Authors:
Jaime Alfonso Flores Navas, Luigi Orlando Freire Martínez, Sara Toumi, Moustafa Adel Darwish, Ahmed Ali Qameeh, Rajyalakshmi Pulicherla

Addresses:
Department of Environmental Sciences, National Autonomous University of Mexico, Coyoacán, Mexico City, Mexico. School of Engineering and Applied Sciences, Technical University of Cotopaxi, Latacunga, Cotopaxi, Ecuador. Department of Hydrocarbon Production, Kasdi Merbah University, Ouargla, Ouargla Province, Algeria. Department of Physics, Faculty of Science, Tanta University, Tanta, Gharbia Governorate, Egypt. Department of Physics, University of Lahej, Sabr, Lahj Governorate, Yemen.  Department of Electronics and Communication Engineering, Sri Venkatesa Perumal College of Engineering and Technology, Puttur, Andhra Pradesh, India.

Abstract:

Air pollution is a significant environmental issue that hurts the quality of life as well as the health of individuals. Air quality monitoring helps people understand pollution levels and take preventive measures. This paper develops an Internet of Things (IoT)-based air quality monitoring system that uses machine learning techniques to predict the Air Quality Index (AQI). As input data, the system considers environmental characteristics such as PM2.5, PM10, CO, NO2, and SO2 levels, as well as O2 levels, temperature, humidity, and wind speed. The system then processes these sensor values and feeds them into a machine learning model to predict the AQI. This paper uses the Random Forest regression algorithm to produce reliable forecasts. The predicted Air Quality Index (AQI) value is then categorized as Good, Moderate, Unhealthy, Very Unhealthy, or Hazardous. The Gradio programming language provides a user-friendly interface that makes it easy for users to enter sensor information. The system instantly displays the projected AQI and its category. This research shows how machine learning and Internet of Things concepts can be combined to build a smart air quality monitoring system.

Keywords: Air Quality Index (AQI); Machine Learning (ML); Random Forest; Internet of Things (IoT); Air Quality Monitoring; Wind Speed; Air Pollution; Sensor Information.

Received on: 15/06/2025, Revised on: 18/08/2025, Accepted on: 21/10/2025, Published on: 07/09/2026

DOI: 10.69888/FTSESS.2026.000786

FMDB Transactions on Sustainable Environmental Sciences, 2026 Vol. 3 No. 3, Pages: 143-152

• Views : 18
• Downloads : 8

Download PDF