Plataforma de monitoramento automatizado de CO₂ e qualidade da água em piscicultura com tecnologias abertas

Abstract

The growth of aquaculture, although strategic for global food security, poses challenges related to environmental sustainability, especially with regard to greenhouse gas emissions, such as carbon dioxide (CO₂). This thesis addresses the environmental challenges of intensive aquaculture, focusing on water quality and CO₂ emissions, a gas that is poorly monitored in the sector. The study developed an open multiparametric platform, called Pegad@, to monitor water quality and estimate CO₂ in excavated ponds, filling a scientific gap and offering an accessible and replicable tool. The research was structured on three fronts: a bibliometric study that mapped scientific production on carbon footprints in aquaculture, demonstrating that studies related to fish farming are still under-explored; a systematic review of Information and Communication Technology applications, with emphasis on the Internet of Things, highlighting trends and limitations in the adoption of these technologies in the aquaculture sector, revealing a significant gap in direct CO₂ measurements in these environments; and the development and practical testing of the Pegad@ prototype, consisting of low-cost microcontrollers, environmental sensors (temperature, dissolved oxygen, and CO₂), and cloud connectivity. The system allows remote data visualization and has the potential for integration with artificial intelligence (AI) techniques in the future. The results indicate that the platform is functional, replicable, and economically viable, making it a promising solution for the continuous monitoring of critical parameters in fish farming. The thesis contributes an approach with potential practical application to advance the quantification of the carbon footprint, aligning with the principles of Aquaculture 4.0 and reinforcing the importance of digitization as a strategy for more efficient and environmentally responsible production. Future work includes the incorporation of new sensors, standardization of physical components, and expansion of the database for AI-based predictive analytics.