Swetanisha et al. (2026) Land Use and Land Cover Change Detection Using Remote Sensing and Machine Learning: A Temporal Analysis

Identification

• Journal: Lecture notes in networks and systems
• Year: 2026
• Date: 2026-01-01
• Authors: Subhra Swetanisha, Dibyatman Khadanga, Debi Prasad Sahoo, Santosh Kumar Sahoo
• DOI: 10.1007/978-981-95-0375-9_22

Research Groups

• School of Computing, Trident Academy of Technology, Bhubaneswar, Odisha, India
• Department of Computer Science and Engineering, Faculty of Science and Technology (IcfaiTech), ICFAI Foundation for Higher Education, Hyderabad, Telangana, India

Short Summary

This study analyzes land use and land cover (LULC) changes in Bhubaneswar and Cuttack, Odisha, from March 2019 to March 2024 using remote sensing and machine learning on Google Earth Engine, revealing significant urban expansion alongside vegetation changes and challenges in green cover management.

Objective

• To analyze and interpret land use and land cover (LULC) changes in the Bhubaneswar and Cuttack areas of Odisha, India, over a five-year period (March 2019 to March 2024) using remote sensing and machine learning techniques.

Study Configuration

• Spatial Scale: Bhubaneswar and Cuttack areas in Odisha, India.
• Temporal Scale: March 2019 to March 2024.

Methodology and Data

• Models used: Supervised classification (machine learning).
• Data sources: Satellite imagery (Sentinel-2), Dynamic World datasets, processed using Google Earth Engine (GEE).

Main Results

• Built-up areas increased by 6.21%, corresponding to an urban expansion of approximately 11.57 million square meters.
• Vegetation areas (specifically the Annapa Gold Lush field) increased by 23.24%, adding 21.63 million square meters of green cover and energy park amenities.
• Despite overall vegetation growth, over 7800 trees were removed in Bhubaneswar between 2019 and 2023.
• Government tree-plantation initiatives achieved only 40% of their stated objectives.
• Detected growth patterns indicate a relatively balanced yet complex typological trajectory of urban development.

Contributions

• Presents an effective and scalable method for tracking LULC changes by combining Google Earth Engine with remote sensing datasets.
• Provides imperative insights for decision-makers in sustainable urban management for the studied region.

Funding

• Not explicitly mentioned in the provided text.

Citation

@article{Swetanisha2026Land,
  author = {Swetanisha, Subhra and Khadanga, Dibyatman and Sahoo, Debi Prasad and Sahoo, Santosh Kumar},
  title = {Land Use and Land Cover Change Detection Using Remote Sensing and Machine Learning: A Temporal Analysis},
  journal = {Lecture notes in networks and systems},
  year = {2026},
  doi = {10.1007/978-981-95-0375-9_22},
  url = {https://doi.org/10.1007/978-981-95-0375-9_22}
}