Water quality assurance in aquaculture ponds using Machine Learning and IoT techniques

Abstract

The following work proposes a framework for monitoring and forecasting water quality parameters (temperature and dissolved oxygen) at different scales of the aquaculture industry, either for post larval laboratories, in aquaculture farms or at the time of transporting the product to an aquaculture farm. The prototype system was implemented for the transportation of the aquaculture product and consists of a system of dissolved oxygen and temperature sensors that send the data from the sensors via Bluetooth Low Energy to a mobile application where they are processed and sent via internet to a web application so that users can receive alerts and visualize the monitoring data and the forecast model that was developed using a Long short-term memory (LSTM) neural network so that users can take measures in time to avoid losses in aquaculture production.