In the context of global warming, tropical cyclones (TCs) have garnered significant attention as one of the most severe natural disasters in China, particularly in terms of assessing the disaster losses. This study aims to evaluate the TC disaster loss (TCDL) using machine learning (ML) algorithms and identify the impact of specific feature factors on the prediction of model with an eXplainable Artificial Intelligence (XAI) approach, SHapley Additive exPlanations (SHAP). The results show that LightGBM outperforms Random Forest (RF), Support Vector Machine (SVM), and Naive Bayes (NB) for estimating the TCDL grades, achieving the highest accuracy value of 0.86. According to the SHAP values, the three most important factors in the LightGBM classifier model are proportion of stations with rainfall exceeding 50 mm (ProRain), maximum wind speed (MaxWind), and maximum daily rainfall (MaxRain). Specifically, in the estimation of high TCDL grade, events characterized with MaxWind exceeding 30 m/s, MaxRain exceeding 200 mm, and ProRain exceeding 30% tend to exhibit a higher susceptibility to TC disaster due to positive SHAP values. This study offers a valuable tool for decision-makers to develop scientific strategies in the risk management of TC disaster.

Reflectivity factor bias caused by radar calibration errors would influence the accuracy of Quantitative Precipitation Estimations (QPE), and further result in spatial discontinuity in Multiple Ground Radars QPE (MGR-QPE) products. Due to sampling differences and random errors, the associated discontinuity cannot be thoroughly solved by the single-radar calibration method. Thus, a multiple-radar synchronous calibration approach was proposed to mitigate the spatial discontinuity of MGR-QPE. Firstly, spatial discontinuity was solved by the intercalibration of adjacent ground radars, and then calibration errors were reduced by referring to the Ku-Band Precipitation Radar (KuPR) carried by the Global Precipitation Measurement (GPM) Core Observatory as a standard reference. Finally, Mosaic Reflectivity and MGR-QPE products with spatial continuity were obtained. Using three S-band operational radars covering the lower reaches of the Yangtze River in China, this method was evaluated under four representative precipitation events. The result showed that: (1) the spatial continuity of reflectivity factor and precipitation estimation fields was significantly improved after bias correction, and the reflectivity differences between adjacent radars were reduced by 78% and 82%, respectively; (2) the MGR-QPE data were closer to gauge observations with the normalized absolute error reducing by 0.05 to 0.12.

This paper presents a stand-alone cloud detection algorithm over land (CDL) for Microwave Humidity Sounder -2 (MWHS-2), which is characterized by the first operational satellite sensor measuring 118.75 GHz. The CDL is based on the advanced machine learning (ML) algorithm Gradient Boosting Decision Tree (GBDT), which achieves the state-of-the-art performance on tabular data, with high accuracy, fast training speed, great generalization ability, and weight factor ranking of predictors (or features). Given that the new generation weather radar of China (CINRAD) provides improved cloud information with extensive temporal-spatial coverage, the observations from CINRAD are used to train the algorithm in this study. There are four groups of radiometric information employed to evaluate the CDL: all frequency ranges from MWHS-2 (all-algorithm), the humidity channels near 183.31 GHz (hum-algorithm), the temperature channels near 118.75 GHz (tem-algorithm), and the window channels at 89 and 150 GHz (win-algorithm). It is revealed that the tem-algorithm (around 118.75 GHz) has a superior performance for CDL along with the optimal values of most evaluation metrics. Although the all-algorithm uses all available frequencies, it shows inferior ability for CDL. Followed are the win-algorithm and hum-algorithm, and the win-algorithm performs better. The analysis also indicates that the latitude, zenith angle, and the azimuth are the top ranking features for all four algorithms. The presented algorithm CDL can be applied in the quality control processes of assimilating microwave (MW) radiances or in the retrieval of atmospheric and surface parameters for cloud filtering.

The measurement error of differential reflectivity (Z_DR), especially systematic Z_DR bias, is a fundamental issue for the application of polarimetric radar data. Several calibration methods have been proposed and applied to correct Z_DR bias. However, recent studies have shown that Z_DR bias is time-dependent and can be significantly different on two adjacent days. This means that the frequent monitoring of Z_DR bias is necessary, which is difficult to achieve with existing methods. As radar sensitivity has gradually been enhanced, large amounts of online solar echoes have begun to be observed in volume-scan data. Online solar echoes have a high frequency, and a known theoretical value of Z_DR (0 dB) could thus allow the continuous monitoring of Z_DR bias. However, online solar echoes are also affected by low signal-to-noise ratio and precipitation attenuation for short-wavelength radar. In order to understand the variation of Z_DR bias in a C-band polarimetric radar at the Nanjing University of Information Science and Technology (NUIST-CDP), we analyzed the characteristics of online solar echoes from this radar, including the daily frequency of occurrence, the distribution along the radial direction, precipitation attenuation, and fluctuation caused by noise. Then, an automatic method based on online solar echoes was proposed to monitor the daily Z_DR bias of the NUIST-CDP. In the proposed method, a one-way differential attenuation correction for solar echoes and a maximum likelihood estimation using a Gaussian model were designed to estimate the optimal daily Z_DR bias. The analysis of three months of data from the NUIST-CDP showed the following: (1) Online solar echoes occurred very frequently regardless of precipitation. Under the volume-scan mode, the average number of occurrences was 15 per day and the minimum number was seven. This high frequency could meet the requirements of continuous monitoring of the daily Z_DR bias under precipitation and no-rain conditions. (2) The result from the proposed online solar method was significantly linearly correlated with that from the vertical pointing method (observation at an elevation angle of 90°), with a correlation coefficient of 0.61, suggesting that the proposed method is feasible. (3) The day-to-day variation in the Z_DR bias was relatively large, and 32% of such variations exceeded 0.2 dB, meaning that a one-time calibration was not representative in time. Accordingly, continuous calibration will be necessary. (4) The Z_DR bias was found to be largely influenced by the ambient temperature, with a large negative correlation between the Z_DR bias and the temperature.