Changhoon Song, Teng Yuan Chang, Youngjoon Hong
The paper introduces exPreCast, a deterministic model for accurate and efficient nowcasting of both normal and extreme rainfall using a balanced dataset from the Korea Meteorological Administration.
Predicting extreme weather events like heavy rain or storms is crucial for safety and disaster management. However, it's challenging due to the complex and localized nature of rainfall patterns. This study presents a new forecasting model called exPreCast, which efficiently predicts detailed radar images of precipitation. The model is tested on a newly created, balanced dataset that includes both regular and extreme weather events, and it shows excellent performance in forecasting rainfall accurately.
