Application of AI for Water Quality Assessment in Intelligent Hydration Systems

Resumen

This project evaluated the need for an additional physicochemical analysis of Elkay ezH2O drinking fountains at a private university, utilizing artificial intelligence (AI) to optimize decision-making and ensure water quality in an educational environment. In Peru, access to basic services remains a challenge, and this study explored how AI can enhance potable water management. Using PICO and PRISMA methodologies, key data were collected and analyzed. The bacterial colony growth analysis in two university drinking fountains revealed an inverse correlation between usage frequency and microbial proliferation. Fountain 1, located near restrooms and used by 150 people daily, exhibited lower bacterial growth (3 relative units), possibly due to constant water flow and frequent cleaning. In contrast, Fountain 2, situated in a less frequented area with only 20 daily users, showed significantly higher proliferation (8 relative units), suggesting that low water turnover and reduced maintenance promote bacterial development. These findings highlight the importance of continuous use and proper cleaning practices in maintaining potable water microbiological quality. AI optimization reduced literature collection time by 50%, critical evaluation by 42%, and data synthesis by 57%, while maintaining accuracy and consistency. The results confirm that a physicochemical analysis is necessary for both drinking fountains, thereby strengthening water safety and management in educational settings. Keywords: Water quality, artificial intelligence, physicochemical analysis, contamination.