大气科学学报2025，Vol.48Issue(3)：449-462,14.DOI:10.13878/j.cnki.dqkxxb.20240928001
基于葵花卫星和机器学习的石家庄对流初生判别研究
Convective initiation forecasting in Shijiazhuang using Himawari-8/9 satel-lite data and machine learning
摘要
Abstract
Geostationary meteorological satellites can detect precursor signals of cumulus cloud development ear-lier than weather radar systems,making them valuable for convective initiation forecasting.To leverage this advan-tage,various algorithms have been developed,typically involving cloud detection,the removal of cirrus and mature clouds,overlap tracking,and convective initiation identification.Among these steps,the removal of cirrus and mature clouds is particularly crucial,as these cloud types can obscure developing cumulus clouds.However,existing methods face challenges such as cumulus cloud fragmentation after cirrus and mature cloud removal,dif-ficulties in applying overlap tracking to complex cloud imagery,and limitations in threshold-based convective ini-tiation identification.To address these issues,this study introduces several targeted improvements.First,a novel ap-proach is proposed that treats complete cloud clusters as the primary research subject,allowing for the comprehen-sive extraction of cumulus lifecycle samples.Second,the Hungarian algorithm is incorporated to enhance multi-tar-get tracking capabilities.Third,a random forest algorithm is employed to improve the accuracy of convective initi-ation identification.This study utilizes data from Himawari-8/9 satellites and weather radar observations to analyze convective initiation in the Shijiazhuang region.A cumulus cloud identification method,specifically tailored to the region,was developed and combined with a multi-target tracking algorithm to construct a detailed dataset of con-vective cells.By integrating this dataset with radar observations,cumulus clouds associated with weather processes exhibiting reflectivity values above 35 dBZ were identified.The time at which reflectivity first reached 35 dBZ was recorded as the convective initiation time,providing a robust dataset for further analysis.A comparative analy-sis of multi-channel brightness temperature variations and cumulus cloud development processes revealed key trends.Specifically,as cumulus clouds evolved into strong convective systems,the 10.4 μm brightness temperature in the Shijiazhuang region exhibited a decreasing trend,while the brightness temperature difference between 12.4 μm and 10.4 μm,as well as the three-channel brightness temperature difference(TTD),showed an increasing trend.These patterns were used to identify key factors influencing convective initiation.Based on these findings,a random forest model was developed for convective initiation forecasting in the Shijiazhuang re-gion.The model demonstrated strong performance during testing,achieving a 92％probability of detection(POD)and a 31％false alarm rate(FAR).These results indicate that the model effectively identifies cumulus clouds likely to develop into strong convective systems,even before radar-detectable echoes emerge.A key contribution of this study is its potential to improve the timeliness of severe convective weather warnings in the Shijiazhuang region.By leveraging satellite data and advanced machine learning techniques,the proposed algorithm can detect developing cumulus clouds earlier than traditional radar-based methods.This capability is particularly valuable in regions where severe convective weather significantly impacts agriculture,transportation,and public safety.The in-tegration of Himawari-8/9 satellite data with weather radar observations enhances the understanding of convective processes,leading to more accurate and timely forecasts.In conclusion,this study represents a significant advance-ment in convective initiation forecasting by addressing key challenges in cloud detection,tracking,and identifica-tion while integrating machine learning techniques.The successful application of this model in the Shijiazhuang re-gion demonstrates its potential for broader use in other convective weather-prone areas.Future research could focus on refining the model,expanding the dataset,and exploring additional machine learning approaches to further enhance forecasting accuracy and reliability.This study not only advances the scientific understanding of convective processes but also has practical implications for improving weather warning systems and mitigating se-vere weather impacts.关键词
对流初生/机器学习/多目标跟踪/葵花8/9号卫星/天气雷达Key words
convective initiation/machine learning/multi-object tracking/Himawari-8/9 satellite/weather radar引用本文复制引用
张立霞,周玉淑,万秉成,房荣,梁阔,张哲..基于葵花卫星和机器学习的石家庄对流初生判别研究[J].大气科学学报,2025,48(3):449-462,14.基金项目
国家自然科学基金项目(42175012) （42175012）
江苏省"卓博计划"项目(2023ZB012) （2023ZB012）
中国气象局复盘总结专项(FPZJ2024-012) （FPZJ2024-012）
