Random forests (RFs), an advanced machine learning (ML) method, was used here to develop a robust and rapid quantitative precipitation estimates (QPEs) algorithm for the new-generation geostationary satellite of Himawari-8. In this algorithm, the global precipitation measurement (GPM) product has been employed to train QPE prediction model. The real-time multiband infrared brightness temperature from Himawari-8, combined with the spatiotemporally matched numerical weather prediction (NWP) data from the global forecast system, have been used as predictor variables for QPE. Among the variables used in RF learning model, total precipitable water and K-index from NWP data have the highest rankings, indicating the importance of atmospheric environment for QPE. To enhance the accuracy of RF models or to optimize model training, a sample-balance technique has been utilized to adjust the ratios of samples in nonprecipitation/precipitation classification and quantitative precipitation regression data sets. Further sensitivity and validation analyses help determine the optimal RF classification and regression models for predicting nonprecipitation/precipitation pixel and rain rate. The selected RF classification model is found to predict precipitation area with an accuracy of 0.87. For predicted QPE product, the mean-absolute-error and root-mean-square error of RF regression model are 0.51 and 2.0 mm/h, respectively. Overall, the RF ML algorithm has a higher detection rate over homogenous ocean surface as compared with over land. Meanwhile, this RF algorithm tends to underestimate rain rate, especially in the presence of heavy rainfall. Despite this, it still produces a reasonable pattern of rainfall area and intensity, which are highly consistent with GPM observations.

Accurate and prior identification of local severe storm systems in pre-convection environments using geostationary satellite imagery measurements is a challenging task. Methodologies for “convective initiation” identification have already been developed and explored for operational nowcasting applications; however, warning of such convective systems using the new generation of geostationary satellite imagery measurements in pre-convection environments is still not well studied. In this investigation, the Random Forest (RF) machine learning algorithm is used to develop a predictive statistical model for tracking and identifying three different types of convective storm systems (weak, medium, and severe) over East Asia by combining spatially-temporally collocated Himawari-8 (H08) measurements and Numerical Weather Prediction (NWP) forecast data. The Global Precipitation Measurement (GPM) gridded product is used as a benchmark to train the predictive models based on a sample-balance technique which can adjust or balance the samples of three different convection types to avoid over-fitting any type of dataset. Variables such as brightness temperatures (BTs) from H08 water vapor absorption bands (6.2 μm, 6.9 μm and 7.3 μm) and Total Precipitable Water (TPW) from NWP show relatively high ranks in the predictive model training. These sensitive variables are closely associated with convectively dominated precipitation areas, indicating the importance of predictors from both H08 and NWP data. The final optimal RF model is achieved with an accuracy of 0.79 for classification of all convective storm systems, while the Probability of Detection (POD) of this model for severe and medium convections can reach 0.66 and 0.70, respectively. Two typical sudden convective storm cases in the warm season of 2018 tracked by this algorithm are described, and results indicate that the H08 and NWP based statistical model using the RF algorithm is capable of capturing local burst convective storm systems about 1–2 h earlier than the outbreak of heavy rainfall.

Ground-based weather radar data plays an essential role in monitoring severe convective weather. The detection of such weather systems in time is critical for saving people’s lives and property. However, the limited spatial coverage of radars over the ocean and mountainous regions greatly limits their effective application. In this study, we propose a novel framework of a deep learning-based model to retrieve the radar composite reflectivity factor (RCRF) maps from the Fengyun-4A new-generation geostationary satellite data. The suggested framework consists of three main processes, i.e., satellite and radar data preprocessing, the deep learning-based regression model for retrieving the RCRF maps, as well as the testing and validation of the model. In addition, three typical cases are also analyzed and studied, including a cluster of rapidly developing convective cells, a Northeast China cold vortex, and the Super Typhoon Haishen. Compared with the high-quality precipitation rate products from the integrated Multi-satellite Retrievals for Global Precipitation Measurement, it is found that the retrieved RCRF maps are in good agreement with the precipitation pattern. The statistical results show that retrieved RCRF maps have an R-square of 0.88-0.96, a mean absolute error of 0.3-0.6 dBZ, and a root-mean-square error of 1.2-2.4 dBZ.

Weather radars are commonly used to track the development of convective storms due to their high resolution and accuracy. However, the coverage of existing weather radar is very limited, especially in mountainous and ocean areas. Geostationary meteorological satellites can provide near global coverage and near real-time observations, which can compensate for the lack of radar observations. In this paper, a deep learning method was used to estimate the radar composite reflectivity from observations of China’s new-generation geostationary meteorological satellite FY-4A and topographic data. The derived radar reflectivity products from satellite observations can be used over regions without radar coverage. In general, the deep learning model can reproduce the overall position, shape, and intensity of the radar echoes. In addition, evaluation of the reconstruction radar observations indicates that a modified model based on the attention mechanism (Attention U-Net model) has better performance than the traditional U-Net model in terms of all statistics such as the probability of detection (POD), critical success index (CSI), and root-mean-square error (RMSE), and the modified model has stronger capability on reconstructing details and strong echoes.

Nowcasting of convective weather is a challenging and significant task in operational weather forecasting system. In this study, a new convolution recurrent neural network (ConvRNN)-based regression network for convective weather prediction is proposed, which is named as the Convective Weather Nowcasting Net (CWNNet). The CWNNet adopts the joint observations of Fengyun-4A geostationary satellite and the ground-based Doppler weather radar data of the last 0–1-hour as the inputs of the model to predict the radar reflectivity factor maps of next 0-1 hour. The statistical validating results clearly demonstrate that the mean values of the probability of detection, false alarm ratio, threat score, root mean square error and mean absolute error evaluating the performance of CWNNet for 1-h nowcasting reach 0.87, 0.137, 0.71, 3.365 dBZ and 1.038 dBZ, respectively. Due to that the geostationary meteorological satellite is capable of capturing the features of convective initiation, the CWNNet shows a good performance in convective initiation nowcasting. Besides, several case studies also further indicate that the CWNNet can predict convective initiation more than 30 minutes in advance by monitoring the convective clouds. The CWNNet based on the joint satellite and radar data shows a better nowcasting performance than that only employing single data source. Thus, it can effectively produce more reliable nowcasting for convective weather events.

Severe convection is a disastrous mesoscale weather system. The early detection of such systems is very important for saving peoples’ lives and properties. Previous studies address the issue mainly based on thresholding methods, which are not robust and accurate enough. In this paper, we propose a novel semantic segmentation method (Dugs-UNet) to solve the problem. Our method is based on the well-known U-Net framework. As convective clouds mimic fluids, its detection faces two important challenges. First, the shape and boundary features of clouds need to be carefully exploited. Second, the positive and negative samples for convection detection are very imbalanced. To address the two challenges, our method was carefully developed. Regarding the importance of the shape and boundary features for convective target detection, we introduce a shape stream module to extract these features. Also, a data-dependent upsample operation is adopted in the decoder of U-Net to effectively utilize the features. This is one of our contributions. To address the imbalance issue for convective target detection, the a focal loss function is employed to train our method, which is another contribution. Experimental results of 2018 Fengyun-4A satellite observations in China demonstrate the effectiveness of the proposed method. Compared to conventional thresholding-based methods and deep semantic segmentation algorithms such as SegNet, PSPNet, DeepLav-v3+ and U-Net, the proposed approach performs the best.