Daily forecasts of the Gálvez-Davison Index (GDI) are computed from 0000-UTC Climate Forecast System, version 2 (CFSv2), initializations during the month preceding the ERS (i.e., March 1-31) from 2012-2022. The GDI is an operational convective precipitation forecasting tool that has proven effective at identifying dry, SAL-influenced environments in Puerto Rico. These 41,602 daily GDI fields (11 years x 31 initialization per year x 122 GDI fields per initialization) were used to train a Self-Organizing Map (SOM) that revealed common patterns of GDI variability in the Eastern Caribbean. Preliminary findings show that the apparent SAL nodes in the SOM were more frequent during drought years and less frequent during pluvial years. Specifically, the most dominant SAL-like pattern in the SOM was 30% more frequent during the 2015 drought year. Further, the percent frequency of the highest GDI node and the composite GDI value over PR in the lowest GDI node were both strongly significantly correlated with ERS island-wide precipitation in Puerto Rico, with R2 values of 0.56 and 0.46, respectively. These findings suggest that the spatial and temporal configuration of the SAL, as resolved by a seasonal forecast model, can be leveraged for ERS drought forecasting in Puerto Rico.

