Predictive Analytics of Air Quality for IoT-Enabled Industrial Environments

Air quality is critical to the health, especially in industrial manufacturing environments. Pollutants such as fine particulate matter and toxic gases like CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>, NO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">x</inf> and VOCs are creating serious health risks. The limited ventilation at indoor manufacturing facilities makes them more vulnerable to poor air quality, causing serious health issues such as asthma and long-standing lung damage. Although existing air quality monitoring systems provide sensing capability for airborne particles or gases, they lack smart predictive capabilities to mitigate future risks in complex industrial and manufacturing environments. In this paper, we propose an air quality prediction solution that leverages real-time, streaming, time-series data collected from IoT nodes deployed at different industrial locations. The system can monitor multiple pollutants, including PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf>, PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">10</inf>, CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>, NO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">x</inf>, and VOCs, using variations of Long Short-Term Memory (LSTM) networks to forecast contaminated air with high accuracy. Our approach involves thorough data preprocessing and analysis activities to effectively model each contaminant. The results show significant promise for forecasting and classifying air quality and offer industries a valuable tool to proactively manage indoor environmental conditions and protect human health.