The present study explores familiar environmental datasets and has taken into consideration, due to different machine learning methods, the nature of two different resources, air and water, available and unavailable. In our study two targets have been selected the Air Quality Index – AQI and the Water Quality Index – WQI. The chemical composition data set was pH and nitrate level in this regard for water analysis. With respect to the air quality assessment, CO and particulate matter (PM2.5) pollutants were measured and the researchers used those for analysis. In the absence of score from WQI data, the researchers had to develop their own scoring methodology within which to construct an index of water quality. They then experimented with two models, Random Forest and Decision Tree. Among these the Random Forest data generated better accuracy as compared to that of the Decision Tree data, at a far lower risk of overfitting regarding AQI and WQI predictions. Moreover, the scientists utilized charts and other visualization structures to present trends and pollution more visually. Their results also suggest the promise of machine learning for decision making and environmental monitoring.