Prediction of the onset of the South China Sea summer monsoon based on machine learningOA
Prediction of the onset of the South China Sea summer monsoon based on machine learning
准确预测南海(SCS)夏季季风(SCSSM)的爆发时间,对于南海周边国家的农业规划和防灾减灾至关重要.然而,由于可用数据有限(每年仅有一个数据点),SCSSM爆发日期的预测存在较大不确定性.在本研究中,作者提出了一种新的SCSSM爆发日期预测方法,基于随机森林回归模型,称为多模型预测方法(MMPM,Multi-model Prediction Method).MMPM随机初始化大量预测模型(约10000个),并基于过去九年的数据选择最优模型,用于预测下一年的SCSSM爆发日期.通过该方法,作者有效减弱了年代际变化的影响,并利用前几个月的海表温度,平均海平面气压以及气温趋势等因子,在SCSSM爆发前一个月进行预测.与现有的统计预测方法(SM-17)相比,MMPM将预测性能提升了10％以上.本研究展示了一种创新策略在克服数据限制方面的有效性,为重要天气模式的预测提供了更好的工具.
Suan Hu;Yineng Li;Jieshuo Xie;Ke Huang;Wenping Gong;Lu Yang
School of Marine Sciences,Sun Yat-sen University,Zhuhai,ChinaState Key Laboratory of Tropical Oceanography,Key Laboratory of Science and Technology on Operational Oceanography,South China Sea Institute of Oceanology,Chinese Academy of Sciences,Guangzhou,China||Guangdong Key Lab of Ocean Remote Sensing,South China Sea Institute of Oceanology,Chinese Academy of Sciences,Guangzhou,ChinaState Key Laboratory of Tropical Oceanography,Key Laboratory of Science and Technology on Operational Oceanography,South China Sea Institute of Oceanology,Chinese Academy of Sciences,Guangzhou,ChinaState Key Laboratory of Tropical Oceanography,Key Laboratory of Science and Technology on Operational Oceanography,South China Sea Institute of Oceanology,Chinese Academy of Sciences,Guangzhou,ChinaSchool of Marine Sciences,Sun Yat-sen University,Zhuhai,ChinaSchool of Atmospheric Physics,Nanjing University of Information Science and Technology,Nanjing,China
南海夏季季风机器学习预测
South China SeaSummer monsoonMachine learningPrediction
《大气和海洋科学快报（英文版）》 2026 (4)
8-13,6
This work was jointly supported by the National Natural Science Foundation of China Regional Innovation and Development Joint Fund[grant number U21A6001],a Guangdong Province Basic and Applied Basic Research Fund Project[grant number 2024B1515040024],and the National Natural Science Foundation of China[grant numbers 42276169 and 42205003].
评论