Crop Yield Prediction using Machine Learning

Information Science and Engineering

The quantity of harvest produced per acre of land is known as crop yield. Understanding this number is essential since it helps evaluate food security and explains why potato prices change annually. the subsequent year. In this project, We'll research several techniques for predicting agricultural yield.This work demonstrates that they may also be completed using machine learning methods like the Random Forest and Kalman Filter methods. To complete the greatest outcomes in crop production prediction, we look at multiple iterations of machine learning algorithms and data processing methodologies in this work. 8 To get an extremely precise yield forecasting percentage, one could use the Random Forest Algorithm with Kalman Filter. Forecasting crop yields is necessary for farmers to make it feasible and to make wellinformed decisions on crop management, harvest, and sales. Predicting crop yield with machine learning 1 methods has shown a lot of potential. This study aims to assess the agricultural production predicting performance of a range of methods for machine learning employing historical crop, weather, and soil data. Among Artificial Neural Networks: Artificial Decision Support Systems trees, random forests as well as support vector machines .The research uses data from several crops, such as wheat, corn, and soybeans, and evaluates the usefulness of metrics such as root mean square error and mean absolute error by all algorithms.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.