开发基于机器学习的自动光解率预测系统

IF 5.9 2区 环境科学与生态学 Q1 ENVIRONMENTAL SCIENCES Journal of Environmental Sciences-china Pub Date : 2024-04-05 DOI:10.1016/j.jes.2024.03.051
Weijun Pan , Sunling Gong , Huabing Ke , Xin Li , Duohong Chen , Cheng Huang , Danlin Song
{"title":"开发基于机器学习的自动光解率预测系统","authors":"Weijun Pan ,&nbsp;Sunling Gong ,&nbsp;Huabing Ke ,&nbsp;Xin Li ,&nbsp;Duohong Chen ,&nbsp;Cheng Huang ,&nbsp;Danlin Song","doi":"10.1016/j.jes.2024.03.051","DOIUrl":null,"url":null,"abstract":"<div><p>Based on observed meteorological elements, photolysis rates (J-values) and pollutant concentrations, an automated J-values predicting system by machine learning (J-ML) has been developed to reproduce and predict the J-values of O<sup>1</sup>D, NO<sub>2</sub>, HONO, H<sub>2</sub>O<sub>2</sub>, HCHO, and NO<sub>3</sub>, which are the crucial values for the prediction of the atmospheric oxidation capacity (AOC) and secondary pollutant concentrations such as ozone (O<sub>3</sub>), secondary organic aerosols (SOA). The J-ML can self-select the optimal “Model + Hyperparameters” without human interference. The evaluated results showed that the J-ML had a good performance to reproduce the J-values where most of the correlation (<em>R</em>) coefficients exceed 0.93 and the accuracy (<em>P</em>) values are in the range of 0.68-0.83, comparing with the J-values from observations and from the tropospheric ultraviolet and visible (TUV) radiation model in Beijing, Chengdu, Guangzhou and Shanghai. The hourly prediction was also well performed with R from 0.78 to 0.81 for next 3-days and from 0.69 to 0.71 for next 7-days, respectively. Compared with O<sub>3</sub> concentrations by using J-values from the TUV model, an emission-driven observation-based model (e-OBM) by using the J-values from the J-ML showed a 4%-12% increase in R and 4%-30% decrease in ME, indicating that the J-ML could be used as an excellent supplement to traditional numerical models. The feature importance analysis concluded that the key influential parameter was the surface solar downwards radiation for all J-values, and the other dominant factors for all J-values were 2-m mean temperature, O<sub>3</sub>, total cloud cover, boundary layer height, relative humidity and surface pressure.</p></div>","PeriodicalId":15788,"journal":{"name":"Journal of Environmental Sciences-china","volume":null,"pages":null},"PeriodicalIF":5.9000,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Development of an automated photolysis rates prediction system based on machine learning\",\"authors\":\"Weijun Pan ,&nbsp;Sunling Gong ,&nbsp;Huabing Ke ,&nbsp;Xin Li ,&nbsp;Duohong Chen ,&nbsp;Cheng Huang ,&nbsp;Danlin Song\",\"doi\":\"10.1016/j.jes.2024.03.051\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Based on observed meteorological elements, photolysis rates (J-values) and pollutant concentrations, an automated J-values predicting system by machine learning (J-ML) has been developed to reproduce and predict the J-values of O<sup>1</sup>D, NO<sub>2</sub>, HONO, H<sub>2</sub>O<sub>2</sub>, HCHO, and NO<sub>3</sub>, which are the crucial values for the prediction of the atmospheric oxidation capacity (AOC) and secondary pollutant concentrations such as ozone (O<sub>3</sub>), secondary organic aerosols (SOA). The J-ML can self-select the optimal “Model + Hyperparameters” without human interference. The evaluated results showed that the J-ML had a good performance to reproduce the J-values where most of the correlation (<em>R</em>) coefficients exceed 0.93 and the accuracy (<em>P</em>) values are in the range of 0.68-0.83, comparing with the J-values from observations and from the tropospheric ultraviolet and visible (TUV) radiation model in Beijing, Chengdu, Guangzhou and Shanghai. The hourly prediction was also well performed with R from 0.78 to 0.81 for next 3-days and from 0.69 to 0.71 for next 7-days, respectively. Compared with O<sub>3</sub> concentrations by using J-values from the TUV model, an emission-driven observation-based model (e-OBM) by using the J-values from the J-ML showed a 4%-12% increase in R and 4%-30% decrease in ME, indicating that the J-ML could be used as an excellent supplement to traditional numerical models. The feature importance analysis concluded that the key influential parameter was the surface solar downwards radiation for all J-values, and the other dominant factors for all J-values were 2-m mean temperature, O<sub>3</sub>, total cloud cover, boundary layer height, relative humidity and surface pressure.</p></div>\",\"PeriodicalId\":15788,\"journal\":{\"name\":\"Journal of Environmental Sciences-china\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.9000,\"publicationDate\":\"2024-04-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Environmental Sciences-china\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1001074224001748\",\"RegionNum\":2,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Environmental Sciences-china","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1001074224001748","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

