Evaluation of formal waste reduction facility location compared to recyclable plastic waste generation in Denpasar City, Bali, Indonesia

Abstract

This paper aims to evaluate the location of formal waste reduction facilities in comparison to the distribution of recyclable plastic waste generation in Denpasar City, Bali Province, Indonesia. The distribution of recyclable plastic waste generation was carried out by conducting primary sampling from 200 houses, following the guidelines of SNI-19-3964-1994. Socioeconomic variables, including house size, population density, Gross Domestic Product (GDP), and area classification, were obtained through interviews and the use of remote sensing data products. The distribution of recyclable plastic waste is modeled using the best of six machine learning models: LGBM (Light Gradient Boosting Machine), Linear Regression, Random Forest, and SVM (Support Vector Machine), XGBoost, and Adaboost. The LGBM model was selected with an R2 of 0.939 in the training dataset, an R2 of 0.954 in the testing dataset, and the lowest RMSE and MAE. The map of recyclable plastic waste generation distribution is created through a spatial analysis that consists of three classes with ranges of <248.5, >248.5 and <732.5, and >732.5 grams/household/week. The effectiveness of the coverage area and capacity through spatial analysis indicates that the waste reduction facilities in Denpasar City are 32% and 46%, respectively.