Simulation model of Reactive Nitrogen Species in an Urban Atmosphere using a Deep Neural Network: RNDv1.0

IF 4 3区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

Geoscientific Model Development Pub Date : 2023-09-13 DOI:10.5194/gmd-16-5251-2023

Junsu Gil, Meehye Lee, Jeonghwan Kim, Gangwoong Lee, Joonyoung Ahn, Cheol-Hee Kim

引用次数: 0

Abstract

Abstract. Nitrous acid (HONO) plays an important role in the formation of ozone and fine aerosols in the urban atmosphere. In this study, a new simulation approach is presented to calculate the HONO mixing ratios using a deep neural technique based on measured variables. The Reactive Nitrogen Species using a Deep Neural Network (RND) simulation is implemented in Python. The first version of RND (RNDv1.0) is trained, validated, and tested with HONO measurement data obtained in Seoul, South Korea, from 2016 to 2021. RNDv1.0 is constructed using k-fold cross validation and evaluated with index of agreement, correlation coefficient, root mean squared error, and mean absolute error. The results show that RNDv1.0 adequately represents the main characteristics of the measured HONO, and it is thus proposed as a supplementary model for calculating the HONO mixing ratio in a polluted urban environment.

查看原文本刊更多论文

基于深度神经网络的城市大气活性氮模拟模型:RNDv1.0

摘要亚硝酸(HONO)在城市大气中臭氧和细颗粒物的形成中起着重要作用。在本研究中，提出了一种新的模拟方法，利用基于测量变量的深度神经技术计算HONO混合比。使用深度神经网络(RND)模拟的活性氮物种是在Python中实现的。第一版RND (RNDv1.0)在2016年至2021年期间在韩国首尔使用HONO测量数据进行了训练、验证和测试。RNDv1.0采用k-fold交叉验证构建，并采用一致性指数、相关系数、均方根误差和平均绝对误差进行评价。结果表明，RNDv1.0能较好地反映实测HONO的主要特征，可作为计算城市污染环境下HONO混合比的补充模型。

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

Geoscientific Model Development GEOSCIENCES, MULTIDISCIPLINARY-

CiteScore

8.60

自引率

9.80%

发文量

352

审稿时长

6-12 weeks

期刊介绍： Geoscientific Model Development (GMD) is an international scientific journal dedicated to the publication and public discussion of the description, development, and evaluation of numerical models of the Earth system and its components. The following manuscript types can be considered for peer-reviewed publication: * geoscientific model descriptions, from statistical models to box models to GCMs; * development and technical papers, describing developments such as new parameterizations or technical aspects of running models such as the reproducibility of results; * new methods for assessment of models, including work on developing new metrics for assessing model performance and novel ways of comparing model results with observational data; * papers describing new standard experiments for assessing model performance or novel ways of comparing model results with observational data; * model experiment descriptions, including experimental details and project protocols; * full evaluations of previously published models.