Date of Publication :8th August 2024

Abstract:The optimization of crop yield has arisen as a major problem in modern agriculture. because of the growing demand for food and the necessity for efficient resource management. Accuracy and precision are hampered by the limits associated with conventional agricultural production and prediction techniques impacting crop optimization. The practice of projecting a crop's future output is known as crop yield prediction. while considering the dependent factors into account. While the methods of Machine Learning (ML) are widely used to forecast yield and their potential to make accurate assessments and possess an adequate understanding of crop attributes usually leads to more accurate forecasts and qualifies them for prediction. Using factors of environment such as Temperature, PH, Rainfall, Humidity and nutrient levels (N, P, K) plays a vital role in evaluating crop health and growth phases. This research explores the serviceability of algorithms for crop optimization by considering accuracy, among other criteria. The study's conclusion notes that it expects further developments in ML techniques and existing technology to produce comprehensive, affordable solutions for better estimates of crop and environmental states, enabling well-informed decision-making. This study examines the many ML approaches used in crop optimization and offers a thorough evaluation of the approaches' accuracy.

Reference :