Improving the accuracy of global precipitation measurement integrated multi-satellite retrievals (GPM IMERG) using atmosphere precipitable water and altitude in climatic regions of Iran

The global precipitation measurement integrated multi-satellite retrievals (GPM IMERG) provide a new opportunity to estimate precipitation remotely. However, the accuracy of estimations varies in different regions. Therefore, the aim of this study is to improve the IMERG precipitation estimations using two influencing factors including total precipitable water (TPW) and altitude data. The investigations were performed in six rainfall climatic regions of Iran using daily and six-hourly IMERG estimations in years 2015 to 2017. TPW was extracted from a locally developed algorithm for the moderate resolution imaging spectroradiometer (MODIS) measurements. Different models named as M1 to M4 were investigated by considering combinations of the linear and quadratic forms of the IMERG precipitation, TPW, and altitude. The results were evaluated by root mean square error (RMSE), correlation coefficient (r), and Nash-Sutcliffe (NSc). The results showed that the M1 represents the best performance among the proposed models, which uses linear relationship of the IMERG estimations and TPW along with the constant value. The mean values of r, RMSE, and NSc criteria for daily precipitation estimations of IMERG were acquired as 0.46, 5.88, and -2.77 mm, respectively. Those values were improved by M1 to 0.52, 0.18, and 0.27 mm, respectively. Moreover, the evaluation results of IMERG six-hourly precipitation estimations showed r, RMSE, and NSc of 0.65, 11.26, and -33.27 mm. The values of these criteria were improved by M1 to 0.65, 0.07, and 0.32 mm. In general, the results proved the ability of TPW to improve IMERG precipitation estimations in the study area.