Long memory conditional random fields on regular lattices

This paper draws its motivation from applications in geophysics, agricultural, and environmental sciences where empirical evidence of slow decay correlations have been found for data observed on a regular lattice. Spatial ARFIMA models represent widely used class spatial analyzing such data. Here, we consider their generalization to conditional autoregressive fractional integrated moving average (CARFIMA) models, larger long memory which allows wider range correlation behavior. For this provide detailed descriptions important representative make the necessary comparison with some other existing discuss inferential computational issues estimation, simulation process approximation. Results model fit predictive performance CARFIMA are also discussed through statistical analysis satellite land surface temperature