ARCHIVES

The agricultural sector has many issues, including unpredictable weather, soil degradation, selecting the right crops, inefficient fertilizer usage, and losses due to plant diseases or weeds. Farmers typically rely on their experience and on unverified local recommendations, which causes them to have a much lower productivity and financial risk than they could otherwise have. Therefore, the agriculture industry is beginning to utilize Artificial Intelligence ("AI") and Machine Learning ("ML") to implement data driven and precision based decision making in agriculture. The authors conduct a review of Smart Crop Advisory Systems (SCAS) and the current literature on SCAS. Examples of SCAS include crop recommendations, fertilizers, plant disease detection, and weather advisories. Methods such as Random Forest and Convolutional Neural Networks (CNNs) are examined for their contribution to agricultural decision support. The review examines existing gaps in research and suggests that new, integrated and scalable SCAS must be developed to support sustainable agriculture.