Machine Learning-Based Forecasting of Waste Generation Proxies Under Data-Limited Conditions for Supporting Adaptive and Sustainable Citarum River Management
Open Access
- 18 May 2026
- journal article
- research article
- Published by MDPI AG in Sustainability
- Vol. 18 (10) , 5076
Abstract
This study addresses the prediction of daily waste generation dynamics under data-limited conditions in a strategic watershed serving over 25 million residents. A machine learning framework is developed using daily proxies reconstructed from annual data (2019–2024) through an additive seasonal stochastic disaggregation approach, while maintaining consistency with official SIPSN records. Statistical analysis identifies the 2023 annual total as anomalous (+127.06% YoY) using the IQR method, while sensitivity tests to various parameter configurations indicate that the baseline setting (α = 0.95; σ_frac = 0.08) provides stable estimates. Four models—Random Forest, Support Vector Regression (SVR), XGBoost, and Long Short-Term Memory (LSTM)—are evaluated using strict chronological partitioning to maintain temporal integrity. Results indicate that the evaluation reflects the model’s ability to reproduce synthetic proxies, rather than direct field observations. SVR performed best (R2 = 0.8157; RMSE = 881.43 t/day), outperforming the persistence baseline by +32.2%. After data leakage correction, XGBoost’s performance decreased significantly (R2 = 0.1591). Feature analysis confirmed the dominance of short-term statistical indicators, while the hierarchical bootstrap approach produced more comprehensive uncertainty estimates, with SVR remaining the most stable across seasons.Keywords
Funding Information
- Universitas Padjadjaran (4099/UN6.3.1/PT.00/2025)
This publication has 40 references indexed in Scilit:
- Spatio-temporal patterns of river water quality in the klang river basin, malaysia: a functional data analysis approach to detect pre- and post-pandemic shiftsEnvironmental Monitoring and Assessment, 2025
- XGBoost To Enhance Learner Performance PredictionComputers and Education: Artificial Intelligence, 2024
- XGBoost based enhanced predictive model for handling missing input parameters: A case study on gas turbineCase Studies in Chemical and Environmental Engineering, 2024
- Plastic debris in riversWIREs Water, 2019
- Univariate Time Series Forecasting of Temperature and Precipitation with a Focus on Machine Learning Algorithms: a Multiple-Case Study from GreeceWater Resources Management, 2018
- A random forest guided tourTEST, 2016
- Adaptive Management: From More Talk to Real ActionEnvironmental Management, 2013
- Identification of appropriate lags and temporal resolutions for low flow indicators in the River Rhine to forecast low flows with different lead timesHydrological Processes, 2012
- Structured Decision Making2012
- The Nature of Statistical Learning Theory1995