Environmental Transparency and Air Pollution Control using Continuous Emissions Monitoring Systems (CEMS)
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V7I2P121Keywords:
Internet of Things (IoT), Hardware, Air Pollution, CEMS, Environmental Transparency, Machine LearningAbstract
Due to the high levels of pollutants like SO₂, NO₂, CO and PM2.5/PM10, air pollution has become a large problem for the environment and human health, caused by high rate of industrialization and urbanization. Real-time assessment of air quality is challenging in absence of low-cost and continuous monitoring systems, particularly in developing regions. The objective of this study is to create an affordable IoT-based Continuous Emission Monitoring System (CEMS) for real-time monitoring and analysis of air pollutants. The methodology comprises of integrating MQ135, MQ7, PMS7003 and BMP280 sensors with Arduino Uno and ESP32 microcontroller and making this device compatible with cloud connectivity by using IoT based cloud service called ThingSpeak. Multiple Linear Regression is used for machine learning-based calibration to improve the accuracy by correlating the sensor outputs with CPCB reference data and minimizing the environmental effects. It can be seen that the system is able to monitor the pollutant change in real time with a calibrated performance of R² = 0.87 and RMSE = 6.5 µg/m³. The hardware testing proved the sensors to be stable in operation: the MQ135 sensor was able to detect air quality changes in the range of 50–180 µg/m³, the MQ7 sensor measured the concentration of CO up to 25,000 µg/m³, and the PMS7003 sensor consistently measured the concentration of particles in the range of 60–200 µg/m³. The cloud transmission was reliable with an average delay of 10-15 seconds, achieved by ESP32, and the buzzer alert system responded quickly to hazardous conditions. The suggested CEMS provides an economical, scalable, and effective way to monitor air pollution continuously, improving environmental transparency and facilitating improved air quality management.
References
[1] V. K. Sharma, “Cloud Computing & IoT: 5G Focused IoT with Cloud Solutions,” Int. J. AI, BigData, Comput. Manag. Stud., vol. 6, no. 3, 2025, doi: 10.63282/3050-9416.IJAIBDCMS-V6I3P103.
[2] A. H. Vasanth, “Air Pollution Monitoring System Using IOT,” Int. J. Creat. Res. Thoughts, vol. 9, no. 7, pp. 1–7, 2021.
[3] L. Bai, J. Wang, X. Ma, and H. Lu, “Air Pollution Forecasts: An Overview,” Int. J. Environ. Res. Public Health, vol. 15, no. 4, p. 780, Apr. 2018, doi: 10.3390/ijerph15040780.
[4] S. Sen, “Artificial Intelligence in Mining, Petroleum and Natural Gas Extraction Process Optimization,” Int. J. Emerg. Res. Eng. Technol., vol. 6, no. 1, pp. 121–125, 2025, doi: 10.63282/3050-922X.IJERET-V6I1P115.
[5] A. V. Kychkin, O. V. Gorshkov, and M. A. Kukarkin, “Predictive models integration with an environmental monitoring IoT platform,” J. Appl. Informatics, vol. 17, no. 4, pp. 5–16, Aug. 2022, doi: 10.37791/2687-0649-2022-17-4-5-16.
[6] Y. Muni, “Sustainable Data Centers: a Systematic Review of Technologies and Practices for Carbon Emission Reduction,” Int. J. Adv. Res. Comput. Sci., vol. 16, no. 4, pp. 125–131, 2025, doi: 10.26483/ijarcs.v16i4.7309.
[7] U. Korat and A. Alimohammad, “Efficient Hardware Implementation of Eigen Solver,” in 2026 IEEE 16th Annual Computing and Communication Workshop and Conference (CCWC), IEEE, Jan. 2026, pp. 1376–1385. doi: 10.1109/CCWC67433.2026.11393888.
[8] Y.-L. Zhao et al., “Development of IoT Technologies for Air Pollution Prevention and Improvement,” Aerosol Air Qual. Res., vol. 20, no. 12, pp. 2874–2888, 2020, doi: 10.4209/aaqr.2020.05.0255.
[9] N. Ding et al., “State-of-the-art carbon metering: Continuous emission monitoring systems for industrial applications,” Heliyon, vol. 11, no. 3, p. e42308, Feb. 2025, doi: 10.1016/j.heliyon.2025.e42308.
[10] S. Chen et al., “Carbon and air pollutant emission dynamics of small-scale industrial sectors based on CEMS: a case of tobacco curing industry,” Environ. Pollut., vol. 376, p. 126427, Jul. 2025, doi: 10.1016/j.envpol.2025.126427.
[11] X. Zhou, J. Aurell, W. Mitchell, D. Tabor, and B. Gullett, “A small, lightweight multipollutant sensor system for ground-mobile and aerial emission sampling from open area sources,” Atmos. Environ., vol. 154, pp. 31–41, Apr. 2017, doi: 10.1016/j.atmosenv.2017.01.029.
[12] R. G. Barrientos-Mauricio, A. Q. Medrano-Jacobo, and E. A. Carrera-Salas, “IoT-based air pollution monitoring system: A case study in Artisanal Brick Kilns,” Sustain. Environ., vol. 12, no. 1, Dec. 2026, doi: 10.1080/27658511.2025.2607841.
[13] G. Aprilia, H. Fakhrurroja, and D. Pramesti, “IoT-Base Air Pollution Monitoring System in Urban Area,” in 2025 International Conference on ICT for Smart Society (ICISS), IEEE, Sep. 2025, pp. 1–6. doi: 10.1109/ICISS66954.2025.11389321.
[14] M. N. A. Ramadan, M. A. H. Ali, S. Y. Khoo, M. Alkhedher, and M. Alherbawi, “Real-time IoT-powered AI system for monitoring and forecasting of air pollution in industrial environment,” Ecotoxicol. Environ. Saf., vol. 283, p. 116856, Sep. 2024, doi: 10.1016/j.ecoenv.2024.116856.
[15] L. Tang, M. Jia, J. Yang, L. Li, X. Bo, and Z. Mi, “Chinese industrial air pollution emissions based on the continuous emission monitoring systems network,” Sci. Data, vol. 10, no. 1, p. 153, Mar. 2023, doi: 10.1038/s41597-023-02054-w.
[16] S. Listyarini, L. Warlina, and A. Sambas, “The Air Quality Monitoring Tool Based on Internet of Things to Monitor Pollution Emissions Continuously,” Environ. Ecol. Res., vol. 10, no. 6, pp. 824–829, Dec. 2022, doi: 10.13189/eer.2022.100616.
[17] S. M. S. D. Malleswari and T. K. Mohana, “Air pollution monitoring system using IoT devices: Review,” Mater. Today Proc., vol. 51, pp. 1147–1150, 2022, doi: 10.1016/j.matpr.2021.07.114.
[18] Harish G N, Asharani R, and Nayana R, “IoT-based air pollution monitoring and data analytics using machine learning approach,” World J. Adv. Res. Rev., vol. 12, no. 1, pp. 521–528, Oct. 2021, doi: 10.30574/wjarr.2021.12.1.0411.
