Projection of rainfall under representative concentration pathways scenarios in a data scarce region of Iraq

Abstract

A study has been conducted for projection of monthly rainfall in Baghdad of Iraq using a General Circulation Models (GCM) of Coupled Model Intercomparison Project Phase 5 (CMIP5) under four representative concentration pathways (RCP) scenarios namely RCP2.6, RCP4.5, RCP6.0 and RCP8.5. For this purpose, monthly gridded precipitation datasets produced by the centre for climatic research, University of Delaware (UDel) and GCM BCC-CSM1-1 simulated precipitation data at 46 grid points surrounding Baghdad were used. The statistical downscaling models were developed using Support Vector Machine (SVM) and Random Forest (RF). The performance of downscaling model assessed using different statistical measures showed that SVM could simulate historical rainfall in the region very well. Projection of rainfall using SVM revealed that rainfall at Baghdad will change in the range of 3.5% to -6.2% in the end of this century.