Extension of Convolutional Neural Network along Temporal and Vertical Directions for Precipitation Downscaling
It addresses precipitation estimation for climate modeling, but is incremental as it adapts existing CNN methods to new dimensions.
This study tackled precipitation downscaling by extending 2D CNNs to 3D along temporal and vertical directions, finding that 3D-CNN-Vert improved accuracy with the best RMSE and NSE scores compared to 2D CNNs.
Deep learning has been utilized for the statistical downscaling of climate data. Specifically, a two-dimensional (2D) convolutional neural network (CNN) has been successfully applied to precipitation estimation. This study implements a three-dimensional (3D) CNN to estimate watershed-scale daily precipitation from 3D atmospheric data and compares the results with those for a 2D CNN. The 2D CNN is extended along the time direction (3D-CNN-Time) and the vertical direction (3D-CNN-Vert). The precipitation estimates of these extended CNNs are compared with those of the 2D CNN in terms of the root-mean-square error (RMSE), Nash-Sutcliffe efficiency (NSE), and 99th percentile RMSE. It is found that both 3D-CNN-Time and 3D-CNN-Vert improve the model accuracy for precipitation estimation compared to the 2D CNN. 3D-CNN-Vert provided the best estimates during the training and test periods in terms of RMSE and NSE.