Detection, recognition, and identification ranges for targets in backgrounds are determined by the combined signatures of both target and background. Since the signatures of backgrounds are determined by many variable conditions, such as by illumination, weather, season, time, range and line of sight, the recognition and identification ranges for targets embedded in backgrounds will vary with these conditions, even when the target signature is kept constant. In order to improve our understanding of the temporal behavior of cluttered backgrounds at infrared (IR) wavelengths in varying meteorological conditions, a series of experiments are described to model sequences of acquired IR images using basic meteorological parameters recorded by a synoptic weather station. The acquired imagery contains two sequences of 335 and 490 thermal images recorded every 5 minutes over a period of approximately 2 days in stable, clear weather conditions in mid-latitude winter and summer respectively. Multi-variate linear regression algorithms using basic meteorological variables are used to model the temporal character of each pixel in the sequences of images.