One of India's main economies, agriculture employs over half of the workforce. The industry faces many climatic risks, environmental degradation, and other externalities issues. Thus, researchers increasingly use machine learning (ML) methods to improve crop yield prediction. The research rigorously evaluates and incorporates dominant CYP features, reacting to varied techniques with artificial intelligence for agricultural productivity forecasts. It aims to develop reliable, efficient crop categorization and yield prediction methods to improve agricultural innovation. Comparing agricultural yield prediction ML methods is a key aspect of the work. These methods use climate, plant health, and growth stage datasets. Integrating such information, the scientists aim to develop models that accurately estimate yields, enabling agricultural producers to make informed decisions. This article compares ML agricultural yield prediction methods point-by-point. It details their performance, strengths, and weaknesses, and closes with the best way to improve agricultural production. The publication concludes by outlining future agricultural ML research areas. It emphasizes the need for ongoing innovation and integration of existing methods to meet agricultural industry objectives. The book aims to improve agricultural yield forecasts and promote sustainable agriculture by facilitating communication among farmers, policymakers, and researchers.
Nanban et al. (Wed,) studied this question.