GENERALLY ONE OF THE MOST INTERESTING PROBLEMS IN Image PROCESSING IS TO HAVE A KEY FUNCTION IN DETECTING LAND USE CHANGES. ENVIRONMENTAL PROTECTION AND MANAGEMENT HAS LED TO INCREASING INTEREST IN REMOTE SENSING SOCIETY. IN THIS STUDY WE ADDRESSED THE METHODS RECOGNIZED BY BOTH SUPERVISED AND UNSUPERVISED Classification FOR DETECTING CHANGES IN MULTI TEMPORAL CHANGES IN HIGH RESOLUTION AND MULTI-SPECTRAL Satellite ImageS RESULTING IN THE BEST ALGORITHM FOR CLASSIFYING HIGH RESOLUTION AND MULTI-SPECTRAL Satellite ImageS FOR THE MULTI-LAYER PERCEPTRON ALGORITHM (MLP) WITH AN OVERALL ACCURACY AND KAPPA COEFFICIENT OF 91.28% AND 0.89 RESPECTIVELY. ALSO THE RADIAL BASIS FUNCTION (RBF) WITH AN OVERALL ACCURACY OF 77.75% AND A KAPPA COEFFICIENT OF 0.72 AND FINALLY THE SELF ORGANIZING MAP (SOM) WITH THE LEAST ACCURACY RATE OF 74.09% FOR THE OVERALL ACCURACY AND KAPPA COEFFICIENT OF 0.67 WAS OBTAINED. FINALLY, THE ANALYSIS OF CHANGES IN THIS AREA INCLUDES THE HIGHEST CLASS OF LAND USE CHANGES IS ASSOCIATED WITH THE CLASS OF NO USE (ARID) AND THE VEGETATION CLASS WITH 8450 SQUARE METERS OF ARID LAND CHANGED INTO VEGETATION CLASS. ALSO 482 SQUARE METERS OF VEGETATION CLASS IS CHANGED TO BUILDINGS.