In order to address the challenges of limited accuracy in identifying non-meteorological clutter and the spatial overlap between meteorological and non-meteorological echoes in cloud radar observations under complex weather conditions, in this study, we propose a quality-control method for cloud-radar data, which integrates machine learning with neighborhood filtering, This quality-control method first uses the Light Gradient Boosting Machine (LightGBM) to initially identify clutter, then employs a customized neighborhood filtering module to optimize and eliminate residual isolated clutter. This two-stage framework combines the strengths of accurate machine-learning-based classification and physically motivated filtering optimization, enabling reliable discrimination between meteorological and non-meteorological echoes. Based on multi-region, long-term and multi-model radar baseline observations, which cover typical complex weather types such as snow, fog, rain, low clouds and dust, the refined manual labeling of meteorological and non-meteorological echoes is carried out, combined with multi-source ground observation data such as surface observations, temperature and humidity. Based on this, a feature training dataset for machine learning is constructed, which contains over 20 million samples. A multi-index evaluation system—including echo classification accuracy and non-meteorological clutter rejection rate—is used to quantitatively assess the quality-control performance of the method in different weather scenarios. The results indicate that the proposed method demonstrates stable performance in typical complex weather scenarios, with comprehensive scores of 90.73 (snow), 94.23 (rain), 96.49 (low clouds), 91.10 (fog) and 95.79 (dust) on a 100-point scale. Through typical case studies and statistical data analysis, the proposed algorithm achieves better quality-control scores in comparison with the Random Forest and single LightGBM algorithms. It provides a new technical approach for cloud-radar data quality control and also offers a theoretical basis for the feature selection of machine-learning-based quality-control models, further enhancing the application value of cloud-radar data in refined meteorological observations.
Hou et al. (Thu,) studied this question.