Change monitoring on the Earth's surface has become vital for understanding environmental processes and developing sustainable resource management decisions. For numerous applications, ranging from mapping urban sprawl to assessing the impacts of natural hazards, approximating environmental damage, and analyzing forest loss, precision in change detection (CD) methods is paramount. This work entails a thorough examination of enhanced CD techniques that are particularly designed to improve accuracy when detecting changes in satellite data. The three methods that are examined include Dual-stream convolution with absolute difference of skip concatenation (DSC-AD-SC), absolute convolutional prior fusion (AC-PF), and dual-stream convolution with skip concatenation (DSC-SC). To optimize CD accuracy and effectiveness in monitoring changes in geographical features over time, each method employs specialized convolutional operations. The research analyzes environmental changes over time using Onera satellite change detection dataset. A data augmentation step is introduced to the pipeline to enhance dataset diversity and model robustness. Performance is compared using multiple parameters, and the results indicate the highest Dice Similarity Score of 0.9284 for the DSC-AD-SC model, followed by AC-PF at 0.9037 and DSC-SC at 0.7577. The proposed methods are found to be effective in enhancing change detection performance and yield informative measures for use in environmental monitoring and disaster response applications.