Spatio-Temporal Prediction of Urban Expansion Using Sentinel Data and ML-Model

Author

N. Kavitha, J. Steffi


Abstract

 Rapid urbanization has significantly transformed Land Use and Land Cover (LULC) patterns worldwide, highlighting the necessity for continuous monitoring and prediction of urban growth to facilitate sustainable urban planning. This study proposes a spatio-temporal framework to analyze urban expansion in Tirunelveli, Tamil Nadu, India, through the integration of Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical satellite data using a Random Forest machine learning classifier. Spectral indices derived from optical imagery were integrated with SAR backscatter features to generate LULC maps for multiple temporal periods, enabling a comprehensive assessment of land-cover dynamics. The accuracy of the classified maps was evaluated through standard accuracy assessment techniques, confirming the reliability of the proposed framework. Post-classification change detection analysis revealed a consistent expansion of built-up areas over the study period, along with changes in vegetation, barren land, and other land-cover classes. Furthermore, based on the observed urban growth trends, future urban expansion was projected to support long-term urban planning. The findings demonstrate that the synergistic use of optical and radar remote sensing data coupled with machine learning provides an effective approach for monitoring urban dynamics and offers valuable insights for sustainable land-use planning and urban development strategies.


Keywords

Urban Growth, LULC, Sentinel-1, Sentinel-2, Random Forest, Remote Sensing, Change Detection, Tirunelveli.



Full Text:

Download Paper PDF


References


  1. L. G. de Almeida et al., “Integration of Sentinel-1 and Sentinel-2 for Classification and LULC Mapping in the Urban Area of Belém, Eastern Brazilian Amazon,” Remote Sensing, vol. 11, 2019.
  2. Schowengerdt, Remote Sensing: Models and Methods for Image Processing, 3rd ed. Burlington, MA, USA: Academic Press, 2007.
  3. Breiman, “Random Forests,” Machine Learning, vol. 45, pp. 5–32, 2001.
  4. Belgiu and L. Drăguţ, “Random Forest in Remote Sensing: A Review of Applications and Future Directions,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 114, pp. 24–31, 2016.
  5. Drusch et al., “Sentinel-2: ESA’s Optical High-Resolution Mission for GMES Operational Services,” Remote Sensing of Environment, vol. 120, pp. 25–36, 2012.
  6. Gorelick, M. Hancher, M. Dixon, S. Ilyushchenko, D. Thau, and R. Moore, “Google Earth Engine: Planetary-Scale Geospatial Analysis for Everyone,” Remote Sensing of Environment, vol. 202, pp. 18–27, 2017.
  7. Torres et al., “GMES Sentinel-1 Mission,” Remote Sensing of Environment, vol. 120, pp. 9–24, 2012.
  8. D. Duro, S. E. Franklin, and M. G. Dubé, “A Comparison of Pixel-Based and Object-Based Image Analysis with Selected Machine Learning Algorithms for the Classification of Agricultural Landscapes Using SPOT-5 HRG Imagery,” Remote Sensing of Environment, vol. 118, pp. 259–272, 2012.
  9. Esch et al., “Where We Need to Know More About the World’s Urbanization,” Nature Sustainability, vol. 2, pp. 118–124, 2019.
  10. Zha, J. Gao, and S. Ni, “Use of Normalized Difference Built-Up Index in Automatically Mapping Urban Areas from TM Imagery,” International Journal of Remote Sensing, vol. 24, no. 3, pp. 583–594, 2003.

 

 

Share your valuable work from Social Media Buttons