Crop Recommend System using Random Forest Algorithm

In rural India, farming is the primary source of income for many people and plays a significant role in the economy of the nation. But compared to other nations, fewer crops are produced per hectare. Due to the low yield, small farmers find it difficult to make a living, which can result in financial difficulties and even suicides. This study offers a user-friendly method that uses pesticide and meteorological data to assist farmers in forecasting crop yields. The system employs GPS to locate the farmer and is accessible as a mobile app. Farmers input information about weather, pesticide use, soil type, and land size. After that, the system makes recommendations for the best crops to plant or forecasts the yield of a selected crop using machine learning. Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF), Multivariate Linear Regression (MLR), and K-Nearest Neighbor (KNN) are among the machine learning techniques used by the system. With a 95% accuracy rate, the Random Forest approach produced the greatest results out of all of these. With ANN at 92%, SVM at 90%, KNN at 88%, and MLR at 85%, other techniques also demonstrated strong performance. The algorithm not only forecasts yields but also gives farmers advice on when to use pesticides and fertilizers to enhance crop development. This technology uses meteorological and pesticide data to help farmers make better decisions, produce more crops, and earn more money.