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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |