Abstract
Food storage security is critical to the national economy and people's lives. The environmental parameters of the granary should be accurately monitored in order to provide a better preservation environment for food storage. In this paper, we use temperature sensors to measure and collect grain temperature data for a period of 423 days from a real world granary, and collect the corresponding meteorological data from China Meteorological Data Network. We propose to leverage weather data to predict the average temperature of the grain pile with a support vector regression (SVR) approach. We first analyze the correlation between a large amount of historical data from the granary and the corresponding weather forecast data based on the Pearson correlation coefficient. In addition, we implement outlier detection and data normalization for data preprocessing. Finally, we incorporate different kernel functions in the SVR model to predict the temperature of grain pile using weather data. The results show that the proposed approach is highly accurate and the Gaussian radial basis function (RBF) kernel function achieves the best performance.