Sustainable Aquaculture in Smart Cities Cloud-integrated Internet of Things (IOT) Framework with Soil and Water Assessment Tool (SWAT) and Fuzzy Logic Models for Water Quality Monitoring

Abstract

Aquaculture development in smart cities is a sustainable attempt to bring environmentally friendly, transformative food production to urban centers and a new direction in the management of urban environments with the help of Internet of Things (IoT) applications. Nonetheless, the adoption can become inhibited by such challenges as high initial investments to create an IoT infrastructure and implement technologies, particularly in developing regions. The paper examines the possibilities of using IoT applications to help promote sustainable aquaculture through formulating a Soil and Water Assessment Tool (SWOT) model over a given watershed and partitioning it into topography and land use as sub-basins. The model runs in an iterative calibration loop that proceeds to re-minimize differences between simulated and measured water quality data, using strategically positioned sensors with links to a central data acquisition system via the wireless network. The accuracy of a prediction model, based on fuzzy logic, with real-time sensor data, SWAT runs, and future weather predictions, is established and optimised. Advancements in technology, such as the combination of Wireless Sensor Networks (WSNs) and cloud computing, have made it possible to collect, process, and analyse data in a scalable and secure manner. This enables simulations of water quality to be accurate, as seen with the SWAT model. Using the degree of membership, the water quality values between 0.3 and 0.9 are considered. The paper emphasizes the remarkable insights of IoT towards the sustainable development in aquaculture; in the future, it can be merged with the smart city significantly. Real-time water quality parameters (temperature, pH, dissolved oxygen, and conductivity), historical and real-time climate datasets (precipitation, temperature, and wind patterns) obtained from National Oceanic and Atmospheric Administration (NOAA) databases, and SWAT simulation outputs formed the core datasets for developing and calibrating the fuzzy logic-based predictive model.