She discussed a master's thesis in the Faculty of Engineering at Wasit University entitled Modelling the demand for biological oxygen and dissolved oxygen in the waters of the Tigris River (source of Azizia Point).
The letter, prepared by student Huda Yusuf Anad, aims to use bod and do as important indicators of water quality in the Tigris River at the Azizia point source (WWTP).
The research included the use of ANNs technology to predict and estimate BOD and do concentrations, and water samples for the period from October 2018 to March 2019 were collected weekly, from 22 points before the station, at the station and 10 km after the station. Every 500 metros all water samples were analyzed and studied for some physical and chemical parameters including pH, and the Multiple Linear Regression Model (MLR) was used to calibrate the ANN model and obtain some statistical transactions of the linear regression model.
The research results showed that the hidden layered neural network (10,8) was very accurate to predict the value of BOD and DO respectively and sensitivity analysis showed that discharge and distance had a greater impact on forecasting BOD and DOO concentrations and ann link transactions were equal to 0.987 And 0.937 for BOD and DO.As well, 34.36, 51.86 = RMSE and =MAPE %5.04, 4.46% for BOD and DO, respectively.
The results of the comparison between the linear regression model and the neural network model showed that networks can be used successfully and provide high accuracy to predict the value of DO concentrations, BOD as parameters of the quality of the uh.
106
13 comments
One post
I like it.
comment
Participation