Modeling high-resolution precipitation by coupling a regional climate model with a machine learning model: an application to Sai Gon-Dong Nai Rivers Basin in Vietnam

Modeling of large rainfall events plays an important role in water resources and floodplain management. Rainfall is resulted from complex interactions between climate factors (air moisture, temperature, wind speed, etc.) and land surface (topography, soil, land cover, etc.). Therefore, deriving accurate areal rainfall is not only relied on atmospheric boundary conditions, but also on the reliability and availability of soils, topography, and vegetation data. Consequently, uncertainties in both atmospheric and land surface conditions contributes to rainfall model errors. In this study, a blended technique combining dynamical and statistical downscaling has been explored. The proposed downscaling approach uses input provided from three different global reanalysis data sets including ERA-Interim, ERA20C, and CFSR. These reanalysis atmospheric data are hybridly downscaled by means of the Weather Research and Forecasting (WRF) model, which is followed by the application of an artificial neural network (ANN) model to further downscale the WRF output to a finer resolution over the studied region. The proposed technique has been applied to the third largest river basin in Vietnam, the Sai Gon-Dong Nai Rivers Basin; and the calibration and validation show the simulation results agreed well with observation data. Results of this study suggest that the proposed approach can improve the accuracy of simulated data, as it merges model simulations with observations over the modeled region. Another highlight of this approach is inexpensive computational demand on both computation times and output storage.