Short-term salinity prediction for coastal areas of the Vietnamese Mekong Delta using various machine learning algorithms: a case study in Soc Trang Province
Abstract Saltwater intrusion has significant and diverse impacts on agriculture, freshwater resources, and the well-being of coastal communities. To effectively address this issue, precise models for predicting saltwater intrusion must be developed, as well as timely information for reaction plannin...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-03-01
|
| Series: | Applied Water Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s13201-025-02419-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850181847971004416 |
|---|---|
| author | Le Thi Thanh Dang Hiroshi Ishidaira Ky Phung Nguyen Kazuyoshi Souma Jun Magome |
| author_facet | Le Thi Thanh Dang Hiroshi Ishidaira Ky Phung Nguyen Kazuyoshi Souma Jun Magome |
| author_sort | Le Thi Thanh Dang |
| collection | DOAJ |
| description | Abstract Saltwater intrusion has significant and diverse impacts on agriculture, freshwater resources, and the well-being of coastal communities. To effectively address this issue, precise models for predicting saltwater intrusion must be developed, as well as timely information for reaction planning. In this study, a spectrum of machine learning (ML) methodologies, specifically Random Forest Regression (RFR), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), and Ridge Regression (RR), was systematically employed to predict salinity levels within the coastal environs of the Mekong Delta, Vietnam. The input dataset comprised hourly salinity measurements from Tran De, Long Phu, Dai Ngai, and Soc Trang stations and hourly water-level data from Tran De station and hourly discharge data from the Can Tho hydrological station. The dataset was partitioned into two distinct sets for the purpose of model development and evaluation, employing a division ratio of 75% for training (constituting 8469 observations) and 25% for testing (comprising 2822 observations). The results indicate that ML models are suitable for short-term salinity prediction, with a forecasting time of up to 16 h in this area. These research findings highlight the potential of machine learning in addressing saltwater intrusion and provide valuable insights for developing appropriate response policies. By leveraging the strengths of these models and considering the optimal forecasting time, policymakers can make informed decisions and implement effective measures to mitigate the impacts of saltwater intrusion in the Mekong Delta. |
| format | Article |
| id | doaj-art-a66dac14a8c74594a9cd7b695446ed3f |
| institution | OA Journals |
| issn | 2190-5487 2190-5495 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Applied Water Science |
| spelling | doaj-art-a66dac14a8c74594a9cd7b695446ed3f2025-08-20T02:17:49ZengSpringerOpenApplied Water Science2190-54872190-54952025-03-0115412510.1007/s13201-025-02419-zShort-term salinity prediction for coastal areas of the Vietnamese Mekong Delta using various machine learning algorithms: a case study in Soc Trang ProvinceLe Thi Thanh Dang0Hiroshi Ishidaira1Ky Phung Nguyen2Kazuyoshi Souma3Jun Magome4Faculty of Environment, University of Science, Vietnam National University Ho Chi Minh CityInterdisciplinary Centre for River Basin Environment, University of YamanashiThu Duc People’s CommitteeInterdisciplinary Centre for River Basin Environment, University of YamanashiInterdisciplinary Centre for River Basin Environment, University of YamanashiAbstract Saltwater intrusion has significant and diverse impacts on agriculture, freshwater resources, and the well-being of coastal communities. To effectively address this issue, precise models for predicting saltwater intrusion must be developed, as well as timely information for reaction planning. In this study, a spectrum of machine learning (ML) methodologies, specifically Random Forest Regression (RFR), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), and Ridge Regression (RR), was systematically employed to predict salinity levels within the coastal environs of the Mekong Delta, Vietnam. The input dataset comprised hourly salinity measurements from Tran De, Long Phu, Dai Ngai, and Soc Trang stations and hourly water-level data from Tran De station and hourly discharge data from the Can Tho hydrological station. The dataset was partitioned into two distinct sets for the purpose of model development and evaluation, employing a division ratio of 75% for training (constituting 8469 observations) and 25% for testing (comprising 2822 observations). The results indicate that ML models are suitable for short-term salinity prediction, with a forecasting time of up to 16 h in this area. These research findings highlight the potential of machine learning in addressing saltwater intrusion and provide valuable insights for developing appropriate response policies. By leveraging the strengths of these models and considering the optimal forecasting time, policymakers can make informed decisions and implement effective measures to mitigate the impacts of saltwater intrusion in the Mekong Delta.https://doi.org/10.1007/s13201-025-02419-zSalinityMachine learning modelsOptimal timeCoastal communitiesVietnamese Mekong Delta |
| spellingShingle | Le Thi Thanh Dang Hiroshi Ishidaira Ky Phung Nguyen Kazuyoshi Souma Jun Magome Short-term salinity prediction for coastal areas of the Vietnamese Mekong Delta using various machine learning algorithms: a case study in Soc Trang Province Applied Water Science Salinity Machine learning models Optimal time Coastal communities Vietnamese Mekong Delta |
| title | Short-term salinity prediction for coastal areas of the Vietnamese Mekong Delta using various machine learning algorithms: a case study in Soc Trang Province |
| title_full | Short-term salinity prediction for coastal areas of the Vietnamese Mekong Delta using various machine learning algorithms: a case study in Soc Trang Province |
| title_fullStr | Short-term salinity prediction for coastal areas of the Vietnamese Mekong Delta using various machine learning algorithms: a case study in Soc Trang Province |
| title_full_unstemmed | Short-term salinity prediction for coastal areas of the Vietnamese Mekong Delta using various machine learning algorithms: a case study in Soc Trang Province |
| title_short | Short-term salinity prediction for coastal areas of the Vietnamese Mekong Delta using various machine learning algorithms: a case study in Soc Trang Province |
| title_sort | short term salinity prediction for coastal areas of the vietnamese mekong delta using various machine learning algorithms a case study in soc trang province |
| topic | Salinity Machine learning models Optimal time Coastal communities Vietnamese Mekong Delta |
| url | https://doi.org/10.1007/s13201-025-02419-z |
| work_keys_str_mv | AT lethithanhdang shorttermsalinitypredictionforcoastalareasofthevietnamesemekongdeltausingvariousmachinelearningalgorithmsacasestudyinsoctrangprovince AT hiroshiishidaira shorttermsalinitypredictionforcoastalareasofthevietnamesemekongdeltausingvariousmachinelearningalgorithmsacasestudyinsoctrangprovince AT kyphungnguyen shorttermsalinitypredictionforcoastalareasofthevietnamesemekongdeltausingvariousmachinelearningalgorithmsacasestudyinsoctrangprovince AT kazuyoshisouma shorttermsalinitypredictionforcoastalareasofthevietnamesemekongdeltausingvariousmachinelearningalgorithmsacasestudyinsoctrangprovince AT junmagome shorttermsalinitypredictionforcoastalareasofthevietnamesemekongdeltausingvariousmachinelearningalgorithmsacasestudyinsoctrangprovince |