Abstract

Big data in agriculture is an integration of computational methods and statistical analysis. The massive amounts of data generated in agriculture are no match for Big Data. When compared to more conventional approaches, it efficiently gathers and combines unique data for analysis. With the ability to recognize patterns in the data, Big Data may be of service in the agriculture sector. The sheer volume of data involved in processing such satellite photos might be daunting. The vast volumes of data generated during agricultural yield forecast are manageable with the help of Big Data Analysis. The goal of Machine Learning is to create efficient and quick learning algorithms that can anticipate outcomes based on data. In this study, we use two different methods for making predictions: the Multiple Linear Regression (MLR) model and an Artificial Neural Network (ANN). For the purpose of selecting the most effective characteristics of the yield components, multi-level regression (MLR) is a useful technique. The definition of an ANN is the structure of connections between several levels of neurons. The weights of connections are periodically adjusted via a learning process.

Description