Gust fronts (GFs) belong to the boundary layer convergence system. A strong GF can cause serious wind disasters, so its automatic monitoring and identification are very helpful but difficult in daily meteorological operations. By collecting convective weather processes in Hubei, Jiangsu, and other regions of China, 1422 GFs from 106 S-band new-generation weather radar (CINRAD/SA) volume scan data are labeled as positive samples by means of human–computer interaction, and the same number of negative samples are randomly tagged from no GF radar data. A deep learning dataset including 2844 labels with a positive and negative sample ratio of 1:1 is constructed, and 80%, 10%, and 10% of the dataset are separated as training, validation, and test sets, respectively. Then, the training dataset is expanded to 273,120 samples by data augmentation technology. Since the height of a GF is generally less than 1.5 km, three deep-learning-based models are trained for GF automatic recognition according to the distance from the radars. Three models (M1, M2, M3) are trained with the data at a 0.5° elevation angle from 65 to 180 km away from the radars, at 0.5° and 1.5° angles from 40 to 65 km, and at 0.5°, 1.5°, and 2.4° angles within 40 km, respectively. The precision, confusion matrix, and its derived indicators including receiver operating characteristic curve (ROC) and the area under ROC (AUC) are used to evaluate the three models by the test set. The results show that the identification precisions of the models are 97.66% (M1), 90% (M2), and 90.43% (M3), respectively. All the hit rates are over 89%, the false positive rates are less than 11%, and the critical success indexes (CSIs) surpass 82%. In addition, all the optimal critical points on the ROC curves are close to (0, 1), and the AUC values are above 0.93. These results suggest that the three models can effectively achieve the automatic discrimination of GFs. Finally, the models are demonstrated by three GF events detected with Qingpu, Nantong, and Cangzhou radars.

Quantitative precipitation forecast (QPF) verification stands out as one of the most formidable endeavors in the realm of forecast verification. Traditional verification methods are not suitable for high-resolution forecasting products in some cases. Therefore, the SAL (structure, amplitude and location) method was proposed as a method of object-based spatial verification that studies precipitation verification in a certain range, which is combined with factors including structure, amplitude and location of the targets. However, the setting of the precipitation threshold would affect the result of the verification. This paper presented an improved method for determining the precipitation threshold using the QPF from ECMWF, which is an ensemble forecast model and three-source fusion product that was used in China from 1 July to 31 August 2020, and then the results obtained with this method were compared with the other two traditional methods. Furthermore, the SAL and the traditional verification methods were carried out for geometric, simulated and real cases, respectively. The results showed the following: (1) The proposed method in this paper for determining the threshold was more accurate at identifying the precipitation objects. (2) The verification area size was critical for SAL calculation. If the area selected was too large, the calculated SAL value had little significance. (3) ME (Mean Error) could not identify the displacement between prediction and observation, while HSS (Heidke Skill Score) was sensitive to the displacement of the prediction field. (4) Compared with the traditional verification methods, the SAL method was more straight forward and simple, and it could give a better representation of prediction ability. Therefore, forecasters can better understand the model prediction effect and what needs to be improved.

The change in raindrop spectrum characteristics is an important factor affecting the accuracy of estimations of precipitation. The in-depth study of raindrop spectrum characteristics is of great interest for understanding precipitation process and improving quantitative radar precipitation estimation. In this paper, the raindrop size distributions at Longli (57913), Puding (57808) and Luodian (57916) stations in Guizhou were analyzed from the perspective of precipitation microphysical characteristics. The results showed that the raindrop size distribution was different among different regions. The correlation coefficients of the mass-weighted average diameter for the rain intensities at these three stations were 46.89%, 49.51%, and 47.03%, respectively, which were slightly lower than the normal correlation coefficients of the average volume diameter for the rain intensities: 67.80%, 71.28%, and 71.46%, respectively. Based on the data from the Guiyang weather radar, raindrop spectrometer, and automatic rain gauge, the dynamic Z-I relationship method and the LSTM neural network method were used to estimate precipitation. The correlation coefficients of the dynamic Z-I relationship method and the LSTM neural network method at the three stations studied were 0.8432, 0.7763, and 0.8658 and 0.8745, 0.9125, and 0.8676, respectively. Regarding the process of stratiform cloud precipitation, the correlation coefficients of the dynamic Z-I relationship method and LSTM neural network method at the three stations were 0.6933, 0.0902, and 0.1409 and 0.7114, 0.4984, and 0.4902, respectively. In the estimation of cumulative precipitation for 45 days from 1 July to 16 August 2020, the relative errors of the neural network estimation at the three stations were −4.25%, −11.35%, and −8.68% and the relative errors of the dynamic Z-I relationship estimation were −2.68%, −7.41%, and −21.23%, respectively. The final relative error of the neural network was slightly worse than that of the dynamic Z-I relationship in the cumulative precipitation estimations of Longli station and Puding station, but the overall correlation coefficients of the LSTM neural network method were better than those of the dynamic Z-I relationship method.

