S. Soleimani-Alyar, M. Soleimani-Alyar, R. Yarahmadi, P. Beyk-Mohammadloo, P. Fazeli
{"title":"The study of indoor particulate matter in office buildings based on artificial intelligence","authors":"S. Soleimani-Alyar, M. Soleimani-Alyar, R. Yarahmadi, P. Beyk-Mohammadloo, P. Fazeli","doi":"10.1007/s13762-024-06277-1","DOIUrl":null,"url":null,"abstract":"<div><p>The necessity of supplying proper indoor air quality in workplaces to provide the principles of a healthy and productive labor force and avoid negative outcomes is a known fact. This study assessed particulate matter (PM) concentrations in office buildings of governmental organizations across five regions in Tehran over four seasons (2018–2019) to model annual indoor PM patterns using machine learning. PM concentrations, including PM<sub>1</sub>, PM<sub>2.5</sub>, PM<sub>10</sub>, and Total Particulate Matter (TPM), were categorized using ensemble modeling techniques such as Linear Regression, Random Forest, Gradient Boosting, XGBoost, CatBoost, Support Vector Regression, and K-nearest neighbors. Key air quality parameters measured were CO2 (784 ppm), SO2 (0.114 μg/m<sup>3</sup>), PM<sub>2.5</sub> (4.604 μg/m<sup>3</sup>), temperature (24.8 °C), and relative humidity (21.16%). While most parameters met guidelines, PM<sub>10</sub> levels (97.5 μg/m<sup>3</sup>) exceeded WHO standards and relative humidity was below recommended levels, highlighting areas for improvement. PM<sub>2.5</sub> and PM<sub>10</sub> showed the strongest positive correlation (<i>p</i> value = 0.0001) and similar seasonal trends, with higher concentrations in autumn and summer and lower levels in spring and winter. The southern region exhibited consistently higher PM concentrations, while no significant changes were noted in the East or West. Among the models, CatBoost performed best in predicting air quality. The study suggests that indoor PM levels are influenced by psychrometric conditions and building location, providing valuable insights for improving air quality and occupant health.</p></div>","PeriodicalId":589,"journal":{"name":"International Journal of Environmental Science and Technology","volume":"22 7","pages":"5763 - 5776"},"PeriodicalIF":3.0000,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Environmental Science and Technology","FirstCategoryId":"93","ListUrlMain":"https://link.springer.com/article/10.1007/s13762-024-06277-1","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
The necessity of supplying proper indoor air quality in workplaces to provide the principles of a healthy and productive labor force and avoid negative outcomes is a known fact. This study assessed particulate matter (PM) concentrations in office buildings of governmental organizations across five regions in Tehran over four seasons (2018–2019) to model annual indoor PM patterns using machine learning. PM concentrations, including PM1, PM2.5, PM10, and Total Particulate Matter (TPM), were categorized using ensemble modeling techniques such as Linear Regression, Random Forest, Gradient Boosting, XGBoost, CatBoost, Support Vector Regression, and K-nearest neighbors. Key air quality parameters measured were CO2 (784 ppm), SO2 (0.114 μg/m3), PM2.5 (4.604 μg/m3), temperature (24.8 °C), and relative humidity (21.16%). While most parameters met guidelines, PM10 levels (97.5 μg/m3) exceeded WHO standards and relative humidity was below recommended levels, highlighting areas for improvement. PM2.5 and PM10 showed the strongest positive correlation (p value = 0.0001) and similar seasonal trends, with higher concentrations in autumn and summer and lower levels in spring and winter. The southern region exhibited consistently higher PM concentrations, while no significant changes were noted in the East or West. Among the models, CatBoost performed best in predicting air quality. The study suggests that indoor PM levels are influenced by psychrometric conditions and building location, providing valuable insights for improving air quality and occupant health.
期刊介绍:
International Journal of Environmental Science and Technology (IJEST) is an international scholarly refereed research journal which aims to promote the theory and practice of environmental science and technology, innovation, engineering and management.
A broad outline of the journal''s scope includes: peer reviewed original research articles, case and technical reports, reviews and analyses papers, short communications and notes to the editor, in interdisciplinary information on the practice and status of research in environmental science and technology, both natural and man made.
The main aspects of research areas include, but are not exclusive to; environmental chemistry and biology, environments pollution control and abatement technology, transport and fate of pollutants in the environment, concentrations and dispersion of wastes in air, water, and soil, point and non-point sources pollution, heavy metals and organic compounds in the environment, atmospheric pollutants and trace gases, solid and hazardous waste management; soil biodegradation and bioremediation of contaminated sites; environmental impact assessment, industrial ecology, ecological and human risk assessment; improved energy management and auditing efficiency and environmental standards and criteria.