Smart IoT Fresh Water Fish Pond Water Quality Monitoring and Control System for Yield Prediction Tertiary Education Trust Fund (TETFUND NRF, 2020-2024)

This award was made under the 2020 TETFund National Research Fund for implementing a Smart IoT Fresh Water Fish Pond Water Quality Monitoring and Control System for Yield Prediction. Research to generate water chemistry parameters using IoT sensors and build machine learning models.

The Aim of the project is to develop a smart agricultural system in which fresh water fishes are grown in conventional aquaculture and aquaponics pond systems where the physico-chemical water parameters and fish  physiological growth parameters are monitored and controlled using diverse IoT sensors.

Objectives

Set up a mobile aquaponics pond system where fish are cultured and plant grown at the same time and identification of the plant-animal biomass relationships.

Collect real-time data from the fresh water fish ponds using the IoT sensors and store the data in an indigenous cloud data repository made available to scientists.

Design and Implement a GSM-edge-cloud orchestration for the fish pond controller system which controls the water sensors and automatically send the data read by the sensors to the cloud repository.

Determination of production parameters such as weight gain, specific growth rate, feed conversion ratio, condition factor, normalized biomass index and the cost resulting from the culture of the fish using varied water quality monitoring and control systems.

Develop a machine learning model for the prediction fish growth and yield after using the dataset generated by the sensors to train the machine.

The study involves

Ø setting up two experimental fish pond sites, consisting of 30 ponds (12 conventional aquaculture ponds, 12 aquaponics pond systems and 6 control ponds) for the purposes of replications, which enhance higher level of result accuracy. Each system will have a control experiment with which the results of the IoT smart ponds are compared.

Ø Deployment of low power and low cost water quality sensors in a fresh water aquaponics system that monitors pH level, dissolved oxygen, temperature, ammonia, nitrate and nitrite, and turbidity of the water measuring the physiological growth parameters in the fish ponds that affect fish growth and yield.

Ø Design and Implement a GSM-edge-cloud orchestration for the fishpond controller system which controls the water sensors and automatically send the data read by the sensors to the cloud repository.

Ø Collect real-time data from the fresh water fish ponds using the IoT sensors and store the data in an indigenous cloud data repository made available to scientists.

Ø Determination of production parameters such as weight gain, specific growth rate, feed conversion ratio, condition factor, normalized biomass index and fish biochemical, hematological oxidative stress and histopathological parameters.

Ø Develop a machine learning model for automated prediction fish growth and yield after using the dataset generated by the sensors to train the machine

Ø Set up a mobile aquaponics pond system for the identification of its plant-animal biomass relationships