This paper introduces a novel method for synthetic aperture radar (SAR) image change detection based on principal component analysis (PCA) and two-level clustering. The method involves computing two difference images using log-ratio and mean-ratio operators, then fusing them with a PCA model to generate a new difference image. Gabor wavelets are used to extract features across multiple scales and orientations, and a cascading clustering algorithm is applied to classify the difference image into changed and unchanged regions. The method is tested on five SAR datasets, demonstrating its effectiveness in detecting changes with high accuracy. The results show that the proposed method outperforms existing techniques in terms of overall error, percentage of correct classifications, Kappa coefficient, and F1-score. The method's robustness and accuracy make it a valuable tool for environmental monitoring, urban planning, and disaster assessment.This paper introduces a novel method for synthetic aperture radar (SAR) image change detection based on principal component analysis (PCA) and two-level clustering. The method involves computing two difference images using log-ratio and mean-ratio operators, then fusing them with a PCA model to generate a new difference image. Gabor wavelets are used to extract features across multiple scales and orientations, and a cascading clustering algorithm is applied to classify the difference image into changed and unchanged regions. The method is tested on five SAR datasets, demonstrating its effectiveness in detecting changes with high accuracy. The results show that the proposed method outperforms existing techniques in terms of overall error, percentage of correct classifications, Kappa coefficient, and F1-score. The method's robustness and accuracy make it a valuable tool for environmental monitoring, urban planning, and disaster assessment.