Predicting salinity levels in the Mekong delta (Viet Nam): analysis of machine learning and deep learning models

Abstract Salinity intrusion stands out as a severe yet escalating challenge facing the water resource management and agricultural production of the Mekong Delta in Vietnam as a result of climate change and upstream hydrological changes. This paper assesses the efficacy of six different machine learn...

Full description

Saved in:
Bibliographic Details
Main Authors: Phong Nguyen Duc, Thang Tang Duc, Giap Pham Van, Hoat Nguyen Van, Tuan Tran Minh
Format: Article
Language:English
Published: Springer 2025-05-01
Series:Discover Artificial Intelligence
Subjects:
Online Access:https://doi.org/10.1007/s44163-025-00336-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849705299324174336
author Phong Nguyen Duc
Thang Tang Duc
Giap Pham Van
Hoat Nguyen Van
Tuan Tran Minh
author_facet Phong Nguyen Duc
Thang Tang Duc
Giap Pham Van
Hoat Nguyen Van
Tuan Tran Minh
author_sort Phong Nguyen Duc
collection DOAJ
description Abstract Salinity intrusion stands out as a severe yet escalating challenge facing the water resource management and agricultural production of the Mekong Delta in Vietnam as a result of climate change and upstream hydrological changes. This paper assesses the efficacy of six different machine learning (ML) and deep learning models (DL) for hourly prediction of salinity in the Mekong Delta at four stations (Cau Quan, Tra Vinh, Ben Trai, and Tran De). The six models are XGB, GB, SVR, LSTM, RNN and ANN. Using hourly hydrological data of 2015–2020 with upstream discharge and tidal water levels as major inputs we designed training and testing of models (training: Jan 2015-mid 2018; testing: mid 2018-Feb 2020). Our results prove that LSTM and XGB models have the best prediction. In particular, they showed good accuracy in predicting upstream salinity (RMSE: 0.25 to 0.30, R2 > 0.97) and downstream salinity (RMSE: 1.5 to 1.6, R2 > 0.88). This success is due to capacity of high temporal resolution as well as spatio-temporal dynamics of salinity variation. The LSTM structure has proven to be effective at capturing long-term temporal dependencies, such as seasonal discharge patterns, while XGB successfully models non-linear interactions between stations with the greatest success, particularly discharge-tidal level interactions. The ML/DL models are capable of successfully forecasting salinity which can open doors to data-driven water management in the Mekong Delta. Future studies should further add hydro-meteorological parameters, other hybrid architectures, and real-time prediction systems, which could be useful operationally and have wider applicability.
format Article
id doaj-art-1a31b09104e8450b9e0959f68957f6c2
institution DOAJ
issn 2731-0809
language English
publishDate 2025-05-01
publisher Springer
record_format Article
series Discover Artificial Intelligence
spelling doaj-art-1a31b09104e8450b9e0959f68957f6c22025-08-20T03:16:31ZengSpringerDiscover Artificial Intelligence2731-08092025-05-015113510.1007/s44163-025-00336-3Predicting salinity levels in the Mekong delta (Viet Nam): analysis of machine learning and deep learning modelsPhong Nguyen Duc0Thang Tang Duc1Giap Pham Van2Hoat Nguyen Van3Tuan Tran Minh4Institute for Water and Environment, Vietnam Academy for Water ResourcesThe Southern Institute of Water Resources Research, Vietnam Academy for Water ResourcesThe Southern Institute of Water Resources Research, Vietnam Academy for Water ResourcesThe Southern Institute of Water Resources Research, Vietnam Academy for Water ResourcesThe Southern Institute of Water Resources Research, Vietnam Academy for Water ResourcesAbstract Salinity intrusion stands out as a severe yet escalating challenge facing the water resource management and agricultural production of the Mekong Delta in Vietnam as a result of climate change and upstream hydrological changes. This paper assesses the efficacy of six different machine learning (ML) and deep learning models (DL) for hourly prediction of salinity in the Mekong Delta at four stations (Cau Quan, Tra Vinh, Ben Trai, and Tran De). The six models are XGB, GB, SVR, LSTM, RNN and ANN. Using hourly hydrological data of 2015–2020 with upstream discharge and tidal water levels as major inputs we designed training and testing of models (training: Jan 2015-mid 2018; testing: mid 2018-Feb 2020). Our results prove that LSTM and XGB models have the best prediction. In particular, they showed good accuracy in predicting upstream salinity (RMSE: 0.25 to 0.30, R2 > 0.97) and downstream salinity (RMSE: 1.5 to 1.6, R2 > 0.88). This success is due to capacity of high temporal resolution as well as spatio-temporal dynamics of salinity variation. The LSTM structure has proven to be effective at capturing long-term temporal dependencies, such as seasonal discharge patterns, while XGB successfully models non-linear interactions between stations with the greatest success, particularly discharge-tidal level interactions. The ML/DL models are capable of successfully forecasting salinity which can open doors to data-driven water management in the Mekong Delta. Future studies should further add hydro-meteorological parameters, other hybrid architectures, and real-time prediction systems, which could be useful operationally and have wider applicability.https://doi.org/10.1007/s44163-025-00336-3Mekong deltaVietnamMachine learningDeep learningSalinity intrusionWater management
spellingShingle Phong Nguyen Duc
Thang Tang Duc
Giap Pham Van
Hoat Nguyen Van
Tuan Tran Minh
Predicting salinity levels in the Mekong delta (Viet Nam): analysis of machine learning and deep learning models
Discover Artificial Intelligence
Mekong delta
Vietnam
Machine learning
Deep learning
Salinity intrusion
Water management
title Predicting salinity levels in the Mekong delta (Viet Nam): analysis of machine learning and deep learning models
title_full Predicting salinity levels in the Mekong delta (Viet Nam): analysis of machine learning and deep learning models
title_fullStr Predicting salinity levels in the Mekong delta (Viet Nam): analysis of machine learning and deep learning models
title_full_unstemmed Predicting salinity levels in the Mekong delta (Viet Nam): analysis of machine learning and deep learning models
title_short Predicting salinity levels in the Mekong delta (Viet Nam): analysis of machine learning and deep learning models
title_sort predicting salinity levels in the mekong delta viet nam analysis of machine learning and deep learning models
topic Mekong delta
Vietnam
Machine learning
Deep learning
Salinity intrusion
Water management
url https://doi.org/10.1007/s44163-025-00336-3
work_keys_str_mv AT phongnguyenduc predictingsalinitylevelsinthemekongdeltavietnamanalysisofmachinelearninganddeeplearningmodels
AT thangtangduc predictingsalinitylevelsinthemekongdeltavietnamanalysisofmachinelearninganddeeplearningmodels
AT giapphamvan predictingsalinitylevelsinthemekongdeltavietnamanalysisofmachinelearninganddeeplearningmodels
AT hoatnguyenvan predictingsalinitylevelsinthemekongdeltavietnamanalysisofmachinelearninganddeeplearningmodels
AT tuantranminh predictingsalinitylevelsinthemekongdeltavietnamanalysisofmachinelearninganddeeplearningmodels