<p>The accurate prediction of particulate matter concentrations serves as the foundation for effective air quality management. Hisar City, which resides in north-west India, experiences high levels of PM_2.5 and PM₁₀ pollution because of vehicular and industrial emissions, construction and farming activities, and weather conditions. The research tests machine learning models to forecast PM_2.5 and PM₁₀ levels in Hisar City. Historical air quality data together with weather data for a period of 2020–2024 were gathered and an exploratory data analysis was performed to study the seasonal behaviour of particulate matter for the representative location. For modelling analysis, the periodic data from the year 2020 to 2023 was used for model training and the data from the year 2024 was used for testing. The research used Support Vector Regression (SVM), Random Forest (RF), Gradient Boosting, AdaBoost and M5 regression to create and test multiple machine learning models. For model explainability, SHAP analysis along with the sensitivity were performed to study the role and contribution of weather variables on the PM concentration estimation. The researchers used correlation coefficient (CC), root mean squared error (RMSE), and mean absolute error (MAE) as statistical indicators to assess the model performance. The study results showed that ensemble-based models (Gradient Boosting and RF) provide better results than the other regression models for predicting PM concentrations of the city. Correlation coefficient of 0.73 and 0.668 was achieved by Gradient Boosting model for PM_2.5 and PM₁₀ prediction along with the least RMSE values during testing. The RF model achieved CC values of 0.724 and 0.674 for PM_2.5 and PM₁₀ prediction, respectively, during testing. The proposed method shows that machine learning techniques can be used to predict air quality reliably, which helps policymakers develop effective emergency response plans.</p>