Abstract: Estimation of crop yield former to harvest is a significant concern in agriculture, as the changes in crop yield from year-to-year impact international business, food demand, and global market prices. Also, initial estimation of crop yield renders beneficial report to policy planners. Appropriate estimation of crop productivity is required for proficient planning of land usage and economic policy. The estimation will also help the farmers to make decisions such as the selection of alternative crops or in-order-to discard crops at an initial step in case of crucial situations. Further, estimating crop yield can ease the farmers to have a more-desirable perception on cultivation. Thus, it is essential to simulate and estimate the crop yield before cultivation for effective crop management and expected result. As there exists an affinity between crop yield and the factors influencing crop, machine learning methods may be efficient for yield estimations. In this research work, the Decision tree is applied for the crop yield prediction. The Decision tree is compared with binary SVM classifier and Naïve Bayes. Decision tree performs well for the crop production analysis.

Keywords: Decision tree, Binary SVM classifier, Naïve bayes.

PDF | DOI: 10.17148/IJARCCE.2021.10318

Open chat
Chat with IJARCCE