Abstract
Quantitative precipitation estimation (QPE) based on Doppler radar plays an important role in severe weather monitoring, industrial and agricultural production, and natural disaster prediction and prevention. However, the temporal and spatial variability of precipitation leads to large errors in radar estimates of mixed precipitation. To improve the accuracy of radar QPE, we propose an offline spatiotemporal deep fusion model that uses the reflectivity data of the Shijiazhuang Doppler radar Z9311 and the precipitation data from 17 national weather stations (NWSs) and 260 automatic weather stations (AWSs). Considering the abrupt spatial changes in precipitation, a three-dimensional radar data structure is proposed, and the spatial features of multielevation and multiscale radar data are extracted and merged using the feature fusion network (FFNet). Finally, the time dependence of the precipitation is captured using the long short-term memory (LSTM) network, and the precipitation estimation is obtained. Based on a comparison of the results of the proposed model (FFNet-LSTM) with those of the ordinary kriging (OK) interpolation, two Z-R relationship, the multilayer perceptron (MLP), the LSTM, and the FFNet, the proposed method is superior to these models, has a promising performance, and is a general-purpose rainfall algorithm.
Highlights
A more accurate and real-time quantitative precipitation estimation (QPE) provides a reliable data source for hydrology, meteorology, and disaster forecasting [1, 2]
To illustrate the priority of the proposed model, the Ordinary Kriging (OK) interpolation based on Spherical variogram [19], Z 300R1.4 (Z–R(1)), Z-R relationship based on the optimization algorithm (Z–R(2)) [35], the multilayer perceptron (MLP) model, the feature fusion network (FFNet) model, and the long short-term memory (LSTM) model were selected for comparison with the proposed model. e constant altitude plan position indicating (CAPPI) data at an elevation of 2.0 km were used as the input of the FFNet (FFNet (Grid 2.0 km)) to verify the effectiveness of the FFNet model’s feature fusion
Based on the observations from the 260 Automatic Weather Stations (AWSs), the CC, root mean square error (RMSE), mean absolute error (MAE), and mean bias (MB) of the precipitation estimates obtained using the Z-R (1), MLP model, and FFNet-LSTM (Loss_Sum) were calculated for each gauge, and the gauge values were interpolated into others using the inverse distance weighting (IDW) interpolation to obtain the spatial distribution of the metrics [70]
Summary
Received 6 April 2021; Revised 8 June 2021; Accepted 18 July 2021; Published 28 July 2021. Quantitative precipitation estimation (QPE) based on Doppler radar plays an important role in severe weather monitoring, industrial and agricultural production, and natural disaster prediction and prevention. The temporal and spatial variability of precipitation leads to large errors in radar estimates of mixed precipitation. To improve the accuracy of radar QPE, we propose an offline spatiotemporal deep fusion model that uses the reflectivity data of the Shijiazhuang Doppler radar Z9311 and the precipitation data from 17 national weather stations (NWSs) and 260 automatic weather stations (AWSs). Considering the abrupt spatial changes in precipitation, a three-dimensional radar data structure is proposed, and the spatial features of multielevation and multiscale radar data are extracted and merged using the feature fusion network (FFNet). The time dependence of the precipitation is captured using the long short-term memory (LSTM) network, and the precipitation estimation is obtained. Based on a comparison of the results of the proposed model (FFNet-LSTM) with those of the ordinary kriging (OK) interpolation, two Z-R relationship, the multilayer perceptron (MLP), the LSTM, and the FFNet, the proposed method is superior to these models, has a promising performance, and is a general-purpose rainfall algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
