Abstract
The aquaculture industry is pivotal in meeting the global demand for seafood, yet it faces challenges related to water quality management, disease control, and resource optimization. Sustaining ideal conditions for fish health and output is a difficulty for aquaculture. Conventional approaches to water quality monitoring are time-consuming and labour-intensive, which may result in lost productivity. This paper presents a design system which comprises of an array of sensors for monitoring critical water parameters such as temperature, pH, dissolved oxygen, and water levels. These sensors communicate data to a central processing unit, which utilizes machine learning models to predict optimal feeding schedules, detect anomalies, and initiate automatic corrective actions. The system aims to enhance fish health, improve yield, and reduce operational costs by providing aquaculture farmers with actionable insights and automated control mechanisms. Field tests conducted on a pilot fish pond demonstrated significant improvements in water quality stability, fish growth rates, and resource utilization efficiency. This technology encourages lucrative and sustainable fish farming by integrating sensors and automation to deliver real-time insights into important water quality metrics.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2024 Scholarly Journal of Science and Technology Research and Development