Monitoring Water Quality Parameters in Aquaculture Using Edge Computing

Abstract

In this paper, we study an integration of temperature and pH sensors into the system to collect and monitor water quality parameters in aquaculture using a combination of edge computing (EC), Artificial Intelligence (AI) and Internet-of-Things (IoT). We develop and deploy a model using edge computing and a Long-Short Term Memory (LSTM) algorithm to forecast the aquaculture water quality at the network's edge. The system automatically operates and performs sampling, forecasting, and displaying predicting results on the user interface in real-time. The results of this paper demonstrate that the proposed solution with edge computing and LTSM can produce accurate forecasts with high reliability and prompt responses to water quality monitoring, thus reducing losses and harm due to water pollution in the aquaculture industry.