Prediction of the summertime Northwest Pacific subtropical high based on ConvLSTMOA
Prediction of the summertime Northwest Pacific subtropical high based on ConvLSTM
西北太平洋副热带高压(NWPSH)对东亚天气和气候具有重要影响,其强度和位置的预测至关重要.本研究旨在评估卷积长短期记忆(ConvLSTM)模型提前3个月对夏季500 hPa位势高度及NWPSH强度和面积的预测性能,并将其与动力模式南京信息工程大学气候预测系统1.0版(NUIST-CFS1.0)和加拿大季节-年际预测系统第2版(CanSIPSv2)预测结果对比.评估指标为纬度加权均方根误差(RMSEw),异常相关系数(ACC)和NWPSH指数.在夏季平均和逐月预测中,ConvLSTM模型对西太平洋地区500 hPa位势高度的RMSEw和ACC预测技巧均优于动力模式.ConvLSTM模型预测的NWPSH强度指数与观测值的相关系数高于动力模式结果,预测的NWPSH面积指数也表现出更稳定的性能.与两个动力学模式相比,ConvLSTM模型在8月的改进更为显著,表明其对夏季末期环流形势具有更强的捕捉能力.因此,ConvLSTM模型在夏季NWPSH的预测中具有较好的应用潜力,为该区域的气候预测提供了新的视角和方法.
Fei Yang;Jing Ma;Hongxia Lan;Bin Mu;Shijin Yuan;Jing-Jia Luo
Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters/KLME/ILCEC/Institute of Climate and Application Research(ICAR),Nanjing University of Information Science and Technology,Nanjing,ChinaCollaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters/KLME/ILCEC/Institute of Climate and Application Research(ICAR),Nanjing University of Information Science and Technology,Nanjing,ChinaQiannan Meteorological Bureau,Duyun,ChinaSchool of Computer Science and Technology,Tongji University,Shanghai,ChinaSchool of Computer Science and Technology,Tongji University,Shanghai,ChinaCollaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters/KLME/ILCEC/Institute of Climate and Application Research(ICAR),Nanjing University of Information Science and Technology,Nanjing,China
ConvLSTM西北太平洋副热带高压深度学习气候预测
ConvLSTMNorthwest Pacific subtropical highDeep learningClimate prediction
《大气和海洋科学快报（英文版）》 2026 (2)
14-19,6
This work was supported by the National Key Research and Devel-opment Program of China[grant number 2020YFA0608000].
评论