Next Article in Journal
GPU-Accelerated High-Resolution Dam-Break Flood Simulation Using 0.5 m Airborne LiDAR for Sustainable Disaster Risk Reduction in Ageing Reservoirs: Application to Geumosan Reservoir, South Korea
Previous Article in Journal
Linking Urban Transport and Livability: A GIS-Integrated Multicriteria Decision-Making Evaluation in Kanarya İstanbul
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sustainability
Volume 18
Issue 10
10.3390/su18105076
sustainability-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Machine Learning-Based Forecasting of Waste Generation Proxies Under Data-Limited Conditions for Supporting Adaptive and Sustainable Citarum River Management

by
Sudradjat Supian
1,*,
Sukono
1,
Riaman
1,
Hafizan Juahir
2,
Tubagus Robbi Megantara
3,
Indra
3,
Astrid Sulistya Azahra
3,
Dede Irman Pirdaus
4 and
Moch Panji Agung Saputra
1
1
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran, Jatinangor, Sumedang 45363, Indonesia
2
Faculty of Bioresources & Food Industry, Universiti Sultan Zainal Abidin, Besut Campus, Besut 22200, Malaysia
3
Doctoral Program in Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran, Jatinangor, Sumedang 45363, Indonesia
4
Communication in Research and Publications, Gede Bage, Bandung 40294, Indonesia
*
Author to whom correspondence should be addressed.
Sustainability 2026, 18(10), 5076; https://doi.org/10.3390/su18105076 (registering DOI)
Submission received: 11 April 2026 / Revised: 6 May 2026 / Accepted: 15 May 2026 / Published: 18 May 2026
Versions Notes

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: machine learning; waste generation proxy; Citarum River; predictive modeling; sustainable river management machine learning; waste generation proxy; Citarum River; predictive modeling; sustainable river management

Share and Cite

MDPI and ACS Style

Supian, S.; Sukono; Riaman; Juahir, H.; Megantara, T.R.; Indra; Azahra, A.S.; Pirdaus, D.I.; Saputra, M.P.A. Machine Learning-Based Forecasting of Waste Generation Proxies Under Data-Limited Conditions for Supporting Adaptive and Sustainable Citarum River Management. Sustainability 2026, 18, 5076. https://doi.org/10.3390/su18105076

AMA Style

Supian S, Sukono, Riaman, Juahir H, Megantara TR, Indra, Azahra AS, Pirdaus DI, Saputra MPA. Machine Learning-Based Forecasting of Waste Generation Proxies Under Data-Limited Conditions for Supporting Adaptive and Sustainable Citarum River Management. Sustainability. 2026; 18(10):5076. https://doi.org/10.3390/su18105076

Chicago/Turabian Style

Supian, Sudradjat, Sukono, Riaman, Hafizan Juahir, Tubagus Robbi Megantara, Indra, Astrid Sulistya Azahra, Dede Irman Pirdaus, and Moch Panji Agung Saputra. 2026. "Machine Learning-Based Forecasting of Waste Generation Proxies Under Data-Limited Conditions for Supporting Adaptive and Sustainable Citarum River Management" Sustainability 18, no. 10: 5076. https://doi.org/10.3390/su18105076

APA Style

Supian, S., Sukono, Riaman, Juahir, H., Megantara, T. R., Indra, Azahra, A. S., Pirdaus, D. I., & Saputra, M. P. A. (2026). Machine Learning-Based Forecasting of Waste Generation Proxies Under Data-Limited Conditions for Supporting Adaptive and Sustainable Citarum River Management. Sustainability, 18(10), 5076. https://doi.org/10.3390/su18105076

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop