The recent advances of technology helps in accessing any data remotely. The observations of earth surface can also be done remotely with the help of high resolution satellite images. These remotely sensed data are used in various applications like urban monitoring, fire detection, flood prediction, oil spills, disaster monitoring, rock type mapping, road networks, change detection, etc. for continuous monitoring and accurate results, the data which is acquired has to be of high resolution and minimum errors. The multi-temporal satellite data gives the data in periodic basis which helps for continuous monitoring, but due to the earth’s rotation, climatic changes, sensor characteristics, etc. there are too many distortions and noises which has to be removed before further processing for getting better results. Many researchers have put forth different methodologies for removing the different kinds of noises from the satellite data. Each and every methodology helps in removing a specific kind of noise. This paper proposes a method named Cellular Automata based Gaussian Filter for pre-processing of Multi-temporal Hyperspectral Satellite Images which could be used for removing the noises, filtering it and giving an enhanced image which forms as input for image registration. The performance is analyzed using the Peak Signal to Noise Ratio. The results specify that the proposed methodology is better than the traditional Gaussian Filter. © 2016, Institute of Integrative Omics and Applied Biotechnology. All rights reserved.