Modeling and Forecasting of nanoFeCu Treated Sewage Quality Using Recurrent Neural Network (RNN)

Rapid industrialization and population growth cause severe water pollution increased demand. The use of FeCu nanoparticles (nanoFeCu) in treating sewage has been proven to be a space-efficient method. objective this work is develop recurrent neural network (RNN) model estimate the performance immobilized nanoFeCu treatment, thereby easing monitoring forecasting quality. In work, data was collected from local treatment plant. pH, nitrate, nitrite, ammonia were used as inputs. One-to-one three-to-three RNN architectures developed, optimized, analyzed. result showed that one-to-one predicted all four inputs with good accuracy, where R2 found within range 0.87 0.98. However, stability not model, chemically statistically correlated later model. best developed by single layer 10 neurons an average 0.91. conclusion, research provides support for designing prediction positive significance exploration smart plants.