Smart Crop Advisory System for Small and Marginal Farmers

The Smart Crop Advisory System provides an effective solution to the challenges faced by small and marginal farmers. By using soil parameters, environmental conditions, and machine learning techniques, the system helps in recommending suitable crops and improving agricultural productivity. The inclusion of a disease detection module further supports farmers by identifying plant health issues at an early stage and suggesting basic remedies. The system is designed to be simple and user-friendly, making it accessible even to farmers with limited technical knowledge. It reduces dependency on traditional guess-based methods and enables data-driven decision-making. Overall, the project contributes to improving efficiency, reducing crop losses, and supporting sustainable farming practices.

Mohanty, S. P., Hughes, D. P., and Salathé, M., “Using Deep Learning for Image-Based Plant Disease Detection,” published in Frontiers in Plant Science, 2016, provided important insights into image-based disease detection using deep learning techniques, which influenced the design of the disease detection module in this project. Goodfellow, I., Bengio, Y., and Courville, A., in their book Deep Learning, MIT Press, 2016, offered foundational knowledge on neural networks and deep learning concepts that support the implementation of intelligent models in this system. The Scikit-learn Developers’ work on Machine Learning in Python (2023) contributed to understanding and implementing machine learning algorithms for crop recommendation. The TensorFlow Team’s research on Deep Learning and Image Classification Techniques (2023) helped in building and understanding the image processing model used for plant disease detection. Guidelines from the Food and Agriculture Organization in the E-Agriculture Strategy Guide provided valuable information about agricultural practices and the role of digital technologies in farming systems.