NEW RESEARCH PUBLICATION ON GROUNDWATER QUALITY ASSESSMENT IN THE VIETNAMESE MEKONG DELTA
Originally posted: 20/05/2026
CARE is pleased to introduce the research article published in the Journal of Environmental Management, entitled “Machine learning-based evaluation and dimensionality optimization of groundwater quality indices for drinking and irrigation in the Vietnamese Mekong Delta” by Dr. Ha Quang Khai (FERN, HCMUT) and Tran Ba Loc (CARE, HCMUT).
DOI: https://doi.org/10.1016/j.jenvman.2026.129953
Groundwater is the principal source of drinking and agricultural water supply in the Vietnamese Mekong Delta (VMD). However, groundwater resources are increasingly threatened by salinization, redox-driven metal mobilization, and unsustainable groundwater abstraction. Therefore, reliable and cost-effective assessment approaches are essential to support groundwater management in data-limited environments.
Using a dataset of 1,386 groundwater samples collected from nine provinces, the study assessed groundwater suitability for drinking and irrigation purposes through the Entropy Water Quality Index (EWQI) and Irrigation Water Quality Index (IWQI). In addition, nine machine learning algorithms were applied to reconstruct groundwater quality indices from hydrochemical variables and evaluate their effective predictor dimensionality.
The results showed that 80.6% of groundwater samples were classified as excellent to good for drinking purposes, while 19.4% fell into poor to severely hazardous categories, indicating localized but significant groundwater degradation. In contrast, irrigation suitability was much more limited, with only 20.7% of samples classified as suitable to highly suitable, whereas most groundwater samples ranged from marginally suitable to highly unsuitable.
The study also demonstrated the strong performance of machine learning models, particularly Random Forest and XGBoost, with reconstruction accuracies reaching R² values of up to 0.996 for EWQI and 0.95 for IWQI. The analysis further revealed that groundwater quality indices can be effectively approximated using a limited number of dominant variables, contributing to more cost-effective monitoring strategies for groundwater management.
This research provides valuable insights into groundwater quality assessment and sustainable water resource management in the Vietnamese Mekong Delta, one of the most vulnerable delta regions in Southeast Asia.


