Application of deep learning to estimate stratospheric gravity wave potential energy
Application of deep learning to estimate stratospheric gravity wave potential energy
复制标题
应用深度学习估算平流层重力波势能
DOI：
10.26464/epp2022002
复制
发表时间：
2022
影响因子：
2.9
通讯作者：
Zuo X
中科院分区：
文献类型：
--
作者：
Wu Y;Sheng Z;Zuo X
作为中高层大气最重要的动力过程之一，重力波（GWs）在决定全球大气环流方面发挥着关键作用。重力波势能（GW Ep）是表征引力波强度的重要参数，因此了解其全球分布非常必要。本文采用深度学习算法（DeepLab V3+）来估计平流层重力波 Ep。深度学习模型的输入是ERA5再分析数据集和GMTED2010地形数据。输出是从 60°S–60°N 20–30 公里处平均估计的 GW Ep。采用COSMIC射电掩星（RO）数据计算出的20~30 km范围内的平均GW Ep作为模型输出对应的测量值。结果表明：(1)该方法能够有效地估计GW Ep的纬向趋势。然而，低纬度地区的Ep估计值与实测值之间的误差要大于中纬度地区。深度学习模型中使用的大量卷积运算可能是主要原因。另外，测量的Ep存在与网格插值相关的误差，在低纬度地区，由于GW Ep较大且RO数据相对稀疏，误差往往会被放大，从而影响训练精度。 (2)估计的Ep具有季节变化，冬半球较强，夏半球较弱。 (3) 在估算的GW Ep的月变化中可以清楚地观察到准两年期振荡(QBO)的影响，并且其QBO幅度可能小于实测Ep的幅度。
As one of the most important dynamic processes in the middle and upper atmosphere, gravity waves (GWs) play a key role in determining the global atmospheric circulation. Gravity wave potential energy (GW Ep) is an important parameter that characterizes GW intensity, so understanding its global distribution is necessary. In this paper, a deep learning algorithm (DeepLab V3+) is used to estimate the stratospheric GW Ep. The deep learning model inputs are ERA5 reanalysis datasets and GMTED2010 terrain data. The output is the estimated GW Ep averaged over 2030 km from 60°S60°N. The GW Ep averaged over 20~30 km calculated by COSMIC radio occultation (RO) data is used as the measured value corresponding to the model output. The results showed that (1) this method can effectively estimate the zonal trend of GW Ep. However, the errors between the estimated and measured value of Ep are larger in low-latitude regions than in mid-latitude regions. The large number of convolution operations used in the deep learning model may be the main reason. Additionally, the measured Ep has errors associated with interpolation to the grid, the error tends to be amplified in low-latitude regions because the GW Ep is larger and the RO data are relatively sparse, which affects the training accuracy. (2) The estimated Ep shows seasonal variations, which are stronger in the winter hemisphere and weaker in the summer hemisphere. (3) The effect of quasi-biennial oscillation (QBO) can be clearly observed in the monthly variation in the estimated GW Ep, and its QBO amplitude may be less than that of the measured Ep.
登录
查看更多内容
宇宙测量揭示的全球平流层重力波的时空变化及其平流层突然变暖期间的活动
影响因子：
5.8
作者：
Xu Xiaohua;Yu Daocheng;Luo Jia
通讯作者：
Luo Jia
DOI：
10.1007/s11430-011-4303-1
发表时间：
2012-04
期刊：
Science China Earth Sciences
影响因子：
--
作者：
Dan Chen;Ze Chen;Daren Lü
通讯作者：
Dan Chen;Ze Chen;Daren Lü
DOI：
10.1016/j.jastp.2016.01.014
发表时间：
2016-03
影响因子：
1.9
作者：
R. Kramer;S. Wüst;M. Bittner
通讯作者：
R. Kramer;S. Wüst;M. Bittner
DOI：
10.3390/rs11212463
发表时间：
2019-10
期刊：
Remote. Sens.
影响因子：
--
作者：
A. Moraux;S. Dewitte;Bruno Cornelis;A. Munteanu
通讯作者：
A. Moraux;S. Dewitte;Bruno Cornelis;A. Munteanu
DOI：
10.1007/s11430-016-0065-6
发表时间：
2016
期刊：
Science China Earth Sciences
影响因子：
--
作者：
X. Zeng;X. Xue;X. Dou;Chen Liang;Mingjiao Jia
通讯作者：
X. Zeng;X. Xue;X. Dou;Chen Liang;Mingjiao Jia