首页|期刊导航|大气和海洋科学快报（英文版）|Improving subseasonal forecasting of East Asian monsoon precipitation with deep learning
大气和海洋科学快报（英文版）2025，Vol.18Issue(3)：34-40,7.DOI:10.1016/j.aosl.2024.100520
Improving subseasonal forecasting of East Asian monsoon precipitation with deep learning
Improving subseasonal forecasting of East Asian monsoon precipitation with deep learning
摘要
Abstract
东亚夏季风(EASM)降水的准确次季节预报至关重要,因为它直接影响着数十亿人的生计.然而,最先进的次季节-季节(S2S)预测模型的预测技巧仍然有限.本研究开发了一种卷积神经网络(CNN)回归模型,通过利用动力预测模型预测的更可靠的环流场来提高EASM周降水的预测技巧.经过CNN模型的订正,在提前一周预测EASM降水指数时,11个S2S模式的平均距平相关系数从增加了14％,从0.30增加到0.35;均方根误差减少了22％,从3.22减少到2.52.在这些S2S模式中,通过CNN订正对预测技巧的提高程度取决于模式在准确预测大气环流变量方面的表现.对EASM降水指数的CNN订正只能订正模式的系统误差,与逐个网格订正还是整个区域平均指数订正无关,并且在不同的提前期内CNN的订正效果基本不变.此外,200hPa纬向风被认为是有效订正的最重要变量.关键词
东亚季风降水/次季节预测/深度学习/误差订正Key words
East asian monsoon precipitation/Subseasonal forecast/Deep learning/Bias correction引用本文复制引用
Jiahui Zhou,Fei Liu..Improving subseasonal forecasting of East Asian monsoon precipitation with deep learning[J].大气和海洋科学快报（英文版）,2025,18(3):34-40,7.基金项目
This work was supported by a Guangdong Major Project of Basic and Applied Basic Research[grant number 2020B0301030004]and the Na-tional Natural Science Foundation of China[grant number 42175061]. （）
