Bidirectional Long Short-Term Memory (BILSTM) - Support Vector Machine: A new machine learning model for predicting water quality parameters
Water pollution threatens human health, agriculture, and ecosystems. Accurate prediction of water quality parameters is crucial for effective protection. We suggest a novel hybrid deep learning model that enhances the efficiency of Support Vector Machines (SVMs) in predicting Electrical Conductivity...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Ain Shams Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090447923003994 |
| _version_ | 1797253978721878016 |
|---|---|
| author | Zahra Jamshidzadeh Mohammad Ehteram Hanieh Shabanian |
| author_facet | Zahra Jamshidzadeh Mohammad Ehteram Hanieh Shabanian |
| author_sort | Zahra Jamshidzadeh |
| collection | DOAJ |
| description | Water pollution threatens human health, agriculture, and ecosystems. Accurate prediction of water quality parameters is crucial for effective protection. We suggest a novel hybrid deep learning model that enhances the efficiency of Support Vector Machines (SVMs) in predicting Electrical Conductivity (EC) and Total Dissolved Solids (TDS). Our model combines Bidirectional Long Short-Term Memory (BILSTM) and SVMs to extract essential features and predict output variables. We evaluated the models using input parameters (PH, Ca++, Mg++, Na+, K+, HCO3, SO4, and Cl) for one, two, and three-day predictions. Employing the Ali Baba and Forty Thieves (AFT) optimization algorithm, we identified optimal input combinations. The BILSTM-SVM model accurately estimated TDS values, with MAPE values of 2%, outperforming other models. Similarly, it successfully predicted EC values, exhibiting an R2 value of 0.94. Our proposed model processes complex relationships and captures crucial features from the data, contributing to improved water quality prediction. |
| first_indexed | 2024-03-09T07:35:21Z |
| format | Article |
| id | doaj.art-79cb6928c11741b49b63c20bfb90ad4c |
| institution | Directory Open Access Journal |
| issn | 2090-4479 |
| language | English |
| last_indexed | 2024-04-24T21:42:39Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ain Shams Engineering Journal |
| spelling | doaj.art-79cb6928c11741b49b63c20bfb90ad4c2024-03-21T05:36:26ZengElsevierAin Shams Engineering Journal2090-44792024-03-01153102510Bidirectional Long Short-Term Memory (BILSTM) - Support Vector Machine: A new machine learning model for predicting water quality parametersZahra Jamshidzadeh0Mohammad Ehteram1Hanieh Shabanian2Department of Civil Engineering, University of Kashan, Kashan, IranDepartment of Water Engineering, Semnan University, Semnan, IranComputer Science Department, Western New England University, Springfield, USA; Corresponding author.Water pollution threatens human health, agriculture, and ecosystems. Accurate prediction of water quality parameters is crucial for effective protection. We suggest a novel hybrid deep learning model that enhances the efficiency of Support Vector Machines (SVMs) in predicting Electrical Conductivity (EC) and Total Dissolved Solids (TDS). Our model combines Bidirectional Long Short-Term Memory (BILSTM) and SVMs to extract essential features and predict output variables. We evaluated the models using input parameters (PH, Ca++, Mg++, Na+, K+, HCO3, SO4, and Cl) for one, two, and three-day predictions. Employing the Ali Baba and Forty Thieves (AFT) optimization algorithm, we identified optimal input combinations. The BILSTM-SVM model accurately estimated TDS values, with MAPE values of 2%, outperforming other models. Similarly, it successfully predicted EC values, exhibiting an R2 value of 0.94. Our proposed model processes complex relationships and captures crucial features from the data, contributing to improved water quality prediction.http://www.sciencedirect.com/science/article/pii/S2090447923003994Water qualityDeep learningOptimizationTotal dissolved solidsBidirectional LSTM |
| spellingShingle | Zahra Jamshidzadeh Mohammad Ehteram Hanieh Shabanian Bidirectional Long Short-Term Memory (BILSTM) - Support Vector Machine: A new machine learning model for predicting water quality parameters Ain Shams Engineering Journal Water quality Deep learning Optimization Total dissolved solids Bidirectional LSTM |
| title | Bidirectional Long Short-Term Memory (BILSTM) - Support Vector Machine: A new machine learning model for predicting water quality parameters |
| title_full | Bidirectional Long Short-Term Memory (BILSTM) - Support Vector Machine: A new machine learning model for predicting water quality parameters |
| title_fullStr | Bidirectional Long Short-Term Memory (BILSTM) - Support Vector Machine: A new machine learning model for predicting water quality parameters |
| title_full_unstemmed | Bidirectional Long Short-Term Memory (BILSTM) - Support Vector Machine: A new machine learning model for predicting water quality parameters |
| title_short | Bidirectional Long Short-Term Memory (BILSTM) - Support Vector Machine: A new machine learning model for predicting water quality parameters |
| title_sort | bidirectional long short term memory bilstm support vector machine a new machine learning model for predicting water quality parameters |
| topic | Water quality Deep learning Optimization Total dissolved solids Bidirectional LSTM |
| url | http://www.sciencedirect.com/science/article/pii/S2090447923003994 |
| work_keys_str_mv | AT zahrajamshidzadeh bidirectionallongshorttermmemorybilstmsupportvectormachineanewmachinelearningmodelforpredictingwaterqualityparameters AT mohammadehteram bidirectionallongshorttermmemorybilstmsupportvectormachineanewmachinelearningmodelforpredictingwaterqualityparameters AT haniehshabanian bidirectionallongshorttermmemorybilstmsupportvectormachineanewmachinelearningmodelforpredictingwaterqualityparameters |