Self-Sustaining Greenhouse: Automated Climate and Nutrition Control

Traditional greenhouse farming methods face several challenges in maintaining optimal growing contains for tomatoes and mint plants. Manual irrigation practices often result in water wastage and inconsistent soil moisture levels, while arbitrary fertilizer application without precise NPK(Nitrogen, Phosphorus, Potassium) measurements leads to inefficient nutrient distribution and potential crop damage. Furthermore, unregulated temperature and humidity levels in conventional greenhouse can significantly impact plant growth and yield. Thes4 manual intervention-dependent systems are not only labour-intensive but also prone to human error, leading to increased operational costs and reduced crop productivity. This project implements an automated greenhouse system IoT and Machine Learning technologies through three essential modules. The irrigation module employs soil moisture sensors connected to a drip irrigation system, ensuring precise water delivery based on real-time moisture levels. The fertilizer management module utilizes NPK sensors to measure soil nutrient content, with ML algorithms processing this data to automate and optimize fertilizer dispensing schedules. The third module maintains optimal environmental conditions through automated temperature and humidity control systems. All these modules work cohesively through a central control system, eliminating the need for constant manual monitoring while ensuring efficient resource utilization. This data-driven automation approach not only reduces human intervention but also optimizes resource usage for improved crop yield.