70% of Indian population depend on farming, agriculture and contribute 18% of GDP. According to government statistics, 60% of crop production depends on monsoon rainfall. Hence, it is foremost important to understand the factors affecting the crop yield and there is a need of development of prediction model for crop yield prediction. For experimental evaluation, we have taken Meteorological Data of Chhattisgarh (CG) in which gathered crop production data in different districts of CG in last years, also collected rainfall in the last years in different districts of CG. We have proposed a machine learning model for crop yield prediction, in which dimension reduction algorithm applied to reduce the dimension of gathered data; it will suppress those data which will affect the prediction algorithm accuracy. For preprocessing of input dataset, we have used PCA; further, K-medoid clustering algorithm has been applied to improve the prediction accuracy. In proposed model, we have used the MATLAB curve fitting tool to find the relation between dependent and independent variables. Finally, we have applied support vector regression as machine learning classifier and achieved an average accuracy of 97%.
CITATION STYLE
Khan, H., & Ghosh, S. M. (2020). Crop Yield Prediction from Meteorological Data Using Efficient Machine Learning Model. In Lecture Notes on Data Engineering and Communications Technologies (Vol. 36, pp. 565–574). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-1002-1_57
Mendeley helps you to discover research relevant for your work.