资源环境科技发展态势分析平台

A new three-dimensional convolutional neural network model (3DCNN) has been developed to nowcast a short-lived, local convective storm event by using unique 3-D observations of Multi Parameter Phased Array Weather Radar over Tokyo, Japan on 1 August 2019. Using statistics and forecast skill scores, nowcast skills of 3DCNN were examined with those from a three-dimensional advection nowcast model (3DNOW) which generates extrapolation-based forecasts with lead times up to 10 min. In analyzing the skill scores, two groups of a total rain area and convective rain area were made by different radar reflectivity thresholds of 10 dBZ and 37.5 dBZ, respectively. For the total rain area, it is found that 3DCNN outperformed both the 3DNOW and persistence forecast, showing the higher threat scores for all lead times. For the convective rain area, the 3DCNN and 3DNOW's performances were similar at early lead times, showing almost the same threat scores. Later, the threat score of 3DCNN dropped lower than that of 3DNOW at a lead time of 10 min, indicating that 3DNOW has the better skill at relatively longer lead times. Nowcasts of 3DNOW showed a limitation to yield a broad saturated Z area related to increased errors in advection vectors at the longer lead times although this had an effect to increase the threat score.