Salinity Prediction at the Bhairab River in the South-Western Part of Bangladesh Using Artificial Neural Network
2022
Khan Md. Rabbani Rasha
Salinity is a significant ecological element that influences the kind of creatures that reside in a water body. Salinity also determines the types of plants that will grow in a water body or on land that is fed by a water body. Three models were generated using an artificial neural network to estimate the salinity concentrations in the Bhairab River. Different combinations of variables were used to train the model using sample values of temperature, pH, turbidity, electrical conductivity (EC), color, total dissolved solids (TDS), total solids (TS), and suspended solids (SS). The performance of the models was determined using the statistical mechanism root mean square error (RMSE), coefficient of correlation (R), and determination coefficient (DC). ANN-2 model had the best performance which had the input variables electrical conductivity (EC), total dissolved solids (TDS), and total solids (TS). These three input variables were highly correlated with salinity. The correlation between the observed and the predicted values was also very high, the coefficient of correlation is 0.98 in validation. The RMSE value was very low for the model training and the value reduced even more after validation to 0.58.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Directory of Open Access Journals
Découvrez la collection de ce fournisseur de données dans AGRIS
