Comparison of neural network architectures and inputs for radar rainfall adjustment for typhoon events

SummaryThis work presents a radar rainfall adjustment approach that uses two neural network architectures, support vector regression and the radial basis function neural network. The proposed approach can increase the accuracy of radar rainfall estimates that are underestimated, especially in mountainous regions. Hourly rainfall data observed at 126 raingauges in typhoon events provide the ground-truth information for adjusting radar rainfall estimates. Various inputs to the adjustment model are variable combinations of the radar rainfall, the coordinates, the elevation and the distance to the radar station. Simulation results and their intercomparison indicate that including additional topographic variables in the input vector can enhance the model performance. Validation results pertaining to three typhoon events further demonstrate that the adjustment models can reduce radar rainfall errors. Moreover, the support vector regression outperforms the radial basis function neural network in terms of radar rainfall adjustment. The spatial rainfall distribution of adjusted radar rainfall is also presented, as well as the model calibration and validation by two sets of gauges to show the generality of the method.

► This work presents a radar rainfall adjustment approach that uses support vector regression and the radial basis function neural network. ► Various input combinations including the radar rainfall estimates, coordinates, elevation, and distance were tested and compared. ► Results indicate that including additional topographic variables in the input vector can enhance the model performance. ► The support vector regression outperforms the radial basis function neural network in terms of radar rainfall adjustment in the study area.