Crop yields vary over space and time. At large scales, both spatial and temporal variability are due to the interaction of soil heterogeneities, inter-annual weather variability and changes in technology. The objective of this study was to determine the stability of spatial and temporal patterns of peanut yield based on dynamic crop simulation models and statistical county yield estimates. The Cropping System Model (CSM)-CROPGRO-Peanut model, which is part of the Decision Support System for Agrotechnology Transfer (DSSAT), was used to simulate peanut yield for 53 of the 65 peanut-producing counties in Georgia during the period from 1992 to 2004. County yield estimates for the same period and locations were obtained from the USDA-NASS. Crop model inputs included the genetic characteristics for the Georgia Green peanut variety, soil profile data from the USDA-National Resources Conservation Service (NRCS), and weather data from the National Weather Service (NWS) Cooperative Observer Program (COOP) network. The crop model was validated using data from state variety trials conducted at two locations from 1992 to 2004. Variograms for normalized yields were constructed to examine spatial variability and yield patterns were determined to characterize their temporal variation. Simulated yields were compared with NASS yield estimates. Both the spatial and temporal variability of simulated yields were well characterized and different spatial and temporal yield patterns throughout the Georgia peanut belt were found. The results from this analysis can provide insight on the degree of spatial and temporal yield variability of peanuts and can be useful information for decision makers and stakeholders.