Analysis of Regional Transportation Networks and Socioeconomic Spatial Distribution Based on Remote Sensing Image Supervised Classification: A Case Study of Taizhou City

This study investigates the spatial correlation between transportation networks and socioeconomic activities within Taizhou City, utilizing supervised classification of remote sensing imagery and advanced spatial analytical techniques. Based on Landsat 8 imagery, the study classifies the study area into built-up areas, water bodies, and farmland using a neural network algorithm, achieving a classification accuracy of 91.17%. By employing transportation network data and a grid-based approach, the correlation between road length and building area was analyzed, yielding a Pearson correlation coefficient of 0.5388. This indicates a moderate positive correlation between transportation network density and socioeconomic activities. A comparative analysis of satellite images from 2010, 2016, and 2024 demonstrates the significant driving effect of main road construction on commercial development along the route. The study reveals that transportation network optimization not only enhances accessibility but also significantly promotes economic development in surrounding areas.