Crop Recommendation and Production Prediction

Agriculture has always been a significant occupation across the world, and its products are essential to numerous industries, including clothing and food production. Therefore, our research aimed to predict crop types and yield using advanced machine learning models such as SVM, Random Forest, Decision Trees, and XGBoost. We considered several factors such as crop meteorological conditions, environmental factors, and rainfall to train our models. Our study produced remarkable findings that can help minimize losses in agriculture by selecting suitable crops for a particular land area. We employed two machine learning models in our research. In the first model, we identified the most suitable crops for a particular land area. Then, we used the output of the first model to train the second machine learning model. This second model predicts the crop yield percentage, helping farmers to identify the best crops that provide a high yield for a specific region based on user-provided parameters. Our research produced performance improvements over existing state-of-the-art methods in predicting crop types and yield. Our models demonstrated higher accuracy in identifying suitable crops and predicting crop yield. These findings have significant implications for the agriculture industry, helping farmers to increase production and financial stability while reducing the number of suicides in the agriculture sector. In conclusion, our research contributes to the development of advanced machine learning models for predicting crop types and yield, providing insights into sustainable agricultural practices.