Artificial Neural Network and Near Infrared Light in Water pH and Total Ammonia Nitrogen Prediction

Water quality plays an important role in aquaculture. The operation of a freshwater aquaculture fish farming is highly dependent on the ability to understand, monitor, and control physical chemical constituents water. pH total ammonia nitrogen (TAN) levels are two critical water parameters that affect growth rate health. However, TAN affected by uncontrollable factorse.g.weather, temperature, biological processes occurring Therefore, it monitor changes frequently maintain optimal conditions for habitats. Near infrared spectroscopy (NIR) has been extensively investigated as alternative measurement approach rapid without sample preparation. this research aims evaluate feasibility machine learning combined with NIR light predicting values system. proposed system contains three main components i.e.a multi-wavelength emitting diode (LED), sensing element, model i.e.artificial neural network (ANN). First, transmitted different wavelengths samples was measured using Then, actual were quantified conventional methods. Next, ANN used correlate transmittance values. results show four hidden neurons achieved best prediction performance mean square error (MSE) 0.1466 0.3136 correlation coefficient (R) 0.8398 0.9560 predictions, respectively. These ANNcoupled can be promisingly developed situ