Application of Remote Sensing and GIS Technologies in Developing a Road Transportation Database: A Case Study in Son La Province, Vietnam
DOI:
https://doi.org/10.5281/zenodo.15205298Keywords:
GIS, Remote sensing, transportation database, infrastructure management, Son LaAbstract
The development of a road transportation database plays a crucial role in infrastructure management and planning, especially in mountainous areas with complex terrain such as Son La province. This study integrates remote sensing imagery (Sentinel-2, Landsat-8, and high-resolution satellite images) with GIS technology to build a comprehensive transportation database for the entire study area. Through image preprocessing, supervised classification, and spatial information extraction, the GIS database was constructed with key data layers: road networks, bridges and tunnels, and major traffic nodes. Validation against field survey data shows an overall accuracy of 89%, with the road network layer reaching 91.3%. The results demonstrate that, the GIS-based transportation database can provide detailed information on road infrastructure, supporting evaluation and planning efforts in mountainous regions
Downloads
References
[1] Chen, Y., Zhang, L., & Li, H. (2019). Monitoring urban road network changes using multi-temporal remote sensing data. ISPRS Journal of Photogrammetry and Remote Sensing, 148, 66–77. https://doi.org/10.1016/j.isprsjprs.2018.12.009
[2] European Space Agency (ESA). (2023). Copernicus Sentinel-1 Mission. https://sentinel.esa.int/web/sentinel/missions/sentinel-1
[3] European Space Agency (ESA). (2023). Copernicus Sentinel-2 Mission. https://sentinel.esa.int/web/sentinel/missions/sentinel-2
[4] Goodchild, M. F. (2007). Citizens as sensors: the world of volunteered geography. GeoJournal, 69(4), 211–221. https://doi.org/10.1007/s10708-007-9111-y
[5] Google Earth. (2023). Google Earth Pro software. https://www.google.com/earth/versions/
[6] Kurniawan, A., Haryono, A., & Prasetyo, L. B. (2020). Road network extraction using Sentinel-2 imagery and machine learning classification. Remote Sensing Applications: Society and Environment, 17, 100287. https://doi.org/10.1016/j.rsase.2020.100287
[7] Li, Y., Zhao, W., & Wang, T. (2019). Challenges of road extraction in mountainous terrain using satellite imagery. Remote Sensing Letters, 10(4), 392–401. https://doi.org/10.1080/2150704X.2019.1582064
[8] Nguyễn Văn Hùng, Trần Văn Tùng, Lê Thị Hoa (2021). Ứng dụng ảnh UAV và GIS trong cập nhật hệ thống đường giao thông tỉnh Quảng Nam. Tạp chí Khoa học Trái đất, 43(2), tr. 25–35.
[9] Nguyễn, T. D., Phạm, H. A., & Lê, T. M. (2020). Ứng dụng GIS trong mô phỏng mật độ giao thông tại khu vực nội đô Hà Nội. Tạp chí Khoa học và Công nghệ Giao thông Vận tải, 35(4), tr. 42–50.
[10] OpenStreetMap Foundation. (2023). About OpenStreetMap. https://www.openstreetmap.org/about
[11] Phạm, V. K., Trịnh, T. M., & Nguyễn, V. D. (2018). Đánh giá tiềm năng cập nhật dữ liệu giao thông khu vực miền núi bằng ảnh vệ tinh. Tạp chí Địa lý và Tài nguyên, 28(1), tr. 19–27.
[12] Tổng cục Đường bộ Việt Nam (2023), Cơ sở dữ liệu hạ tầng giao thông đường bộ Việt Nam.
[13] UBND tỉnh Sơn La (2022), Báo cáo Quy hoạch tỉnh Sơn La thời kỳ 2021–2030, tầm nhìn đến năm 2050.
[14] Zhang, J., Wu, Q., & Wang, R. (2021). Road extraction from Sentinel-2 imagery using deep learning techniques. International Journal of Applied Earth Observation and Geoinformation, 103, 102517. https://doi.org/10.1016/j.jag.2021.102517
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
CC 4.0
