The main aim of the project is to create a predictive system that can suggest the most suitable crops and fertilizers based on key environmental and soil-related factors. These factors include soil type, pH level, nitrogen, phosphorus, potassium content, and weather parameters such as rainfall and temperature. With increasing concerns around food security and sustainable farming practices, there is a need for smart, technology-driven solutions that can help optimize crop selection and fertilizer use. This project seeks to address that problem using machine learning models that apply regression and classification techniques to historical agricultural data. By the end of the project, students are expected to have developed a fully functional prototype that predicts appropriate crops and fertilizers for specific regions or soil conditions. The system should provide practical, real-world value by reducing agricultural waste and improving farm productivity, while also enhancing the students' skills in machine learning, data preprocessing, model training, and application development.
The project follows a structured, twelve-week implementation plan that begins with foundational understanding and concludes with a final presentation. In the initial phase, students will learn the backbone of the machine learning model, including its structure and functions. They will then collect, create, or download relevant agricultural datasets containing information on soil properties and weather conditions. Next, they will explore and implement various machine learning libraries in Python, and start constructing a basic framework for the recommendation model.
In the middle phase of the project, students will focus on training the model using a variety of datasets to ensure it can recommend suitable fertilizers and crops for different scenarios. The model will then be tested with new input data, and improvements will be made to enhance its accuracy. In later weeks, the students will work on integrating the model into a user-friendly interface that allows users to input data and receive intelligent suggestions. The final stages of the project involve system testing, detailed documentation, and delivering a team-based presentation showcasing the working model. Throughout the process, students are expected to adhere to ethical coding practices, avoid plagiarism, and follow consistent documentation and development standards.
