Suitable crop suggesting system based on N.P.K. values using machine learning models

Abstract

Bangladesh is a country having an area of 1, 47,570 square kilometers in which a significant part is agricultural lands. As an agricultural country, we are mostly dependent on a cultivation which is dependent on the soil type. There are 3 most important nutrients in any soil, it's known as the primary macronutrients: Nitrogen (N), Phosphorus (P), and Potassium (K). Each of the primary nutrients is very essential in plant nutrition, serving a critical role in the growth and reproduction of the plant. We propose and demonstrate Crop Suggesting System based on N.P.K. values by using machine learning which will determine the best crop to grow in a particular soil based on some major criteria. This model will play a vital role in our agricultural sectors to fulfill the needs of our country by reaching the highest level of efficiency and ensure the best use of our arable lands. We have used four different machine learning algorithms named SVM, Adaboost, Random Forest and Logistic Regression and achieved a maximum of 98% accuracy using SVM.