AIR POLLUTION MONITORING AND FORECAST OF POLLUTION LEVEL USING IOT AND ML

Abstract

Air pollution poses a significant threat to public health, the environment and in recent times is increasing at an alarming rate, necessitating the development of efficient monitoring and prediction systems. This paper presents an innovative approach leveraging the Internet of Things (IoT) and Machine Learning (ML) techniques for real-time air pollution monitoring and prediction. The proposed system integrates a network of IoT sensors strategically placed in urban areas to continuously measure key air quality parameters such as particulate matter (PM), nitrogen dioxide (NO2), sulfur dioxide (SO2), carbon monoxide (CO), ozone (O3), Temperature and Humidity. A microcontroller processes the data from the properly calibrated sensors and sends them to realtime cloud storage through a Wi-Fi module. A remote server then fetches and analyzes the data. We then determine the prime pollutant from the data, which is Particulate Matter. Next, we use the Autoregressive Integrated Moving Average (ARIMA) model to predict the pollution levels from harmful gasses & the Air Quality Index (AQI) of the next day with high accuracy. Precisely, we predict the 24-hourly observations of the following day after training our optimized model with 144 hourly observations of the previous six days. We then evaluate the model with a MAPE (Mean Absolute Percentage Error) score, which ensures that our model is working properly. This system offers proactive decision-making capabilities, enabling stakeholders to issue alerts, implement control measures, and optimize urban infrastructure to mitigate pollution. Visualization tools and reporting mechanisms provide intuitive insights for policymakers and the public.Through continuous evaluation and refinement, the proposed system aims to enhance air quality management, contributing to healthier and more sustainable communities. Therefore we believe that our solution will be helpful if implemented at large scale.