Air Pollution in Jakarta, Indonesia Under Spotlight: An AI-Assisted Semi-Supervised Learning Approach

Abstract

The air quality in the Jakarta area is examined in this study using artificial intelligence (AI) to assist a semi-supervised learning technique. The clustering approach is used in this article to separate air pollution into three main categories moderate, low, and high levels. This clustering helps identify shared characteristics among measures like particulates (PM10 and PM2.5), sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), and ozone (O3), even when air quality labels are not always accessible. Using the Random Forest method, the air quality will be categorized in this experiment with an accuracy rate of 93%. Additionally, the results of variable significance analysis are examined on this article to identify the variables with the biggest effects on air quality, notably PM10, SO2, and NO2. This study demonstrates the enormous potential of applying machine learning techniques, particularly semi-supervised learning approaches, to assist sustainable environmental regulations while also monitoring and enhancing Jakarta's air quality. We describe the experimental procedures, the findings, and the implications of our research for comprehending and addressing urban air pollution in this article.