Sediment load prediction in Johor river: deep learning versus machine learning models
Abstract Sediment transport is a normal phenomenon in rivers and streams, contributing significantly to ecosystem production and preservation by replenishing vital nutrients and preserving aquatic life’s natural habitats. Thus, sediment transport prediction through modeling is crucial for predicting...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-02-01
|
| Series: | Applied Water Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s13201-023-01874-w |
| _version_ | 1797863882742562816 |
|---|---|
| author | Sarmad Dashti Latif K. L. Chong Ali Najah Ahmed Y. F. Huang Mohsen Sherif Ahmed El-Shafie |
| author_facet | Sarmad Dashti Latif K. L. Chong Ali Najah Ahmed Y. F. Huang Mohsen Sherif Ahmed El-Shafie |
| author_sort | Sarmad Dashti Latif |
| collection | DOAJ |
| description | Abstract Sediment transport is a normal phenomenon in rivers and streams, contributing significantly to ecosystem production and preservation by replenishing vital nutrients and preserving aquatic life’s natural habitats. Thus, sediment transport prediction through modeling is crucial for predicting flood events, tracking coastal erosion, planning for water supplies, and managing irrigation. The predictability of process-driven models may encounter various restrictions throughout the validation process. Given that data-driven models work on the assumption that the underlying physical process is not requisite, this opens up the avenue for AI-based model as alternative modeling. However, AI-based models, such as ANN and SVM, face problems, such as long-term dependency, which require alternative dynamic procedures. Since their performance as universal function approximation depends on their compatibility with the nature of the problem itself, this study investigated several distinct AI-based models, such as long short-term memory (LSTM), artificial neural network (ANN), and support vector machine (SVM), in predicting sediment transport in the Johor river. The collected historical daily sediment transport data from January 1, 2008, to December 01, 2018, through autocorrelation function, were used as input for the model. The statistical results showed that, despite their ability (deep learning and machine learning) to provide sediment predictions based on historical input datasets, machine learning, such as ANN, might be more prone to overfitting or being trapped in a local optimum than deep learning, evidenced by the worse in all metrics score. With RMSE = 11.395, MAE = 18.094, and R2 = 0.914, LSTM outperformed other models in the comparison. |
| first_indexed | 2024-04-09T22:43:56Z |
| format | Article |
| id | doaj.art-8db43a50af7e4dc4b9596b4d674d7e9b |
| institution | Directory Open Access Journal |
| issn | 2190-5487 2190-5495 |
| language | English |
| last_indexed | 2024-04-09T22:43:56Z |
| publishDate | 2023-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Applied Water Science |
| spelling | doaj.art-8db43a50af7e4dc4b9596b4d674d7e9b2023-03-22T12:01:38ZengSpringerOpenApplied Water Science2190-54872190-54952023-02-0113311310.1007/s13201-023-01874-wSediment load prediction in Johor river: deep learning versus machine learning modelsSarmad Dashti Latif0K. L. Chong1Ali Najah Ahmed2Y. F. Huang3Mohsen Sherif4Ahmed El-Shafie5Civil Engineering Department, College of Engineering, Komar University of Science and TechnologyDepartment of Civil Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul RahmanDam Safety Management & Engineering Group, Institute of Energy Infrastructure and Department of Civil Engineering, College of Engineering, Universiti Tenaga Nasional (UNITEN)Department of Civil Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul RahmanNational Water and Energy Center, United Arab Emirates UniversityDepartment of Civil Engineering, Faculty of Engineering, University of MalayaAbstract Sediment transport is a normal phenomenon in rivers and streams, contributing significantly to ecosystem production and preservation by replenishing vital nutrients and preserving aquatic life’s natural habitats. Thus, sediment transport prediction through modeling is crucial for predicting flood events, tracking coastal erosion, planning for water supplies, and managing irrigation. The predictability of process-driven models may encounter various restrictions throughout the validation process. Given that data-driven models work on the assumption that the underlying physical process is not requisite, this opens up the avenue for AI-based model as alternative modeling. However, AI-based models, such as ANN and SVM, face problems, such as long-term dependency, which require alternative dynamic procedures. Since their performance as universal function approximation depends on their compatibility with the nature of the problem itself, this study investigated several distinct AI-based models, such as long short-term memory (LSTM), artificial neural network (ANN), and support vector machine (SVM), in predicting sediment transport in the Johor river. The collected historical daily sediment transport data from January 1, 2008, to December 01, 2018, through autocorrelation function, were used as input for the model. The statistical results showed that, despite their ability (deep learning and machine learning) to provide sediment predictions based on historical input datasets, machine learning, such as ANN, might be more prone to overfitting or being trapped in a local optimum than deep learning, evidenced by the worse in all metrics score. With RMSE = 11.395, MAE = 18.094, and R2 = 0.914, LSTM outperformed other models in the comparison.https://doi.org/10.1007/s13201-023-01874-wLong short-term memory (LSTM)Artificial neural network (ANN)Support vector machine (SVM)Sediment transport prediction |
| spellingShingle | Sarmad Dashti Latif K. L. Chong Ali Najah Ahmed Y. F. Huang Mohsen Sherif Ahmed El-Shafie Sediment load prediction in Johor river: deep learning versus machine learning models Applied Water Science Long short-term memory (LSTM) Artificial neural network (ANN) Support vector machine (SVM) Sediment transport prediction |
| title | Sediment load prediction in Johor river: deep learning versus machine learning models |
| title_full | Sediment load prediction in Johor river: deep learning versus machine learning models |
| title_fullStr | Sediment load prediction in Johor river: deep learning versus machine learning models |
| title_full_unstemmed | Sediment load prediction in Johor river: deep learning versus machine learning models |
| title_short | Sediment load prediction in Johor river: deep learning versus machine learning models |
| title_sort | sediment load prediction in johor river deep learning versus machine learning models |
| topic | Long short-term memory (LSTM) Artificial neural network (ANN) Support vector machine (SVM) Sediment transport prediction |
| url | https://doi.org/10.1007/s13201-023-01874-w |
| work_keys_str_mv | AT sarmaddashtilatif sedimentloadpredictioninjohorriverdeeplearningversusmachinelearningmodels AT klchong sedimentloadpredictioninjohorriverdeeplearningversusmachinelearningmodels AT alinajahahmed sedimentloadpredictioninjohorriverdeeplearningversusmachinelearningmodels AT yfhuang sedimentloadpredictioninjohorriverdeeplearningversusmachinelearningmodels AT mohsensherif sedimentloadpredictioninjohorriverdeeplearningversusmachinelearningmodels AT ahmedelshafie sedimentloadpredictioninjohorriverdeeplearningversusmachinelearningmodels |