Transfer Learning Techniques For Improving The Quality Of Prediction In Crop Yield

Abstract

Adequate agricultural methods are essential in a large region like India because of frequent floods, droughts and utmost climate change. However, still maximum agricultural fields are under progress, because of absence of distribution in ecosystem control technologies. Because of these obstacles, production of crops is not upgraded and that impacts the financial sector of agriculture. To avert the issues, Agricultural region have to forecast the crop yield should be estimated from the dataset utilizing the various crop yield estimation methods explained in this research. Various Machine Learning (ML) methods such as Random forest (RF), Support Vector Machine (SVM), K Nearest neighbor (KNN), convolution LSTM and 3D-CNN, Remote Sensing, XGBoost, Gradient Boosting, supervised machine learning technique (SMLT) are the techniques using in this literature survey. Agricultural production has been upgraded based on plant yield estimates. These techniques have respective outputs that helpful to forthcoming researchers about crop yield prediction.