Authors: Craig Ramseyer*, Salisbury University, Thomas Mote, University of Georgia, Paul Miller, University of Georgia
Topics: Climatology and Meteorology
Keywords: precipitation, Caribbean, Saharan dust
Session Type: Poster
Start / End Time: 10:00 AM / 11:40 AM
Room: Napoleon Foyer/Common St. Corridor, Sheraton, 3rd Floor
Presentation File: Download
This study analyzes future rainfall variability and dry day frequency during the early rainfall season (AMJJ) in eastern Puerto Rico. A binary output artificial neural network (ANN) is trained using ERA-Interim Reanalysis data to predict wet and dry days in eastern Puerto Rico. A second ANN was developed to predict precipitation amount for wet days. The ANNs are trained using 10 predictor variables which includes the Galvez-Davison Index (GDI) and its components as well as low- and mid-tropospheric wind fields. The ANNs are run using a CMIP5 global climate model (GCM) ensemble to analyze future changes in precipitation variability. Additionally, changes in convective potential are examined by using shifts in GDI regimes.