T. Thai-Phuong
Faculty of Civil Engineering, Industrial University of Ho Chi Minh City (IUH), Ho Chi Minh City, Vietnam

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Integrating machine learning and sustainable infrastructure: forecasting and improving sanitation coverage in rural Vietnam T. Thai-Phuong; N. Pham-Phuong; N. Luu-Huu; L. Nguyen-Son
International Journal of Advances in Intelligent Informatics Vol 12, No 3 (2026): August 2026
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v12i3.2403

Abstract

Disparities in sanitation coverage between urban and rural Vietnam remain a major barrier to sustainable development and public health, especially in rural areas with high poverty and limited clean water access. This study integrates machine learning and sustainable infrastructure to forecast sanitation coverage and address urban-rural disparities. Using data from 2018 to 2023, socio-economic factors (poverty rate, per capita income) and technical indicators (clean water access) were incorporated into Artificial Neural Network (ANN) and Support Vector Machine (SVM) models, evaluated via five-fold cross-validation. Results showed strong correlations (clean water-sanitation: r = 0.99; poverty-sanitation: r = -0.97), with ANN significantly outperforming SVM (validation R² = 0.999972, RMSE = 0.018912%, MAE = 0.1474%). Rural sanitation coverage increased slowly from 84.7% to 94.7%, while urban areas approached optimal levels. The findings demonstrate that machine learning effectively captures non-linear patterns in heterogeneous data for accurate forecasting. To tackle persistent rural gaps, urine-diverting sanitation systems are proposed as a sustainable solution that conserves water, reuses urine as nitrogen-rich fertilizer, and supports circular economy principles aligned with SDG 6. This approach provides practical insights for policymakers to bridge urban-rural inequalities, improve public health, and promote resilient infrastructure in developing contexts.