Our study and analysis of the distribution differences in raindrop spectra in a Guizhou precipitation prediction model were of great significance for understanding precipitation microphysical processes and improving radar quantitative precipitation prediction. This article selected the Dafang, Majiang, and Luodian stations at different altitudes in Guizhou and analyzed the distribution characteristics of precipitation particles at different altitudes. This article used precipitation data from the new-generation Doppler weather radar, OTT-Parsivel laser raindrop spectrometer, and automatic meteorological observation stations in Guiyang via M-P and GAMMA and established methods to fit the particle size of raindrop spectrum precipitation. Based on the LSTM neural network method, we constructed a precipitation prediction model for Guizhou and conducted performance testing. The results show that (1) the precipitation particles at the three stations are all concentrated in small particle size areas, with a peak value of 0.312 mm and a final falling velocity of 1–5 m/s, and the particle size increases with a decreasing altitude. The contribution rate to the density of particles with a precipitation particle size of less than 1 mm exceeds 80% and decreases with a decreasing altitude. The average volume diameter of precipitation particles has the highest correlation with the precipitation intensity. (2) In the fitting of the raindrop spectrum distribution, the GAMMA distribution fitted by the three stations has a better effect and the fitting effect gradually improves with an increasing altitude. (3) In precipitation prediction for convective clouds and stratiform clouds, the 60 min prediction results are the most consistent with the actual precipitation, with correlation coefficients of 0.9287 and 0.9257, respectively, indicating that the prediction has high reliability.

Radar echo extrapolation is a critical forecasting tool in the field of meteorology, playing an especially vital role in nowcasting and weather modification operations. In recent years, spatiotemporal sequence prediction models based on deep learning have garnered significant attention and achieved notable progress in radar echo extrapolation. However, most of these extrapolation network architectures are built upon convolutional neural networks, using radar echo images as input. Typically, radar echo intensity values ranging from −5 to 70 dBZ with a resolution of 5 dBZ are converted into 0–255 grayscale images from pseudo-color representations, which inevitably results in the loss of important echo details. Furthermore, as the extrapolation time increases, the smoothing effect inherent to convolution operations leads to increasingly blurred predictions. To address the algorithmic limitations of deep learning-based echo extrapolation models, this study introduces three major improvements: (1) A Deep Convolutional Generative Adversarial Network (DCGAN) is integrated into the ConvLSTM-based extrapolation model to construct a DCGAN-enhanced architecture, significantly improving the quality of radar echo extrapolation; (2) Considering that the evolution of radar echoes is closely related to the surrounding meteorological environment, the study incorporates specific physical variable products from the initial zero-hour field of RMAPS-NOW (the Rapid-update Multiscale Analysis and Prediction System—NOWcasting subsystem), developed by the Institute of Urban Meteorology, China. These variables are encoded jointly with high-resolution (0.5 dB) radar mosaic data to form multiple radar cells as input. A multi-channel radar echo extrapolation network architecture (MR-DCGAN) is then designed based on the DCGAN framework; (3) Since radar echo decay becomes more prominent over longer extrapolation horizons, this study departs from previous approaches that use a single model to extrapolate 120 min. Instead, it customizes time-specific loss functions for spatiotemporal attenuation correction and independently trains 20 separate models to achieve the full 120 min extrapolation. The dataset consists of radar composite reflectivity mosaics over North China within the range of 116.10–117.50°E and 37.77–38.77°N, collected from June to September during 2018–2022. A total of 39,000 data samples were matched with the initial zero-hour fields from RMAPS-NOW, with 80% (31,200 samples) used for training and 20% (7800 samples) for testing. Based on the ConvLSTM and the proposed MR-DCGAN architecture, 20 extrapolation models were trained using four different input encoding strategies. The models were evaluated using the Critical Success Index (CSI), Probability of Detection (POD), and False Alarm Ratio (FAR). Compared to the baseline ConvLSTM-based extrapolation model without physical variables, the models trained with the MR-DCGAN architecture achieved, on average, 18.59%, 8.76%, and 11.28% higher CSI values, 19.46%, 19.21%, and 19.18% higher POD values, and 19.85%, 11.48%, and 9.88% lower FAR values under the 20 dBZ, 30 dBZ, and 35 dBZ reflectivity thresholds, respectively. Among all tested configurations, the model that incorporated three physical variables—relative humidity (rh), u-wind, and v-wind—demonstrated the best overall performance across various thresholds, with CSI and POD values improving by an average of 16.75% and 24.75%, respectively, and FAR reduced by 15.36%. Moreover, the SSIM of the MR-DCGAN models demonstrates a more gradual decline and maintains higher overall values, indicating superior capability in preserving echo structural features. Meanwhile, the comparative experiments demonstrate that the MR-DCGAN (u, v + rh) model outperforms the MR-ConvLSTM (u, v + rh) model in terms of evaluation metrics. In summary, the model trained with the MR-DCGAN architecture effectively enhances the accuracy of radar echo extrapolation.

Raindrop size distribution (RSD) is an index for reflecting precipitation characteristics. Analyzing the differences of RSD plays an important role in understanding the precipitation microphysical processes and improving quantitative precipitation prediction of radar. In this paper, the RSD data of Dafang (57708) station, Majang (57828) station, and Luodian (57916) station (with an altitude of 1722.7m, 985.0m, and 441.5m, respectively) in Guizhou are analyzed according to the precipitation microphysical characteristics. First,Particles with particle size less than 1mm contributes the highest value to the density of particle number , and decrease with the descending altitude. Second, the GAMMA distribution fit shows a better fit compare to M-P distribution fit, and GAMMA distribution fit increases with the ascending altitude. Third, the mass-weighted average diameter is not sensitive enough to the change of precipitation intensity with correlation coefficients of 54.84%, but there is a obvious relationship between the average volume diameter and the precipitation intensity with correlation coefficients of 69.15%. Then, the precipitation prediction model is established using LSTM neural network after fusing the representative microphysical characteristics of RSD with radar and rain gauge data. The precipitation prediction model is applied to the Dafang (57708) site to predict precipitation for time range of 0-180 minutes, and it is found that for the prediction of convective cloud and stratiform cloud precipitation, the 60-minute prediction results are the most consistent with the actual precipitation, where the correlation coefficients are 92.87% and 92.57%, respectively. Conclusively, the results demonstrate that combining with the RSD base data could improve the reliability of precipitation forecasting.