Human survival depends on farming. Resource competition, population growth, and climate change are the key variables increasing food production. Smart farming extends the application of technology into existing farming principles to address such complex issues in agricultural production. To maintain sustainability and food security, machine learning in agriculture is crucial. Through agricultural production prediction, technology can help farmers in generating more. The paper's main objective is to predict crop yield using the factors of region, output, productivity, and region treated. Four machine learning-based approaches, including Decision Trees, Linear Regressions, Logistic Regressions, and Regression Models, have been used to assess agricultural productivity. As cross-validation techniques for validation, mean absolute error, mean square error, and root mean square error was used. Numerous machine learning techniques fall short of the Decision tree in comparison. The authors of this study utilized the imagery from remote sensing to extract characteristics using methods based on machine learning.

Artificial intelligence, Decision tree, linea r regression, Machine learning