Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65473
Volume:
10 |
6 |
Jun 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science and Engineering
Bharatiya Vidya Bhavan's Sardar Patel Institute of Technology (SPIT)
Department of Computer Science and Engineering
Bharatiya Vidya Bhavan's Sardar Patel Institute of Technology (SPIT)
Department of Computer Science and Engineering
Bharatiya Vidya Bhavan's Sardar Patel Institute of Technology (SPIT)
Department of Computer Science and Engineering
Bharatiya Vidya Bhavan's Sardar Patel Institute of Technology (SPIT)
Land use and land cover (LULC) changes espe-cially partial deforestation where the forest canopy becomes thinner are important to monitor for sustainable ecosystem management in tropical regions such as the Assam forests in Northeast India. This study examines partial deforesta- tion covering about 10,000 km2 of Assam (26°40’N–26°50’N, 93°20’E–93°40’E) for the years 2020–2024. Open-source geo-informatics tools, Python-based image processing, and remote sensing methods were used for the analysis. The study area includes a mix of hill and plain forests. Multi-temporal Sentinel- 2 Level-2A images (10 m resolution) were used to detect subtle vegetation loss. False-color composites (NIR-Red-Green) helped visually identify healthy forests and thinning areas. NIR/Red ratios were used to measure spectral changes, and Euclidean RGB distances captured color differences between years. Weighted change maps highlighted partial forest loss. Drops in the ratio and distances suggested that about 20% of forest edges experienced degradation in 2024 compared to 2020. We used several segmentation methods—SLIC, Felzenszwalb, Quickshift, and Watershed to segment the image into about 150,000 small parts. These segments were then classified into Low, Medium, and High risk groups using GPU-accelerated k-means clustering. This open-source, non-NDVI method is highly sensitive to subtle canopy thinning and is useful for conservation in regions with limited data. The results indicate increasing forest degradation due to logging, with consequences for biodiversity and carbon storage.
KEYWORDS
Future work will enhance temporal resolution by inte-grating Sentinel-1 SAR for cloud-free monitoring and deep learning (e.g., U-Net/Siamese networks) for automated feature extraction. Ground validation with drones/LiDAR and socio-economic surveys on jhum/logging will quantify biomass loss and predict drivers. Scaling to the full Brahmaputra basin via Google Earth Engine, with real-time dashboards, and fusing hyperspectral data or new indices (e.g., Normalized Difference Red–NIR–SWIR) will improve sensitivity to selective logging.
[1] Hansen, M.C., et al. Global forest change. Science, 342(6160), 2013. [2] Reddy, C.S., et al. Monitoring forest dynamics in Northeast India. Journal of Remote Sensing, 22(4), 2016. [3] Gao, B.C. NDVI limitations in forest monitoring. Remote Sensing of Environment, 60(3), 1996. [4] Wulder, M.A., et al. Sentinel-2 applications in forest monitoring. Remote Sensing, 11(8), 2019. [5] Zhu, Z. Change detection using multi-temporal satellite im-agery. Remote Sensing, 6(9), 2014. [6] Drusch, M., et al. Sentinel-2: ESA’s optical high-resolution mission. Remote Sensing of Environment, 120, 25–36, 2012. [7] Tucker, C.J. Red and photographic infrared linear combinations. Remote Sensing of Environment, 8(2), 127–150, 1979. [8] Huete, A.R. A soil-adjusted vegetation index (SAVI). Remote Sensing of Environment, 25(3), 295–309, 1988. [9] Forkuo, E.K., Frimpong, A. Analysis of forest cover change detection. International Journal of Remote Sensing, 31(13), 2010. [10] Asner, G.P. Selective logging in tropical forests. Remote Sensing of Environment, 102(3-4), 2006.
Publication Date
6/25/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
6
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...