Application of Machine Learning for Predicting the Crop Yield

A robust crop yield prediction model leveraging various Machine Learning techniques and added with a user- friendly web interface to obtain the details on expected yield of a given crop will help in the decision-making of the farmer. Remote sensing plays a vital role in crop yield prediction. Satellites collect data on various parameters that influence crop growth. Utilizing the key methods of data preprocessing to determine the optimum yield of a crop, the processes have been conducted systematically. To identify the optimal expected yield of a crop, various Machine Learning algorithms such as Linear Regression and Decision Tree Regression are applied. Furthermore, analysis is conducted by employing various regression metrics. Some of them are mean-squared error (MSE), mean-absolute error (MAE), r-squared metric. This is to enable easier comparison among the algorithms. In addition to that, cross-validation techniques like K-Fold Cross Validation are being applied to ensure greater accuracy of the model. These models are then integrated into a user-friendly interface driven by the Flask framework to present the optimal yield of a given crop systematically.