Air Pollution Prediction using Supervised Machine Learning Technique

Abstract

Toxins in the air pose a threat to human health and the environment worldwide, a problem known as air pollution. Predicting air quality from pollution using machine learning techniques might be an effective step in mitigating this issue in the transportation sector. Statistical analysis, multiple analyses, variations, missing value treatment, validation, and cleaning/correction of air quality data have all been previously considered. Then, supervised machine learning methods like Logistic Regression, Random Forest, Decision Tree, and Naive Byes are used to make predictions about the air quality. Precision, Recall, and F1 Score are used to evaluate the effectiveness of various machine learning methods. Predictions of air quality using the Decision Tree method are accurate. The Bureau of Meteorology can use this app to improve their forecasts of air quality. The use of Artificial Intelligence methods to enhance this work is a possibility for the future.