Water quality modelling of the River Ganga using artificial neural network with reference to the various training functions
The River Ganga (2,525 km long) is the largest River basin in India, covering 26.2 percent of India's total geographical area and recently granted living entity status by the court. It is the holiest River and also among the dirtiest in the world. That’s why it is mandatory to maintain its wate...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Action for Sustainable Efficacious Development and Awareness
2017-06-01
|
| Series: | Environment Conservation Journal |
| Subjects: | |
| Online Access: | https://journal.environcj.in/index.php/ecj/article/view/276 |
| _version_ | 1818893808012623872 |
|---|---|
| author | Anil Kumar Bisht Ravendra Singh R. Bhutiani Ashutosh Bhatt Krishan Kumar |
| author_facet | Anil Kumar Bisht Ravendra Singh R. Bhutiani Ashutosh Bhatt Krishan Kumar |
| author_sort | Anil Kumar Bisht |
| collection | DOAJ |
| description | The River Ganga (2,525 km long) is the largest River basin in India, covering 26.2 percent of India's total geographical area and recently granted living entity status by the court. It is the holiest River and also among the dirtiest in the world. That’s why it is mandatory to maintain its water quality (WQ). Though, monitoring and assessment of WQ of a River is a very challenging task. In this research work, Soft Computing (SC) based popular and commononly used Artificial Neural Network (ANN) technique has been used for modelling the WQ of the Ganga River by developing a prediction model based on six different training functions. Five sampling stations along this River stretch were selected from DEVPRAYAG to ROORKEE in the Uttarakhand state of India. The monthly data sets of five water quality parameters temperature, pH, dissolved oxygen (DO), biochemical oxygen demand (BOD) and total coliform (TC) for the time period from 2001 to 2015 have been taken. The feed forward error back propagation neural network method has been used to develop the WQ-prediction model by conducting various experiments following a neural network structure of 5-10-1, 0.1 as a training goal and various training functions. Using the Mean square error (MSE) statistical method the prediction performance of the developed model was evaluated. The model developed with traincgp (Conjugate Gradient with Polak-Ribiere Restarts) comes out to be the worst one (MSE=0.786) while the other model with trainlm (Levenberg-Marquardt backpropagation) rule proved to be the best one (MSE=0.163) among others. Consequently, it is found that ANNs are capable of predicting WQ of the River Ganga with acceptable results. |
| first_indexed | 2024-12-19T18:18:28Z |
| format | Article |
| id | doaj.art-235acc79f84e4a23a2e42e7bad23e734 |
| institution | Directory Open Access Journal |
| issn | 0972-3099 2278-5124 |
| language | English |
| last_indexed | 2024-12-19T18:18:28Z |
| publishDate | 2017-06-01 |
| publisher | Action for Sustainable Efficacious Development and Awareness |
| record_format | Article |
| series | Environment Conservation Journal |
| spelling | doaj.art-235acc79f84e4a23a2e42e7bad23e7342022-12-21T20:11:02ZengAction for Sustainable Efficacious Development and AwarenessEnvironment Conservation Journal0972-30992278-51242017-06-01181&210.36953/ECJ.2017.181206Water quality modelling of the River Ganga using artificial neural network with reference to the various training functionsAnil Kumar Bisht 0Ravendra Singh 1R. Bhutiani 2Ashutosh Bhatt 3Krishan Kumar4Deptt.of CS & IT, MJP Rohilkhand University, Bareilly, U.P., India Deptt.of CS & IT, MJP Rohilkhand University, Bareilly, U.P., India Limnology and Ecological Modelling Lab. Department of Zoology & Environmental Sciences, Gurukula Kangri Vishwavidyalaya, Haridwar - 249404 , Uttarakhand, IndiaDeptt.of CSE, BIAS, Bhimtal, U.K., IndiaDepartment of Computer Science, Gurukula Kangri Vishwavidyalaya Haridwar, U.K, IndiaThe River Ganga (2,525 km long) is the largest River basin in India, covering 26.2 percent of India's total geographical area and recently granted living entity status by the court. It is the holiest River and also among the dirtiest in the world. That’s why it is mandatory to maintain its water quality (WQ). Though, monitoring and assessment of WQ of a River is a very challenging task. In this research work, Soft Computing (SC) based popular and commononly used Artificial Neural Network (ANN) technique has been used for modelling the WQ of the Ganga River by developing a prediction model based on six different training functions. Five sampling stations along this River stretch were selected from DEVPRAYAG to ROORKEE in the Uttarakhand state of India. The monthly data sets of five water quality parameters temperature, pH, dissolved oxygen (DO), biochemical oxygen demand (BOD) and total coliform (TC) for the time period from 2001 to 2015 have been taken. The feed forward error back propagation neural network method has been used to develop the WQ-prediction model by conducting various experiments following a neural network structure of 5-10-1, 0.1 as a training goal and various training functions. Using the Mean square error (MSE) statistical method the prediction performance of the developed model was evaluated. The model developed with traincgp (Conjugate Gradient with Polak-Ribiere Restarts) comes out to be the worst one (MSE=0.786) while the other model with trainlm (Levenberg-Marquardt backpropagation) rule proved to be the best one (MSE=0.163) among others. Consequently, it is found that ANNs are capable of predicting WQ of the River Ganga with acceptable results.https://journal.environcj.in/index.php/ecj/article/view/276Artificial Neural Network (ANN)Water Quality (WQ)Dissolved Oxygen (DO)Biochemical Oxygen Demand (BOD)Total Coliform (TC)Mean Square Error (MSE) |
| spellingShingle | Anil Kumar Bisht Ravendra Singh R. Bhutiani Ashutosh Bhatt Krishan Kumar Water quality modelling of the River Ganga using artificial neural network with reference to the various training functions Environment Conservation Journal Artificial Neural Network (ANN) Water Quality (WQ) Dissolved Oxygen (DO) Biochemical Oxygen Demand (BOD) Total Coliform (TC) Mean Square Error (MSE) |
| title | Water quality modelling of the River Ganga using artificial neural network with reference to the various training functions |
| title_full | Water quality modelling of the River Ganga using artificial neural network with reference to the various training functions |
| title_fullStr | Water quality modelling of the River Ganga using artificial neural network with reference to the various training functions |
| title_full_unstemmed | Water quality modelling of the River Ganga using artificial neural network with reference to the various training functions |
| title_short | Water quality modelling of the River Ganga using artificial neural network with reference to the various training functions |
| title_sort | water quality modelling of the river ganga using artificial neural network with reference to the various training functions |
| topic | Artificial Neural Network (ANN) Water Quality (WQ) Dissolved Oxygen (DO) Biochemical Oxygen Demand (BOD) Total Coliform (TC) Mean Square Error (MSE) |
| url | https://journal.environcj.in/index.php/ecj/article/view/276 |
| work_keys_str_mv | AT anilkumarbisht waterqualitymodellingoftherivergangausingartificialneuralnetworkwithreferencetothevarioustrainingfunctions AT ravendrasingh waterqualitymodellingoftherivergangausingartificialneuralnetworkwithreferencetothevarioustrainingfunctions AT rbhutiani waterqualitymodellingoftherivergangausingartificialneuralnetworkwithreferencetothevarioustrainingfunctions AT ashutoshbhatt waterqualitymodellingoftherivergangausingartificialneuralnetworkwithreferencetothevarioustrainingfunctions AT krishankumar waterqualitymodellingoftherivergangausingartificialneuralnetworkwithreferencetothevarioustrainingfunctions |