基于人口调查大数据和环境监测的机器学习预测中国 22 个城市的室内 PM2.5

IF 6.2 2区环境科学与生态学 Q1 ENVIRONMENTAL SCIENCES

Ecotoxicology and Environmental Safety Pub Date : 2024-11-05 DOI:10.1016/j.ecoenv.2024.117285

Yanjun Du , Yingying Zhang , Yaoling Li , Qiang Huang , Yanwen Wang , Qing Wang , Runmei Ma , Qinghua Sun , Qin Wang , Tiantian Li

{"title":"基于人口调查大数据和环境监测的机器学习预测中国 22 个城市的室内 PM2.5","authors":"Yanjun Du , Yingying Zhang , Yaoling Li , Qiang Huang , Yanwen Wang , Qing Wang , Runmei Ma , Qinghua Sun , Qin Wang , Tiantian Li","doi":"10.1016/j.ecoenv.2024.117285","DOIUrl":null,"url":null,"abstract":"<div><div>Many studies have confirmed that PM<sub>2.5</sub> exposure can cause a variety of diseases. Because people spend most of their time indoors, exposure to PM<sub>2.5</sub> in indoor environments is critical to population health. Large-population, long-term, continuous, and accurate indoor PM<sub>2.5</sub> data are important but scarce because of the difficulties in monitoring the indoor air quality on a large scale. Model simulation provides a new research direction. In this study, an advanced machine learning model was constructed using environmental health big data to predict the daily indoor PM<sub>2.5</sub> concentration data in 22 typical air pollution cities in China from 2013 to 2017. The test R<sup>2</sup> value of this model reached as high as 0.89, and the RMSE of the model was 9.13. The predicted annual indoor PM<sub>2.5</sub> concentrations of the cities ranged from 54.6 μg/m<sup>3</sup> to 82.7 μg/m<sup>3</sup>, and showed a decreasing trend year by year. The pollution level exceeds the recommended AQG level of PM<sub>2.5</sub> and has potential impact on human health. The results could take a breakthrough in obtaining accurate big data of indoor PM<sub>2.5</sub> and contribute to research on the indoor air quality and human health in China.</div></div><div><h3>Synopsis</h3><div>This study established a machine learning model and predicted indoor PM<sub>2.5</sub> big data, which could support the research of indoor PM<sub>2.5</sub> and health.</div></div>","PeriodicalId":303,"journal":{"name":"Ecotoxicology and Environmental Safety","volume":"287 ","pages":"Article 117285"},"PeriodicalIF":6.2000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Big data from population surveys and environmental monitoring-based machine learning predictions of indoor PM2.5 in 22 cities in China\",\"authors\":\"Yanjun Du , Yingying Zhang , Yaoling Li , Qiang Huang , Yanwen Wang , Qing Wang , Runmei Ma , Qinghua Sun , Qin Wang , Tiantian Li\",\"doi\":\"10.1016/j.ecoenv.2024.117285\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Many studies have confirmed that PM<sub>2.5</sub> exposure can cause a variety of diseases. Because people spend most of their time indoors, exposure to PM<sub>2.5</sub> in indoor environments is critical to population health. Large-population, long-term, continuous, and accurate indoor PM<sub>2.5</sub> data are important but scarce because of the difficulties in monitoring the indoor air quality on a large scale. Model simulation provides a new research direction. In this study, an advanced machine learning model was constructed using environmental health big data to predict the daily indoor PM<sub>2.5</sub> concentration data in 22 typical air pollution cities in China from 2013 to 2017. The test R<sup>2</sup> value of this model reached as high as 0.89, and the RMSE of the model was 9.13. The predicted annual indoor PM<sub>2.5</sub> concentrations of the cities ranged from 54.6 μg/m<sup>3</sup> to 82.7 μg/m<sup>3</sup>, and showed a decreasing trend year by year. The pollution level exceeds the recommended AQG level of PM<sub>2.5</sub> and has potential impact on human health. The results could take a breakthrough in obtaining accurate big data of indoor PM<sub>2.5</sub> and contribute to research on the indoor air quality and human health in China.</div></div><div><h3>Synopsis</h3><div>This study established a machine learning model and predicted indoor PM<sub>2.5</sub> big data, which could support the research of indoor PM<sub>2.5</sub> and health.</div></div>\",\"PeriodicalId\":303,\"journal\":{\"name\":\"Ecotoxicology and Environmental Safety\",\"volume\":\"287 \",\"pages\":\"Article 117285\"},\"PeriodicalIF\":6.2000,\"publicationDate\":\"2024-11-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ecotoxicology and Environmental Safety\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0147651324013617\",\"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":"Ecotoxicology and Environmental Safety","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0147651324013617","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

许多研究证实，接触 PM2.5 可导致多种疾病。由于人们大部分时间都在室内度过，因此室内环境中的 PM2.5 暴露对人群健康至关重要。大范围、长期、连续和准确的室内 PM2.5 数据非常重要，但由于难以大规模监测室内空气质量，这些数据非常稀缺。模型模拟提供了一个新的研究方向。本研究利用环境健康大数据构建了先进的机器学习模型，对中国22个典型空气污染城市2013年至2017年每日室内PM2.5浓度数据进行预测。该模型的检验 R2 值高达 0.89，模型均方根误差为 9.13。预测的城市室内 PM2.5 年浓度在 54.6 μg/m3 至 82.7 μg/m3 之间，并呈逐年下降趋势。该污染水平超过了空气质量组推荐的 PM2.5 水平，对人体健康有潜在影响。本研究建立了机器学习模型，对室内 PM2.5 大数据进行了预测，为室内 PM2.5 与健康的研究提供了支持。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Big data from population surveys and environmental monitoring-based machine learning predictions of indoor PM2.5 in 22 cities in China

Many studies have confirmed that PM_2.5 exposure can cause a variety of diseases. Because people spend most of their time indoors, exposure to PM_2.5 in indoor environments is critical to population health. Large-population, long-term, continuous, and accurate indoor PM_2.5 data are important but scarce because of the difficulties in monitoring the indoor air quality on a large scale. Model simulation provides a new research direction. In this study, an advanced machine learning model was constructed using environmental health big data to predict the daily indoor PM_2.5 concentration data in 22 typical air pollution cities in China from 2013 to 2017. The test R² value of this model reached as high as 0.89, and the RMSE of the model was 9.13. The predicted annual indoor PM_2.5 concentrations of the cities ranged from 54.6 μg/m³ to 82.7 μg/m³, and showed a decreasing trend year by year. The pollution level exceeds the recommended AQG level of PM_2.5 and has potential impact on human health. The results could take a breakthrough in obtaining accurate big data of indoor PM_2.5 and contribute to research on the indoor air quality and human health in China.

Synopsis

This study established a machine learning model and predicted indoor PM_2.5 big data, which could support the research of indoor PM_2.5 and health.

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

Ecotoxicology and Environmental Safety 环境科学-毒理学

CiteScore

12.10

自引率

5.90%

发文量

1234

审稿时长

88 days

期刊介绍： Ecotoxicology and Environmental Safety is a multi-disciplinary journal that focuses on understanding the exposure and effects of environmental contamination on organisms including human health. The scope of the journal covers three main themes. The topics within these themes, indicated below, include (but are not limited to) the following: Ecotoxicology、Environmental Chemistry、Environmental Safety etc.