Crop Type Prediction: A Statistical and Machine Learning Approach

Farmers' ability to accurately anticipate crop type is critical to global food production and sustainable smart cities since timely decisions on imports and exports, based on precise forecasts, are crucial to the country's food security. In India, agriculture and allied sectors constitute the country's primary source of revenue. Seventy percent of the country's rural residents are small or marginal agriculture producers. Cereal crops such as rice, wheat, and other pulses make up the bulk of India's food supply. Regarding cultivation, climate and soil conditions play a vital role. Information is of utmost need in predicting which crop is best suited given the soil and climate. This paper provides a statistical look at the features and indicates the best crop type on the given features in an Indian smart city context. Machine learning algorithms like k-NN, SVM, RF, and GB trees are examined for crop-type prediction. Building an accurate crop forecast system required high accuracy, and the GB tree technique provided that. It outperforms all the classification algorithms with an accuracy of 99.11% and an F1-score of 99.20%.

Automated summary

Farmers' ability to forecast crop types accurately plays a critical role in global food production and sustainable smart cities. Timely decisions on imports and exports based on precise predictions are crucial for a country's food security. This study focuses on India, where agriculture is the primary source of revenue, and analyzes statistical features to determine the best crop type in the context of an Indian smart city. Machine learning algorithms such as k-NN, SVM, RF, and GB trees are examined, with GB trees demonstrating the highest accuracy of 99.11% and an F1-score of 99.20%.