利用数据挖掘辅助的机器和深度学习,从气象学(2015年至2020年)进行当地综合空气质量预测

David A. Wood
{"title":"利用数据挖掘辅助的机器和深度学习,从气象学(2015年至2020年)进行当地综合空气质量预测","authors":"David A. Wood","doi":"10.1016/j.samod.2021.100002","DOIUrl":null,"url":null,"abstract":"<div><p>Overall air quality local indices can usefully be established by combining normalised values of common individual pollutant values. This reveals distinctive seasonal trends that are strongly influenced by local meteorological conditions. A newly compiled dataset for 2015 to 2020 covering Dallas County (USA), combining six pollutants into a combined local area benchmark (CLAB), is assessed in terms of eleven meteorological variables. It is possible to distinguish the effects of lock-down induced impacts in the CLAB index and some of its component pollutants during 2020. Nine machine learning and three deep learning algorithms are compared in their abilities to predict CLAB from the meteorological variables on supervised and unseen bases. Prediction results for 2019 and 2020 are distinctive for annual and quarterly timeframes. In-depth prediction outlier analysis using a transparent data-matching algorithm provides insight to the few data records for which CLAB is not accurately predicted from ground-level meteorological data.</p></div>","PeriodicalId":101193,"journal":{"name":"Sustainability Analytics and Modeling","volume":"2 ","pages":"Article 100002"},"PeriodicalIF":0.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667259621000023/pdfft?md5=37b03ebad1223de314e4249cea1bb045&pid=1-s2.0-S2667259621000023-main.pdf","citationCount":"7","resultStr":"{\"title\":\"Local integrated air quality predictions from meteorology (2015 to 2020) with machine and deep learning assisted by data mining\",\"authors\":\"David A. Wood\",\"doi\":\"10.1016/j.samod.2021.100002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Overall air quality local indices can usefully be established by combining normalised values of common individual pollutant values. This reveals distinctive seasonal trends that are strongly influenced by local meteorological conditions. A newly compiled dataset for 2015 to 2020 covering Dallas County (USA), combining six pollutants into a combined local area benchmark (CLAB), is assessed in terms of eleven meteorological variables. It is possible to distinguish the effects of lock-down induced impacts in the CLAB index and some of its component pollutants during 2020. Nine machine learning and three deep learning algorithms are compared in their abilities to predict CLAB from the meteorological variables on supervised and unseen bases. Prediction results for 2019 and 2020 are distinctive for annual and quarterly timeframes. In-depth prediction outlier analysis using a transparent data-matching algorithm provides insight to the few data records for which CLAB is not accurately predicted from ground-level meteorological data.</p></div>\",\"PeriodicalId\":101193,\"journal\":{\"name\":\"Sustainability Analytics and Modeling\",\"volume\":\"2 \",\"pages\":\"Article 100002\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2667259621000023/pdfft?md5=37b03ebad1223de314e4249cea1bb045&pid=1-s2.0-S2667259621000023-main.pdf\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Sustainability Analytics and Modeling\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2667259621000023\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sustainability Analytics and Modeling","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667259621000023","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

摘要

综合个别常见污染物的标准化数值,可有效地建立整体本地空气质素指数。这揭示了受当地气象条件强烈影响的独特季节性趋势。新编制的2015年至2020年的数据集涵盖了达拉斯县(美国),将六种污染物结合到一个综合的局部基准(CLAB)中,根据11个气象变量进行评估。在2020年期间,CLAB指数及其部分成分污染物的锁定效应是可以区分的。比较了九种机器学习算法和三种深度学习算法在监督和看不见的基础上从气象变量预测CLAB的能力。2019年和2020年的预测结果在年度和季度时间框架上是不同的。使用透明的数据匹配算法进行深入的预测离群值分析,可以深入了解地面气象数据无法准确预测CLAB的少数数据记录。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Local integrated air quality predictions from meteorology (2015 to 2020) with machine and deep learning assisted by data mining

Overall air quality local indices can usefully be established by combining normalised values of common individual pollutant values. This reveals distinctive seasonal trends that are strongly influenced by local meteorological conditions. A newly compiled dataset for 2015 to 2020 covering Dallas County (USA), combining six pollutants into a combined local area benchmark (CLAB), is assessed in terms of eleven meteorological variables. It is possible to distinguish the effects of lock-down induced impacts in the CLAB index and some of its component pollutants during 2020. Nine machine learning and three deep learning algorithms are compared in their abilities to predict CLAB from the meteorological variables on supervised and unseen bases. Prediction results for 2019 and 2020 are distinctive for annual and quarterly timeframes. In-depth prediction outlier analysis using a transparent data-matching algorithm provides insight to the few data records for which CLAB is not accurately predicted from ground-level meteorological data.

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
自引率
0.00%
发文量
0
×
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