Intensive urban development has resulted in the degradation of the urban thermal environment. Th ere is a growing consensus on the need to enhance urban thermal comfort through well-designed f orms, especially in open spaces like urban canyons. To address this, our study focuses on Xi'an's commercial pedestrian streets, employing K-means clustering analysis to create 32 representative models based on actual scenes, capturing their textural characteristics. Simultaneously, 11 geometri c indicators (2D/3D) were chosen to quantify the canyon's geometric form. We assessed the spatia l and temporal distribution differences in the thermal environment across these models using Envimet simulation. Finally, Spearman correlation analysis was employed to examine the correlation an d significance of the two sets of indicators, culminating in formulating an ideal model. The findin gs reveal that (1) wind conditions are predominantly influenced by the canyon's geometric form, f ollowed by solar radiation and temperature, with the lowest relative humidity change amplitude a mong the assessed thermal parameters. (2) Among the 11 geometric form indicators, 3D indicators correlate more significantly with thermal environment parameters than 2D indicators. Specifically, SO significantly impacts the thermal environment, P holds greater significance than De, and both BSC and BSR are significantly correlated with air temperature and wind speed, with a weaker co rrelation to solar radiation. (3) In the Xi'an region, courtyards oriented north-south demonstrate a more favorable trend in the thermal environment.