Analysis of Determinant Factors of Carbon Efficiency in Indonesia Based on Domestic Waste Management using Causal Machine Learning

Carbon efficiency Causal machine learning Domestic waste management

Authors

January 31, 2025

Downloads

Introduction: Domestic waste management, which is a provincial-level program, is expected to reduce greenhouse gas (GHG) emissions for the sustainability of climate control efforts in Indonesia. Given this context, it is necessary to conduct a carbon efficiency analysis in Indonesia based on domestic waste management efforts. Methods: This study used an observational research design with a cross-sectional time approach. This study predicted the reduction in carbon emissions based on domestic waste management using causal machine learning by analyzing data on GHG emissions and domestic waste management from all provinces in Indonesia. An advantage of causal machine learning is its ability to assess the impact of treatment (domestic waste management) on the results (GHG emissions), as well as mitigating the effects of confounding variables. Results and Discussion: Despite improvements in waste management, several provinces experienced increased waste production, particularly from domestic waste and plastic waste. Analysis using the R programming language revealed that waste management is a significant variable (p = 0.011). However, data limitations posed challenges to comprehensive analysis. Conclusion: Achieving carbon efficiency requires serious waste management efforts. All provinces and cities/regencies must actively participate in program implementation. Routine reporting is essential to monitor the progress toward reducing GHG emissions.