This is the authors' abstract. We don't add key points for this paper.
India's economy heavily relies on agriculture, with over half of its land, which is 328.7 million hectares, designated as agricultural land. Agriculture generates around 17.8% of India's G.D.P. and over 18% of its exports in 2022-2023. More than half of India's workforce is employed in the agriculture industry. However, the success of agriculture in India is affected by several variables like soil quality, crop genetics, and climate. Precise yield prediction is necessary for creating import-export policies, increasing farmers' income, and for agri-commodity strategic action plans. It is also required for field-level quantification and financial evaluation. Yield prediction requires proficiency in climate change, water, pesticides, land area, weather factors, and soil characteristics. Recent studies have shown that machine learning algorithms driven by A.I. can predict wheat crop yields in India and other countries with promising results. This study compares various machine learning methods, such as Naïve Bayes (N.B.), K-Nearest Neighbor (K.N.N.), Gradient Boost (G.B.), Random Forest (R.F.), Decision Trees (D.T.), Extreme Gradient Boost (X.G.B.), and Artificial Neural Network (ANN) models. The results revealed that the best yield prediction models were the Random Forest (R.F.) and Extreme Gradient Boost (X.G.B.) models.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Mehla et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: