​Predicting changes in air pollutant concentrations due to human and nature drivers are critical and challenging, 

particularly in areas with scant data inputs and high variability of parameters. This paper builds an Air Quality Index (AQI) model 

using Machine Learning algorithms and techniques. The paper employs Machine Learning Algorithms such as Decision Tree 

(DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Random Forest (RF) and Logistic Regression. The model can 

predict the most pollutant factors from real readings published daily by the Jordan Ministry of Environment (MoEnv) for the 

period from January 2017 to April 2019. Jordan has prioritized air quality problems by establishing detection and monitoring 

stations in 12 positions across the country to measure Air Quality (AQ). Pollutant concentrations recorded by MoEnv use fully 

forewarn official organizations and individuals of daily air quality in the atmosphere over time and beneficially used by health and 

climate studies organizations. The study has detected the most contaminated sites and determined the pollutant concentrations. 

These estimates will indicate the most influenced pollutants and their behavior in the pollution process for further 

recommendations and actions to effects cardiopulmonary patients, environmental and climate researches, as well as to vulnerable 

ecosystems.