Estimation and detection of rice yields in Thailand using spatial and longitudinal data analysis

Abstract

The objectives of this research are to propose a model for estimating and detecting rice yields in Thailand, to investigate the factors related to the rice yields, to find the trend, and to construct the maps of rice yields in Thailand. A linear mixed model (LMM) including the spatial effects which follow the conditional autoregressive model (CAR) and the time effects which follow the first-order linear autoregressive (AR(1)) model is proposed. The estimated rice yields are used to construct the rice yield maps in Thailand. The dependent variables are the rice yield in each month of each province. The factors considered are rainfall, average temperatures and regions. The results indicate that the factors enfluencing the rice yields are rainfall, average temperatures and regions (North, Northeast, South, East, West, Central region is a refrence region). The trend also effects the rice yields. The rice yeilds maps are easy for readers to identify which areas have high or low yields and easy to compare the yields among areas by looking at their different colors.