Crop Yield Prediction in India Using Machine Learning Model

Abstract

The advancement of the global economy is greatly influenced by the agricultural sector. Agricultural production comprises one of India’s major industrial sectors, and economic growth heavily depends on it to maintain sustainability in remote counties. Undoubtedly one of the most significant issues in agricultural production is yield prediction, which will serve the government in formulating suitable planning strategies to improve productivity while also ensuring a reasonable price for impoverished farmers. Farming is dependent on the surroundings as well as the climate. Agriculture is influenced by many variables, including topsoil, weather, tides, nutrients, humidity, rainfall, harvests, pests, and botanicals. One of the key technologies for forecasting grain yields is machine learning. In this paper, we have employed four supervised machine learning approaches which are K-nearest neighbor (KNN), logistic regression, decision tree, and random forest. The factors taken into account in this model include fertilizer consumption, namely nitrogen (N), phosphorus (P), and potassium (K), as well as temperature, humidity, pH, and rainfall. With an astounding 99.77% accuracy, the random forest model was determined to be the most fit.