利用卫星数据、地面监测仪和机器学习对西非每日PM2.5进行20年高时空分辨率估算

Daniel M. Westervelt*, Joe Adabouk Amooli and Abhishek Anand, 
{"title":"利用卫星数据、地面监测仪和机器学习对西非每日PM2.5进行20年高时空分辨率估算","authors":"Daniel M. Westervelt*,&nbsp;Joe Adabouk Amooli and Abhishek Anand,&nbsp;","doi":"10.1021/acsestair.4c00366","DOIUrl":null,"url":null,"abstract":"<p >Estimates of air pollution mortality in sub-Saharan Africa are limited by a lack of observations of fine particulate matter (PM<sub>2.5</sub>). Satellite data represents a promising solution with near-complete spatial coverage and high temporal coverage, but representativeness of surface conditions is a critical issue. Here we estimate surface PM<sub>2.5</sub> concentrations over West Africa at a daily, 1 km<sup>2</sup> spatiotemporal resolution based on satellite-derived and reanalysis inputs trained against surface PM<sub>2.5</sub> observations using several machine learning algorithms. Among machine learning models tested, Extreme Gradient Boosting (XGBoost) demonstrated the highest accuracy, with a 0.91 <i>r</i><sup>2</sup>, mean absolute error of 9.1 μg m<sup>–3</sup>, and a CvMAE of 0.1, indicating about a 10% error across all sites on aggregate. Seasonal and annual PM<sub>2.5</sub> patterns were well captured, revealing severe air quality challenges via near-universal exceedances of World Health Organization air quality guidelines and interim targets. The data set’s long-term perspective (2005–2024) highlights worsening air quality trends in both rural and urban areas. Our findings provide actionable data to support air quality management and policy, public health, and environmental justice initiatives in a critically underserved region of the world.</p>","PeriodicalId":100014,"journal":{"name":"ACS ES&T Air","volume":"2 8","pages":"1468–1477"},"PeriodicalIF":0.0000,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Twenty Years of High Spatiotemporal Resolution Estimates of Daily PM2.5 in West Africa Using Satellite Data, Surface Monitors, and Machine Learning\",\"authors\":\"Daniel M. Westervelt*,&nbsp;Joe Adabouk Amooli and Abhishek Anand,&nbsp;\",\"doi\":\"10.1021/acsestair.4c00366\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >Estimates of air pollution mortality in sub-Saharan Africa are limited by a lack of observations of fine particulate matter (PM<sub>2.5</sub>). Satellite data represents a promising solution with near-complete spatial coverage and high temporal coverage, but representativeness of surface conditions is a critical issue. Here we estimate surface PM<sub>2.5</sub> concentrations over West Africa at a daily, 1 km<sup>2</sup> spatiotemporal resolution based on satellite-derived and reanalysis inputs trained against surface PM<sub>2.5</sub> observations using several machine learning algorithms. Among machine learning models tested, Extreme Gradient Boosting (XGBoost) demonstrated the highest accuracy, with a 0.91 <i>r</i><sup>2</sup>, mean absolute error of 9.1 μg m<sup>–3</sup>, and a CvMAE of 0.1, indicating about a 10% error across all sites on aggregate. Seasonal and annual PM<sub>2.5</sub> patterns were well captured, revealing severe air quality challenges via near-universal exceedances of World Health Organization air quality guidelines and interim targets. The data set’s long-term perspective (2005–2024) highlights worsening air quality trends in both rural and urban areas. Our findings provide actionable data to support air quality management and policy, public health, and environmental justice initiatives in a critically underserved region of the world.</p>\",\"PeriodicalId\":100014,\"journal\":{\"name\":\"ACS ES&T Air\",\"volume\":\"2 8\",\"pages\":\"1468–1477\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-07-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS ES&T Air\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://pubs.acs.org/doi/10.1021/acsestair.4c00366\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS ES&T Air","FirstCategoryId":"1085","ListUrlMain":"https://pubs.acs.org/doi/10.1021/acsestair.4c00366","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

由于缺乏对细颗粒物(PM2.5)的观测,对撒哈拉以南非洲地区空气污染死亡率的估计受到限制。卫星数据具有接近完全的空间覆盖和高时间覆盖,是一种很有希望的解决方案,但地表条件的代表性是一个关键问题。在这里,我们基于卫星衍生和再分析输入,使用几种机器学习算法对表面PM2.5观测数据进行训练,以每天1平方公里的时空分辨率估计西非的表面PM2.5浓度。在测试的机器学习模型中,Extreme Gradient Boosting (XGBoost)表现出最高的准确性,r2为0.91,平均绝对误差为9.1 μg - 3, CvMAE为0.1,表明所有站点的总体误差约为10%。季节性和年度PM2.5模式被很好地捕捉到,通过几乎普遍超出世界卫生组织空气质量准则和中期目标,揭示了严重的空气质量挑战。该数据集的长期前景(2005-2024年)强调了农村和城市地区空气质量恶化的趋势。我们的研究结果提供了可操作的数据,以支持世界上服务严重不足地区的空气质量管理和政策、公共卫生和环境司法倡议。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Twenty Years of High Spatiotemporal Resolution Estimates of Daily PM2.5 in West Africa Using Satellite Data, Surface Monitors, and Machine Learning

Twenty Years of High Spatiotemporal Resolution Estimates of Daily PM2.5 in West Africa Using Satellite Data, Surface Monitors, and Machine Learning

Estimates of air pollution mortality in sub-Saharan Africa are limited by a lack of observations of fine particulate matter (PM2.5). Satellite data represents a promising solution with near-complete spatial coverage and high temporal coverage, but representativeness of surface conditions is a critical issue. Here we estimate surface PM2.5 concentrations over West Africa at a daily, 1 km2 spatiotemporal resolution based on satellite-derived and reanalysis inputs trained against surface PM2.5 observations using several machine learning algorithms. Among machine learning models tested, Extreme Gradient Boosting (XGBoost) demonstrated the highest accuracy, with a 0.91 r2, mean absolute error of 9.1 μg m–3, and a CvMAE of 0.1, indicating about a 10% error across all sites on aggregate. Seasonal and annual PM2.5 patterns were well captured, revealing severe air quality challenges via near-universal exceedances of World Health Organization air quality guidelines and interim targets. The data set’s long-term perspective (2005–2024) highlights worsening air quality trends in both rural and urban areas. Our findings provide actionable data to support air quality management and policy, public health, and environmental justice initiatives in a critically underserved region of the world.

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:604180095
Book学术官方微信