根据观测到的气象要素、光解率(J 值)和污染物浓度,开发了一种机器学习 J 值自动预测系统(J-ML),用于重现和预测 O1D、NO2、HONO、H2O2、HCHO 和 NO3 的 J 值,这些值是预测大气氧化能力(AOC)和臭氧(O3)、二次有机气溶胶(SOA)等二次污染物浓度的关键值。J-ML 可自行选择最佳 "模型+超参数",无需人工干预。评估结果表明,与北京、成都、广州和上海的观测数据以及对流层紫外线和可见光(TUV)辐射模型得出的 J 值相比,J-ML 在再现 J 值方面表现良好,大部分相关系数(R)超过 0.93,准确度(P)在 0.68-0.83 之间。未来 3 天的 R 值为 0.78 至 0.81,未来 7 天的 R 值为 0.69 至 0.71。与使用 TUV 模式的 J 值预测 O3 浓度相比,使用 J-ML 的 J 值建立的基于观测的排放驱动模式(e-OBM)的 R 值提高了 4%-12%,ME 值降低了 4%-30%,表明 J-ML 可以作为传统数值模式的良好补充。特征重要性分析结果表明,对所有 J 值的关键影响参数是地表太阳向下辐射,对所有 J 值的其他主导因素是 2 米平均温度、O3、总云量、边界层高度、相对湿度和地面气压。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Development of an automated photolysis rates prediction system based on machine learning

Based on observed meteorological elements, photolysis rates (J-values) and pollutant concentrations, an automated J-values predicting system by machine learning (J-ML) has been developed to reproduce and predict the J-values of O1D, NO2, HONO, H2O2, HCHO, and NO3, which are the crucial values for the prediction of the atmospheric oxidation capacity (AOC) and secondary pollutant concentrations such as ozone (O3), secondary organic aerosols (SOA). The J-ML can self-select the optimal “Model + Hyperparameters” without human interference. The evaluated results showed that the J-ML had a good performance to reproduce the J-values where most of the correlation (R) coefficients exceed 0.93 and the accuracy (P) values are in the range of 0.68-0.83, comparing with the J-values from observations and from the tropospheric ultraviolet and visible (TUV) radiation model in Beijing, Chengdu, Guangzhou and Shanghai. The hourly prediction was also well performed with R from 0.78 to 0.81 for next 3-days and from 0.69 to 0.71 for next 7-days, respectively. Compared with O3 concentrations by using J-values from the TUV model, an emission-driven observation-based model (e-OBM) by using the J-values from the J-ML showed a 4%-12% increase in R and 4%-30% decrease in ME, indicating that the J-ML could be used as an excellent supplement to traditional numerical models. The feature importance analysis concluded that the key influential parameter was the surface solar downwards radiation for all J-values, and the other dominant factors for all J-values were 2-m mean temperature, O3, total cloud cover, boundary layer height, relative humidity and surface pressure.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Environmental Sciences-china
Journal of Environmental Sciences-china 环境科学-环境科学
CiteScore
13.70
自引率
0.00%
发文量
6354
审稿时长
2.6 months
期刊介绍: The Journal of Environmental Sciences is an international journal started in 1989. The journal is devoted to publish original, peer-reviewed research papers on main aspects of environmental sciences, such as environmental chemistry, environmental biology, ecology, geosciences and environmental physics. Appropriate subjects include basic and applied research on atmospheric, terrestrial and aquatic environments, pollution control and abatement technology, conservation of natural resources, environmental health and toxicology. Announcements of international environmental science meetings and other recent information are also included.
期刊最新文献
Hydrothermal temperature-dependent compositions and copper complexing behaviors of hydrochar-derived dissolved organic matter: Insights from FT-ICR MS and multi-spectroscopic analysis Antibiotic resistance partitioning during on-farm manure separation and high temperature rotary drum composting Carbon dioxide reduction through mineral carbonation by steel slag Ultra-small cesium silver bismuth bromide quantum dots fabricated by modified hot-injection method for highly efficient degradation of contaminants in organic solvent Cement-mortar lining failure and metal release caused by electrochemical corrosion of ductile iron pipes in drinking water distribution systems
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1