Comparative Analysis of ML Algorithms and Smart UI for Optimum Crop Yield Prediction

Abstract

A key viewpoint for finding practical and effective solutions to crop yield problems is Machine Learning (ML). Using supervised learning, machine learning (ML) may predict a result from a set of predictors. We build an appropriate function from a set of variables that will map the input variable to the desired output in order to get the desired outcomes. Crop yield prediction comprises predicting crop production from historical data that includes elements related to various crops, such as temperature, humidity, pH, and rainfall. It provides us with a general concept of the best-forecasted crop that will be grown in the field under various weather circumstances. If crop productivity is projected based on numerous qualities by utilizing different datasets, the farmer community can gain significantly. The machine learning techniques Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression are used to make these predictions (LR). Which strategy achieves the highest crop forecast value is examined. The best crop yield model prediction is determined to be provided by the RF algorithm when the accuracy scores of the three applied methods are compared. To make it simpler to enter attribute values and obtain the corresponding prediction, we further built a user interface (UI).