Developing a Neural Network Based Microwave Sensing System for Accurate Salinity Prediction in Water

Abstract High and low salinity levels play a crucial role in the vitality of organisms and affect natural ecosystems, agricultural yields and human health. To mitigate the risks associated with high blood pressure and cardiovascular diseases, the World Health Organization (WHO) advocates reducing salt consumption among adults, suggesting an intake of no more than 5 g daily. In this study, a non-invasive microwave (MW) sensing approach, that is augmented by deep neural network (DNN) models is proposed to predict salinity levels. The MW detection measurement system, including a Horn antenna, has been developed to evaluate the salt content in bottled spring waters (BSWs). The system with DNN model provides a novel solution for real-time water quality monitoring. The input and output dataset for DNN model were generated using four different BSWs, each with a salt content ranging from 0 to 32 g and increased by 1 g. The developed DNN model, designed with six fully connected layers, uses reflection coefficients (RCs) as input dataset to predict salt content in grams accurately. The accuracy performance of the DNN model in various bandwidths was evaluated by dividing the 1–13 GHz range into 78 different bands and the lowest error rate was found to be in the 1–8 GHz bandwidth (2.18%). Furthermore, each BSW was measured five times, and the performance of the model was evaluated according to the number of measurements. In three or more measurements, the model demonstrated notable improvement(15.3%) in predicting salt content.