Crop Yield Prediction Using Machine Learning Algorithm

Abstract

Populace development rates are on a phenomenal development direction, expanding people's nourishment needs. In spite of the fact that rural innovation is progressing, it is vital to note that characteristic assets such as water and soil supplements are constrained. Determining rural generation can make strides asset administration, budgetary choices, supplement arranging, soil wellbeing, and give early caution of issues within the nourishment chain. In the realm of crop yield prediction, machine learning plays a pivotal role in addressing the complexities of agricultural systems. By integrating methods like the Takagi-Sugeno-Kang Fuzzy Model (TSK) and the Mini-batch Gradient Descent (MBGD) algorithm, this study aims to enhance accuracy and adaptability in forecasting multiple crop yields simultaneously as this approach not only captures intricate relationships between different crops but also handles uncertainties inherent in real-world data, offering a transparent and interpretable framework for decision support in agricultural management, while optimizing computational efficiency through quicker convergence and accommodates non-linear relationships between input variables and crop yields, reduces computational costs associated with large datasets, thereby enhancing the model's scalability and performance in real-time agricultural predictions. Overall, the integration of the TSK model with MBGD represents a robust approach for precise and reliable crop yield forecasting, supporting informed decision-making and sustainable agricultural practices.