Nowcasting and early warning of severe convective weather play crucial roles in heavy rainfall warning, flood mitigation, and water resource management. However, achieving effective temporal‐spatial resolution nowcasting is a very challenging task owing to the complex dynamics and chaos. Recently, an increasing amount of research has focused on utilizing deep learning approaches for this task because of their powerful abilities in learning spatiotemporal feature representation in an end‐to‐end manner. In this paper, we present convolutional long short‐term memory with a layer called star‐shape bridge to transfer features across time steps. We build an end‐to‐end trainable model for the nowcasting problem using the radar echo data set. Furthermore, we propose a raining‐oriented loss function inspired by the critical success index and utilize the group normalization technique to refine the convergence performance in optimizing our deep network. Experiments indicate that our model outperforms convolutional long short‐term memory with the cross entropy loss function and the conventional extrapolation method.

The microphysical characteristics of rain may vary in different rain regions of a tropical cyclone (TC), but few studies have demonstrated the differences in raindrop size distributions (RSDs) of convective rain in different rainbands of a specific TC. This study examines the RSD characteristics and evolution of convective rain within outer rainbands and a coastal-front-like rainband associated with Typhoon Fitow, based on observational data from a disdrometer at Shibo station in Shanghai, China, during 6-7 October 2013. Considering the fast passage of convective TC rainbands over the disdrometer and the low rain rate of stratiform rain in the outer area, this study proposes a modified rain-type classification method based on the disdrometer data. This study indicates that convective outer-rainband rain (ORR) and coastal-front rain (CFR) have different rain parameters, three parameters of the gamma model, radar reflectivity-rain rate (Z-R), and shape-slope (μ-Λ) relationships. The convective ORR has higher concentrations at all drop sizes than the convective CFR as well as larger spectral width, leading to the greater rainfall rate. The different Z-R relationships suggest the necessity of a variable relationship for quantitative precipitation estimation (QPE) in different rain regions of the TC. This study also demonstrates for the first time that the RSD evolution with increasing rain rate is different in various convective rainbands associated with Fitow, suggesting that different microphysical parameterization schemes may be required for different rainbands in TC models.Note. The terms R, Z, W, N T , D m , D max , and log 10 N w represent rain rate, radar reflectivity, rain water content, total drop concentration, mass-weighted mean diameter, maximum diameter, and normalized intercept parameter, respectively. The rainfall duration and accumulated amount are also given for the different rain types in each stage. "C," "S," and "T" denote the convective, stratiform, and total rainfall, respectively.

The goal of this study was to improve the accuracy of model forecasting, such that forecasters could use model products to make more efficient daily weather predictions. Historical data of the 12 hr following a given time for various meteorological factors from the control forecasts of the European Centre for Medium‐Range Weather Forecasting (ECMWF) between 20 ° and 40 ° N latitude and 110 °–130 ° E longitude were used to verify the performance of the proposed method. Eight major meteorological factors were selected via correlation analysis between control forecast meteorological factors and real‐time rainfall. The samples were divided into four types using the K‐means clustered method. Each type was respectively modelled by long short‐term memory (LSTM) in order to correct rainfall forecasts for eastern China. The eight major meteorological factors were used as the model input, and the differences between real‐time rainfall data and model‐forecast rainfall were used as the model output. The corrected results revealed that the root mean square error decreased by 0.65, and the threat scores of light rainfall and rainstorms were improved.

A novel tropical cyclone (TC) intensity classification and estimation model (TCICENet) is proposed using infrared geostationary satellite images from the northwest Pacific Ocean basin in combination with a cascading deep convolutional neural network (CNN). The proposed model consists of two CNN network modules: a TC intensity classification (TCIC) module and a TC intensity estimation (TCIE) module. First, the TCIC module is utilized to divide TC intensity into three categories using infrared satellite images. Next, three TCIE models based on the CNN regression network that combine different intensity types of infrared satellite images with the TC best track data are presented. The three TCIE models consider classification error with the TCIC module in order to improve TCIE accuracy. A total of 1001 TCs from 1981-2019 were used to verify the proposed TCICENet model, with 844 TCs from 1981-2013 employed as training samples, 76 TCs from 2014-2016 used as validation samples, and 81 TCs from 2017-2019 used as testing samples. In order to reduce the computation burden of training the TCICENet model, various input image sizes were explored. An image size of 170 × 170 pixels achieved the best performance, with an overall root mean square error of 8.60 kt and a mean absolute error of 6.67 kt compared to the best track. Index Terms-Deep convolutional neural network (CNN), intensity estimation, intensity grade classification, tropical cyclone (TC). I. INTRODUCTIONT HE northwest Pacific Ocean basin is one of the most active tropical cyclone (TC) areas in the world, generating approximately 27 TCs per year. According to the TC standards (http://agora.ex.nii.ac.jp/digital-typhoon/help/unit.html. ja#id2) released by the Japan Meteorological Agency (JMA), TCs can be divided into six grades: tropical depression (TD; ∼33 kt), tropical storm (TS; 34-47 kt), severe tropical storm