Efficient management of water resources plays a critical role in countries characterized by high aridity levels and vulnerability to floods, as seen in the case of Pakistan. However, challenges arise, largely stemming from the scarcity of resources required for effective water management. Fortunately, Remote Sensing field has emerged as a significant player, providing time series data, and allowing the mapping of surface water bodies in an automated and efficient manner. Therefore, this study predominantly focuses on leveraging time series RGB and 12-band Sentinel-L2A imagery to carry out the segmentation of surface water bodies for spatio-temporal analysis. The study introduces a detailed approach to collecting and preparing surface water body imagery data in Pakistan. Additionally, accurate ground truth water masks are generated using the manual annotation tool, LabelMe. Furthermore, extensive experimentation was conducted to assess the capabilities of variants of a state-of-the-art deep learning segmentation model to segment the multi-temporal surface water bodies from both true-color RGB and 12-band Sentinel-L2A surface water bodies images. The study further encompasses the implementation of distinct strategies for training and validation, augmenting the robustness of the deep learning model and its capacity to generalize effectively across different scenarios. Experiments compared RGB and 12-band image results, with RGB images outperforming due to the uniform resolution of their bands.