Smart Crop – Precision Agriculture using Machine Learning

Abstract

The agriculture industry in India makes a significant contribution of around 17% to Gross Domestic Product (GDP) of the country and serves as the primary employer for over 60% of the country's labor force. The sector has undergone significant changes because of the introduction of innovative technology, like vertical farming, among other examples. However, it is noteworthy that a considerable proportion of Indian farmers persist in employing traditional methods and adhering to cultural beliefs when managing their agricultural land. To exemplify, farmers adhere to their established agricultural protocols by patiently expecting favorable weather conditions, instead of modifying their techniques in response to evolving weather patterns. The primary aim of this research is to help farmers in making reasonable decisions regarding crop selection, considering their unique circumstances and the prevailing environmental conditions. The achievement of this objective will be aid through the advancement of prediction models that consider many factors that affect the growth of crops, such as soil nutrients, soil pH levels, humidity levels, and rainfall patterns. A range of machine learning models are utilized, encompassing Decision Tree (DT), Support Vector Machine (SVM), Logistic Regression (LR), and Gaussian Naïve Bayes (GNB).