Artificial Neural Network and Near Infrared Light in Water pH and Total Ammonia Nitrogen Prediction
Keywords:
Artificial Neural Network, Near Infrared Light, Total Ammonia Nitrogen, pH, Multiple WavelengthsAbstract
Water quality plays an important role in aquaculture. The operation of a freshwater fish farming in aquaculture is highly dependent on one’s ability in understanding, monitoring, and controlling the physical and chemical constituent of water. pH and total ammonia nitrogen (TAN) values are two critical water quality parameters that affect the growth rate and healthiness of fish. However, pH and TAN values are affected by uncontrollable factors e.g. weather, temperature, and biological process that occur in the water. Thus, it is important to frequently monitor the changes of pH and TAN values in order to maintain an optimum condition for the freshwater habitats. Near infrared (NIR) spectroscopy has been widely studied as an alternative measurement approach for rapid quality control without a sample preparation. Hence, this research aims to evaluate the feasibility of machine learning coupled with NIR light in predicting the water pH and TAN values of a fish farming system. The proposed system contains three main components, i.e. a light emitting diode (LED) with multiple wavelengths, a light sensing element, and a machine learning model (i.e. artificial neural network (ANN)). First, the transmitted NIR light with different wavelengths from water samples were measured using the proposed system. After that, the actual pH and TAN values of the water samples were quantified using conventional methods. Next, ANN was used to correlate the measured NIR transmittance to the pH and TAN values. Results show that ANN that used four hidden neurons achieved the best prediction performance with mean square error (MSE) of 0.1466 and 0.3136; and correlation coefficient (R) values of 0.8398 and 0.9560 for the pH and TAN predictions, respectively. These findings show that ANN coupled with multiple wavelength NIR light is promising to be developed for in-situ water quality prediction without a sample preparation.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 International Journal of Integrated Engineering

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Open access licenses
Open Access is by licensing the content with a Creative Commons (CC) license.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.