<![CDATA[The problem of increasing air pollution that occurs globally also occurs in Indonesia, including in Jambi Province. Air pollution has dust particles in it, one of which is Particulate Matter (PM2.5). The concentration of PM2.5 in the air is influenced by the meteorological conditions of an area, as well as the events around it, whether it is a natural event or an event caused by human activities. This study predicted PM2.5 concentration in Jambi city using Multiple Linear Regression and Random Forest Regression algorithms with air temperature, air humidity, wind speed, rainfall and hot spots as independent variabels. In the process, this study compares the two algorithms and assesses the accuracy of each algorithm. The Multiple Linear Regression algorithm is able to generate a model that can describe the relationship between air temperature, air humidity, wind speed, rainfall and hot spots to PM2.5 concentration, although the error value is larger than that of the Random Forest Regression algorithm. The Random Forest Regression algorithm produces a model with an RMSE of 0.033μg/mm3 smaller than the Multiple Linear Regression algorithm. In the accuracy test with MAPE, the Random Forest Regression algorithm has a value of 74,0% where Multiple Linear Regression has a value of 73,0% so that the Random Forest Regression algorithm has a higher accuracy in predicting PM2.5 concentrations.]]>
Copyrights © 2025
