Current research in precision agriculture focuses on integrating machine learning and data analytics to predict crop diseases, optimize fertilization, and recommend suitable crops based on environmental factors. Our approach builds on these efforts by developing a comprehensive decision support tool that combines real-time weather data, convolutional neural networks (CNN) for disease detection, and machine learning algorithms for crop recommendation and fertilizer application, ensuring accurate and actionable insights for farmers. The aim is to revolutionize modern farming by utilizing advanced technology to optimize cultivation methods and ensure sustainability. The proposed system features multiple modules addressing critical aspects of farming, including disease classification and prevention, weather-based crop protection, and tailored crop recommendations based on specific soil and climate conditions, alongside a fertilizer calculator for optimal nutrient application. The proposed system leveraged convolutional neural networks (CNN) for accurate disease detection and prediction, demonstrating high accuracy and efficiency. Crop recommendation was based on a random forest model, while the weather-based crop protection feature utilized a decision tree, both contributing significantly to the overall effectiveness of the system. By offering farmers these data-driven insights, the system aims to significantly reduce crop losses, boost efficiency, and promote more environmentally sustainable farming methods. This system serves as an accessible, scalable solution for farmers, supporting informed decision-making and fostering a future of precision-driven agriculture.