A Neural-network-based Alternative Scheme to Include Nonhydrostatic Processes in an Atmospheric Dynamical Core

IF 6.5 2区 地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES
Yang Xia, Bin Wang, Lijuan Li, Li Liu, Jianghao Li, Li Dong, Shiming Xu, Yiyuan Li, Wenwen Xia, Wenyu Huang, Juanjuan Liu, Yong Wang, Hongbo Liu, Ye Pu, Yujun He, Kun Xia
{"title":"A Neural-network-based Alternative Scheme to Include Nonhydrostatic Processes in an Atmospheric Dynamical Core","authors":"Yang Xia, Bin Wang, Lijuan Li, Li Liu, Jianghao Li, Li Dong, Shiming Xu, Yiyuan Li, Wenwen Xia, Wenyu Huang, Juanjuan Liu, Yong Wang, Hongbo Liu, Ye Pu, Yujun He, Kun Xia","doi":"10.1007/s00376-023-3119-1","DOIUrl":null,"url":null,"abstract":"<p>Here, a nonhydrostatic alternative scheme (NAS) is proposed for the grey zone where the nonhydrostatic impact on the atmosphere is evident but not large enough to justify the necessity to include an implicit nonhydrostatic solver in an atmospheric dynamical core. The NAS is designed to replace this solver, which can be incorporated into any hydrostatic models so that existing well-developed hydrostatic models can effectively serve for a longer time. Recent advances in machine learning (ML) provide a potential tool for capturing the main complicated nonlinear-nonhydrostatic relationship. In this study, an ML approach called a neural network (NN) was adopted to select leading input features and develop the NAS. The NNs were trained and evaluated with 12-day simulation results of dry baroclinic-wave tests by the Weather Research and Forecasting (WRF) model. The forward time difference of the nonhydrostatic tendency was used as the target variable, and the five selected features were the nonhydrostatic tendency at the last time step, and four hydrostatic variables at the current step including geopotential height, pressure in two different forms, and potential temperature, respectively. Finally, a practical NAS was developed with these features and trained layer by layer at a 20-km horizontal resolution, which can accurately reproduce the temporal variation and vertical distribution of the nonhydrostatic tendency. Corrected by the NN-based NAS, the improved hydrostatic solver at different horizontal resolutions can run stably for at least one month and effectively reduce most of the nonhydrostatic errors in terms of system bias, anomaly root-mean-square error, and the error of the wave spatial pattern, which proves the feasibility and superiority of this scheme.</p>","PeriodicalId":7249,"journal":{"name":"Advances in Atmospheric Sciences","volume":"31 1","pages":""},"PeriodicalIF":6.5000,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Atmospheric Sciences","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1007/s00376-023-3119-1","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Here, a nonhydrostatic alternative scheme (NAS) is proposed for the grey zone where the nonhydrostatic impact on the atmosphere is evident but not large enough to justify the necessity to include an implicit nonhydrostatic solver in an atmospheric dynamical core. The NAS is designed to replace this solver, which can be incorporated into any hydrostatic models so that existing well-developed hydrostatic models can effectively serve for a longer time. Recent advances in machine learning (ML) provide a potential tool for capturing the main complicated nonlinear-nonhydrostatic relationship. In this study, an ML approach called a neural network (NN) was adopted to select leading input features and develop the NAS. The NNs were trained and evaluated with 12-day simulation results of dry baroclinic-wave tests by the Weather Research and Forecasting (WRF) model. The forward time difference of the nonhydrostatic tendency was used as the target variable, and the five selected features were the nonhydrostatic tendency at the last time step, and four hydrostatic variables at the current step including geopotential height, pressure in two different forms, and potential temperature, respectively. Finally, a practical NAS was developed with these features and trained layer by layer at a 20-km horizontal resolution, which can accurately reproduce the temporal variation and vertical distribution of the nonhydrostatic tendency. Corrected by the NN-based NAS, the improved hydrostatic solver at different horizontal resolutions can run stably for at least one month and effectively reduce most of the nonhydrostatic errors in terms of system bias, anomaly root-mean-square error, and the error of the wave spatial pattern, which proves the feasibility and superiority of this scheme.

基于神经网络的替代方案,将非静水过程纳入大气动力学核心
这里提出了一种非静力学替代方案(NAS),用于非静力学对大气的影响明显但又不足以证明有必要在大气动力学核心中包含隐式非静力学求解器的灰色区域。NAS 的设计目的是取代这种求解器,它可以被纳入任何静力学模型,从而使现有完善的静力学模型可以有效地服务更长的时间。机器学习(ML)的最新进展为捕捉主要的复杂非线性-非静力学关系提供了一个潜在工具。本研究采用了一种称为神经网络(NN)的 ML 方法来选择主要输入特征并开发 NAS。通过天气研究和预报(WRF)模型对干气压波测试的 12 天模拟结果对神经网络进行了训练和评估。以非静水趋向的前向时差作为目标变量,所选的五个特征分别是上一时间步的非静水趋向和当前时间步的四个静水变量,包括位势高度、两种不同形式的压力和位势温度。最后,利用这些特征开发了实用的 NAS,并以 20 千米的水平分辨率进行逐层训练,该 NAS 可以准确地再现非静水倾向的时间变化和垂直分布。经基于 NN 的 NAS 修正后,改进后的不同水平分辨率的静力学求解器可稳定运行至少一个月,并在系统偏差、异常均方根误差和波浪空间模式误差等方面有效减小了大部分非静力学误差,证明了该方案的可行性和优越性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Advances in Atmospheric Sciences
Advances in Atmospheric Sciences 地学-气象与大气科学
CiteScore
9.30
自引率
5.20%
发文量
154
审稿时长
6 months
期刊介绍: Advances in Atmospheric Sciences, launched in 1984, aims to rapidly publish original scientific papers on the dynamics, physics and chemistry of the atmosphere and ocean. It covers the latest achievements and developments in the atmospheric sciences, including marine meteorology and meteorology-associated geophysics, as well as the theoretical and practical aspects of these disciplines. Papers on weather systems, numerical weather prediction, climate dynamics and variability, satellite meteorology, remote sensing, air chemistry and the boundary layer, clouds and weather modification, can be found in the journal. Papers describing the application of new mathematics or new instruments are also collected here.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信