Version 1
: Received: 5 February 2023 / Approved: 6 February 2023 / Online: 6 February 2023 (07:37:03 CET)
Version 2
: Received: 27 February 2023 / Approved: 27 February 2023 / Online: 27 February 2023 (07:25:06 CET)
Selim, A.; Shuvo, S.N.A.; Islam, M.M.; Moniruzzaman, M.; Shah, S.; Ohiduzzaman, M. Predictive Models for Dissolved Oxygen in an Urban Lake by Regression Analysis and Artificial Neural Network. Total Environment Research Themes 2023, 100066, doi:10.1016/j.totert.2023.100066.
Selim, A.; Shuvo, S.N.A.; Islam, M.M.; Moniruzzaman, M.; Shah, S.; Ohiduzzaman, M. Predictive Models for Dissolved Oxygen in an Urban Lake by Regression Analysis and Artificial Neural Network. Total Environment Research Themes 2023, 100066, doi:10.1016/j.totert.2023.100066.
Selim, A.; Shuvo, S.N.A.; Islam, M.M.; Moniruzzaman, M.; Shah, S.; Ohiduzzaman, M. Predictive Models for Dissolved Oxygen in an Urban Lake by Regression Analysis and Artificial Neural Network. Total Environment Research Themes 2023, 100066, doi:10.1016/j.totert.2023.100066.
Selim, A.; Shuvo, S.N.A.; Islam, M.M.; Moniruzzaman, M.; Shah, S.; Ohiduzzaman, M. Predictive Models for Dissolved Oxygen in an Urban Lake by Regression Analysis and Artificial Neural Network. Total Environment Research Themes 2023, 100066, doi:10.1016/j.totert.2023.100066.
Abstract
The paper portrays predictive models for dissolved oxygen (DO) levels in an urban lake using common water quality parameters like Temperature, pH, Conductivity and ORP at a time. Data were sampled using three real-time, industry-standard sensors, OPTOD, CTZN, and PHEHT, and then interpolated using the ArcGIS kriging technique. Correlation studies were analyzed through the ML algorithm, the correlation study signified a highly positive correlation between DO and other water parameters and the model was corroborated by R-score in order to create the linear regression model. In addition, an artificial neural network- a machine learning method using the Levenberg-Marquardt algorithm was developed to build a model to predict the do as well. Then, the performance of the models was validated and also the R2 accuracy was checked of the predicted data against the actual data. Thus, the appropriateness of the ANN model for the forecasting of investigated attributes is indicated by the fact that the discrepancy between the forecasted and real ANN model is significantly lesser than that of the regression model. However, the model can be used to reveal DO data from unknown urban lake water.
Environmental and Earth Sciences, Environmental Science
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Received:
27 February 2023
Commenter:
Abu Selim
Commenter's Conflict of Interests:
Author
Comment: The title changed to "Predictive Models for Dissolved Oxygen in an Urban Lake by Regression Analysis and Artificial Neural Network"
Firstly, we tried to model one water quality parameter, then the regression model was compared to a newly developed model by the artificial neural network with the levenberg algorithm for the same parameter. However, we tried to illustrate the detail of both models' errors.
Commenter: Abu Selim
Commenter's Conflict of Interests: Author
Firstly, we tried to model one water quality parameter, then the regression model was compared to a newly developed model by the artificial neural network with the levenberg algorithm for the same parameter. However, we tried to illustrate the detail of both models' errors.