A R T I C L E  I N F O
LETTER TO EDITOR		*Corresponding Author: Reza Fouladi-Fard Email: rfouladi@muq.ac.ir Tel: +989119525525
Article History: Received: 23 December 2020 Accepted: 20 February 2021

About 91% of the world’s population are living in places where ambient air pollution exceeds the limits set by the World Health Organization (WHO). Given 4.2 and 3.8 million people die due to exposure to ambient and indoor air pollution, respectively. So, lack of effective measures toward airborne emissions leads to sacrificing lives on a daily basis ¹. The impact of air pollution on the environment and humans has been already extensively discussed and many countries were successful in raising the public awareness about its deleterious consequences. However, the statistics show that air pollution exposure increased the death rates^2-5. The most famous example of air pollution  and its effects occurred in 1952; "London smog", coined from "smoke" and "fog" ⁶. Another example of a famous air pollution abatement is the United States after enacting the first federal air pollution legislation in 1955 and later in 1970, which led to the establishment of Environmental Protection Agency (EPA) ⁶.
However, many developing countries has sacrificed air pollution for economic growth, including Iran ⁷. Given the extensive contributions made to understand the dynamics and health impacts of indoor and ambient air pollution on the environment and humans ^8-12, brighter prospects are not far-fetched. To this end, effective policies should be adopted in the developing countries, similar to the developed countries, to reduce ambient airborne emissions from mobile as well as industrial sources ¹². In the developing countries, the threat of air pollution often emerges in the winter, when atmospheric entrapment, diesel- and mazut-burning power plants, emissions, and the demand for thermal energy concur; an exacerbated scenario is very likely.
In urban areas, air pollution is impacted by human activities rather than natural sources of air pollution. Furthermore, limited human activities often decrease indoor and outdoor air pollution, as the current COVID-19 pandemic reduced the air pollution ^13-15. Accordingly, Berman and Ebisu ¹⁶ found that COVID-19 pandemic declined NO₂ emissions by 25.5% as well as PM_2.5 pollution in the United States. Although the COVID-19 lockdowns are considered as the main factor in air pollution decline ¹⁷, they led to higher traffic congestion in urban areas due to the limited use of public transportation ¹⁸. Human beings have developed many strategies after COVID-19 lockdowns to promote the use of remote working and efficiency of traffic restrictions on air pollution, which reduced the carbon footprint imposed on the environment. However, these remote and online activities may not fully-satisfy the demand to decrease carbon footprint. Obringer, Rachunok, Maia-Silva, Arbabzadeh, Nateghi, and Madani ¹⁹ suggested that the standard range of carbon footprint of 1 GB was from 28 to 63 g CO₂. The novel implications of air pollution modeling using machine learning algorithms have attracted attention and proved applicable for air pollution dispersion. Rezaali, Fouladi-Fard, Mojarad, Sorooshian, Mahdinia, and Mirzaei ¹² implemented a random forest model to estimate the spatio-temporal distributions of benzene, toluene, ethylbenzene, and xylene (BTEX). Zhang, Fu, and Tian ²⁰ adopted a deep learning approach to estimate air pollution using the images captured by mobile devices. Machine learning methods can also improve the accuracy of traditional techniques, such as land-use regression. Lautenschlager, Becker, Kobs, Steininger, Davidson, Krause, and Hotho ²¹ proposed a machine learning approach for optimizing and facilitating the widely-used land-use regression. Therefore, application of machine learning algorithms can pave the way for future mitigation of air pollution as well as public awareness of pollution levels.
 
This is an Open Access article distributed in accordance with the terms of the Creative Commons Attribution (CC BY 4.0) license, which permits others to distribute, remix, adapt and build upon this work for commercial use.
 
References
1.         WHO. Air pollution. Available from:http:// www. who. int/ health- topics/ airpollution# tab= tab_1. [Cited 23 Janury  2021]
2.         Yu M, Zhu Y, Lin CJ, et al. Effects of air pollution control measures on air quality improvement in Guangzhou, China. J Environ Manag. 2019;244:127-37.
3.         Ma Z, Liu R, Liu Y, et al. Effects of air pollution control policies on PM_2.5 pollution improvement in China from 2005 to 2017: a satellite-based perspective. Atmos Chem Phys. 2019;19(10): 6861-77.
4.         Zhang S, Worrell E, Crijns-Graus W, et al. Co-benefits of energy efficiency improvement and air pollution abatement in the Chinese iron and steel industry. Energy. 2014;78:333-45.
5.         Vedrenne M, Borge R, Lumbreras J, et al. An integrated assessment of two decades of air pollution policy making in Spain: Impacts, costs and improvements. Sci Total Environ. 2015;527:351-61.
6.         Fenger J. Air pollution in the last 50 years – From local to global. Atmos Environ. 2009; 43(1): 13-22.
7.         Pajooyan J, Moradhasel N. Assessing the relation between economic growth and air pollution. J Econ Res. 2008;7(4):141-60.
8.         Fouladi Fard R, Naddafi K, Yunesian M, et al. The assessment of health impacts and external costs of natural gas-fired power plant of Qom. Environ Sci Pollut Res. 2016;23(20):20922-36.
9.         Fouladi Fard R, Naddafi K, Hassanvand MS, et al. Trends of metals enrichment in deposited particulate matter at semi-arid area of
Iran. Environ Sci Pollut Res Int. 2018;25(19): 18737-51.
10.       Mojarrad H, Fouladi Fard R, Rezaali M, et al. Spatial trends, health risk assessment and ozone formation potential linked to BTEX. Hum Ecol Risk Assess. 2020;26(10):2836-57.
11.       Fouladi Fard R, Mahvi AH, Mahdinia M, et al. Data on emerging sulfur dioxide in the emission of natural gas heater. Data in Brief. 2018;155:133-43.
12.       Rezaali M, Fouladi-Fard R, Mojarad H, et al. A wavelet-based random forest approach for indoor BTEX spatiotemporal modeling and health risk assessment. Environ Sci Pollut Res. 2021.
13.       Hosseini MR, Fouladi-Fard R, Aali R. COVID-19 pandemic and sick building syndrome. Indoor Built Environ. 2020;29(8): 1181-3.
14.       Rahimi NR, Fouladi-Fard R, Aali R, et al. Bidirectional association between COVID-19 and the environment: a systematic review. Environ Res. 2020:110692.
15.       Rezaali M, Fouladi-Fard R. Aerosolized SARS-CoV-2 exposure assessment: dispersion modeling with AERMOD. J Environ Health Sci Eng. 2021:1-9.
16.       Berman JD, Ebisu K. Changes in U.S. air pollution during the COVID-19 pandemic. Sci Total Environ. 2020;739:139864.
17.       Venter ZS, Aunan K, Chowdhury S, et al. COVID-19 lockdowns cause global air pollution declines. Proc Natl Acad Sci. 2020;117(32): 18984-90.
18.       Dasgupta P, Srikanth K. Reduced air pollution during COVID-19: Learnings for sustainability from Indian Cities. Glob Transit. 2020;2:
271-82.
19.       Obringer R, Rachunok B, Maia-Silva D, et al. The overlooked environmental footprint of increasing Internet use. Resour Conserv Recycl. 2021;167:105389.
20.       Zhang Q, Fu F, Tian R. A deep learning and image-based model for air quality estimation. Sci Total Environ. 2020;724: 138178.
21.       Lautenschlager F, Becker M, Kobs K, et al. OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning. Atmos Environ. 2020;233:117535.