摘要
长江流域是我国夏季高温热浪灾害的多发区之一,该地区日最高温度(T_(max))具有显著的低频(10~30 d和30~60 d周期)变化特征,超前-滞后相关分析和气温方程诊断的结果显示,影响长江流域T_(max)低频变化的大尺度环流/对流信号包含:自欧亚大陆东移南下的低频波列,自东北亚向西南方向传播的异常环流,以及由西太平洋向东亚传播的低频对流;这些低频对流/环流活动通过改变辐射加热过程及绝热过程,导致长江流域T_(max)的低频变化。为了客观且有效地辨识和捕捉这些先兆信号,并考虑长江流域T_(max)与大尺度因子间的非线性作用,本文采用机器学习方法中的卷积神经网络(Convolutional Neural Network,CNN)对大量历史数据进行训练,并构建了长江流域T_(max)的延伸期预报模型。在独立预报阶段,CNN预报模型对长江流域区域平均T_(max)的预报时效达30 d,提前5~30 d预报的T_(max)与观测T_(max)的时间相关系数介于0.63~0.70(通过99%置信度的显著性检验),量级偏差(均方根误差)小于1个标准差,显示出CNN在延伸期灾害天气预报的应用潜力。
The Yangtze River Ba sin(YRB)is one of the areas with a high frequency of heatwave occurrences in China.The daily maximum temperature(T_(max))in this area shows significant low-frequency oscillation signals for(10—30 d and 30—60 d)time periods.Based on the results of the lead-lag correlation analysis between the YRB T_(max) and the 10—30 d/30—60 d convection and circulation anomalies,we identify the main low-frequency signals affecting the YRB T_(max).There are three types of signals that travel in different directions:1)the eastward and southward signals from the Eurasian continent;2)circulation anomalies propagating southwestward from Northeast Asia;and 3)low-frequency convective signals propagating from the western Pacific toward East Asia.The temperature diagnostic equation results show that when the low-frequency convection/circulation anomalies approach the YRB,both the diabatic(clear-sky radiative heating)and adiabatic(associated with sinking motion)heating processes lead to variations in the YRB temperature.To identify these precursory signals objectively and efficiently,as well as consider the nonlinear interaction between YRB T_(max) and the large-scale predictors,we use Convolutional Neural Network(CNN),a type of deep neural network,to train the historical data,and then develop an extended-range forecast model for YRB T_(max).The independent forecast results show that the CNN-based forecast model is capable of predicting the YRB T_(max) at a 30-day lead time,with the temporal correlation coefficient between the forecast and observed T_(max) of 0.63—0.70(exceeding the 99%confidence level).The current results suggest the potential of CNN in the application of extended-range forecasting as the magnitude of error(root-mean-square error)is less than one standard deviation.
作者
雷蕾
徐邦琪
高庆九
谢洁宏
LEI Lei;HSU Pang-chi;GAO Qingjiu;XIE Jiehong(Key Laboratory of Meteorological Disaster of Ministry of Education(KLME)/Joint International Research Laboratory of Climate and Environment Change(ILCEC)/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters(CIC-FEMD),Nanjing University of Information Science&Technology,Nanjing 210044,China;Jieyang Meteorological Service,Jieyang 515599,China)
出处
《大气科学学报》
CSCD
北大核心
2022年第6期835-849,共15页
Transactions of Atmospheric Sciences
基金
国家自然科学基金资助项目(42088101,42075032)。
关键词
长江流域高温热浪
低频振荡
卷积神经网络
延伸期预报
日最高气温预报
Yangtze River Basin heatwaves
low-frequency oscillation
convolutional neural network
extended-range forecast
daily maximum temperature prediction
