Abstract
The final waste processing facility plays a crucial role in waste management. The growing amount of waste in landfills is causing significant harm to the surrounding environment and the health of nearby residents. This study seeks to offer insights into the projected future waste volume in landfills. This research applies the mathematical models of the Autoregressive Integrated Moving Average (ARIMA) and Autoregressive Fractionally Integrated Moving Average (ARFIMA). This research method begins by determining the source of monthly waste data at the final waste disposal place. Based on monthly observation data from 11 January 2011 to 24 December 2023, identification and estimation of ARIMA and ARFIMA modelling are carried out. Based on the results of the RMSE and MAPE calculations, the ARIMA model is the best for predicting the volume of waste at the final waste processing site location, compared to the ARFIMA model. However, when comparing predictions from the two models with actual conditions for January to June 2024, the ARFIMA model yielded a MAPE value of 6%, while the ARIMA prediction model resulted in a MAPE of 8%. This research is significant in providing predictive information on the volume of waste at the final waste processing site for the government. The results of this research can be used to make policies and design more effective waste management regulations. Furthermore, the appropriate model for predicting waste volume in 2024 is ARIMA (3, 1, 3), and ARFIMA (2, -0.32, 1).
Keywords: ARFIMA, ARIMA, MAPE, RMSE, Waste Volume.