Big Data in agriculture is an integration of computational methods and statistical analysis. The massive amount of agricultural data is manageable through Big Data. When compared to more conventional approaches, it efficiently gathers and compiles unique data for analysis. With the patterns gleaned from the data, Big Data is able to aid in the agricultural industry. The sheer volume of data involved in processing satellite photos might prove daunting. Big Data analysis is useful for managing the huge data volumes generated during agricultural productivity forecast. Machine learning seeks to improve the efficiency and accuracy of learning algorithms so that they can anticipate outcomes based on data with increasing speed and accuracy. Artificial neural networks (ANNs) and the multiple linear regression (MLR) model are used to make predictions. Multi-level regression (MLR) is a helpful method for determining which features of the yield components are the most important. An artificial neural network (ANN) is defined as a network of interconnected artificial neurons. Through a learning procedure, the connection weights between nodes are refined. The activation function will perform a transformation on the weighted input to generate the activation at the neuron’s output. The focus of this work is on enhancing NN’s capacity for prediction. According to the data, the ANN has a higher correlation coefficient with crop 1 than the MLR model does. There is a discrepancy of 0.01, 0.02, 0.03, 0.04, 0.02, 0.03, 0.04, 0.03, 0.03, and 0.03, respectively, between regions 1 and 6. The ANN model outperforms the MLR model for crop 2 by a margin of 0.3 in region 3 and 0.2 in the other areas, as measured by improvements in correlation coefficients.