Urban green spaces play a vital role in enhancing the urban environment, improving quality of life, and contributing to the sustainable development of cities. However, rapid urbanization has resulted in substantial changes in land use, particularly the reduction of urban green spaces. This study leverages Sentinel-2 satellite imagery and machine learning algorithms to monitor and analyze changes in urban green spaces in Thanh Hoa City, Thanh Hoa Province, Vietnam. High-resolution, multi temporal Sentinel-2 data were processed to calculate vegetation indices, including NDVI, NDWI, NDBI, BUI, and SAVI. Two machine learning algorithms, Random Forest (RF) and Support Vector Machine (SVM), were applied to classify land cover into three categories: vegetation, non-vegetation, and water. The most accurate classification result was further refined to reclassify the area into two groups: urban green space (vegetation) and other objects (non-vegetation and water). Object boundaries were calibrated using the Simple Non-Iterative Clustering (SNIC) algorithm for segmentation. The analysis revealed notable changes in urban green space over time, emphasizing the effects of urban expansion on green space distribution. These findings provide valuable insights into the development and degradation of urban green spaces, offering critical information for sustainable urban planning. The results can aid policymakers and urban planners in devising strategies that balance urbanization with environmental conservation in Thanh Hoa City and other similar urban areas. Keywords: Urban green space, Remote sensing, Thanh Hoa Province, Vietnam.