random forest model shows seasonality, but is only weakly influenced by the geographic diversity of the training dataset. Finally, the study shows that the most important predictor is the precipitation predictions by the radar nowcasts followed by the precipitation predictions by the numerical weather predictions. Although meteorological variables other than precipitation are weaker predictors, the results suggest that they can help to reduce the false alarm ratio and to increase the success ratio of the precipitation prediction.
Significance Statement
Machine learning can be useful in improving weather forecasts with relatively inexpensive computational efforts. Specifically, this study has demonstrated that radar nowcasts can be improved by integrating the information from radar and numerical weather prediction using the random forest method. The random forest method’s performance shows seasonality but is only weakly influenced by the geographic diversity of the training dataset. Also, there is no need to use specific strategies to address the imbalance of the precipitation and no precipitation frequency from the observations during model training. However, future study is needed to identify better predictor choices to further improve the random forest method.
Current affiliation: Geophysical Institute, University of Bergen, Bergen, Norway.
© 2020 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).
