Forecasting cereals production based on regression and back-propagation (BP) network model in Eastern Province, Rwanda

In developing countries such as Rwanda whose economy depends on agriculture and where more than 70% of the population relies on rain-fed agriculture for their livelihoods and which is among the highly populated countries in the world, changes in temperature, precipitation, humidity and arable land extremely affect the agricultural production. In response to these changing risks, forecasting cereals production study based on regression and back-propagation (BP) network model was carried out in Eastern Province of Rwanda. 22 years data from 1989 to 2010 of temperature, precipitation, humidity, percentage of cultivated area and cultivated area were taken as dependent variables and cereals production in the same period was considered as independent variable for the regression, while temperature, precipitation, humidity, percentage of cultivated area and cultivated area constituted the input variables to build BP Network model for forecasting cereals production. The model was consistently verified; results were efficient and showed that the general trend of cereals production in Eastern Province of Rwanda is increasing.   Key words: Cereals production, regression, back-propagation (BP) Network model, forecasting, Eastern Province of Rwanda.