Time Series Prediction of Wheat Crop based on FB Prophet Forecast Framework

Abstract

The production of wheat plays an important role in the Indian economy. Wheat yield prediction is significant in trade, industry, and agriculture to increase profitability and better growth for farmers. We propose a prediction model to classify the wheat yield using time series analysis using the FB Prophet algorithm, which is considered as better than most of the other supervised learning models with respect to accuracy. [1]. The study aims to evaluate the predicted growth of wheat yield for the next five years. The dataset is collected by the government agency of India [2], considering the years 1997 to 2022, seasonal data, Gujarat state with four districts, and analysis is done for the Wheat/ Rabi crop. A total of 589 instances are collected from a dataset. We pre-process the data, train the data, and through the testing result set, the experimental result indicates the model achieves the lowest Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) for the summer wheat prediction (10.03 and 0.39 respectively) when the number of the layer in seasonality is yearly. The study will help the research community and other stakeholders to make plans for the next five years for the sustainable growth of India.