AI Farm Assist: Integrating Machine Learning and Deep Learning for Smart Agricultural Recommendations

Agriculture holds a key place in the economies of many developing nations. Artificial intelligence integration stands to boost farming operations quite a bit in terms of efficiency and output. This work introduces AI Farm Assist. It functions as a web platform built around machine learning. The setup helps farmers via three main smart components. Those include crop suggestions, fertilizer advice, and spotting leaf diseases. Real agricultural data from Kaggle feeds into the system. That way, it delivers insights grounded in actual numbers. When it comes to suggesting crops, the CatBoost approach gets trained on various factors. Things like nitrogen levels, phosphorus, potassium, along with temperature, humidity, pH value, and rainfall all play a part. From there, it picks out the best crop match for specific conditions in the environment. Fertilizer recommendations rely on XGBoost instead. It draws from details such as soil variety, the type of crop involved, and how nutrients break down. Leaf disease detection uses a deep learning setup with MobileNetV2 at its core. That model handles classifying images of leaves to pinpoint plant illnesses. Each of these models hits accuracy rates upto 88 percent. Such results point to how well the method works overall. Farmers get a straightforward web interface through this system. It allows for fast, dependable choices in their daily agricultural tasks. Looking ahead, plans call for growing the dataset further. Real-time weather information could join in too. Plus, the disease prediction side might advance with newer deep learning designs.