Use of machine learning and weather predictions to bridge the gap between consumer demands and the market requirements of food crops

Abstract

Bangladesh, being an Agro-Economy based country, is lacking the technological improvements regarding Supply-Demand ratio of Food Supply to the citizens. Since the recent price hike of onions in 2019, it is evident that such technological disadvantages bring severe losses to the projection of demand of food items and can bring significant hindrance to the economy of the country, adversely affecting the daily lives of the people. Therefore, we propose this paper to bridge the gap between Production, Consumption, Import-Export and Supply-Demand ratio using Linear Regression, Polynomial Regression, and Random Forest Techniques on datasets including and not limited to Average Min-Max Monthly Temperature, Average Monthly Rainfall and Humidity, Land Area-Production-Yield ratios, and Daily Consumption etc. This static dataset contains previous years’ data taken from the Yearbook of Agricultural Statistics and Bangladesh Agricultural Research Council of those crops according to the area. The six year production period of 2013 to 2018 and the weather data set of 2008-2018 of Bangladesh have been taken into account in the formation of this dataset to corroborate learning and training of the algorithms and elevating the accuracy rate of the projection. The Cultivation Area estimates acquired are to be cross-verified with Satellite Images.