International Journal of Land Research Article
GreenVisionAI: An AI-Based Framework for Detecting Illegal Mining and Deforestation Using Sentinel-2 Satellite Imagery
Abstract
Illegal mining and deforestation represent two of the most severe anthropogenic threats to forest ecosystems worldwide, causing irreversible ecological degradation, biodiversity loss, and accelerated climate change. Traditional ground-based environmental monitoring methods are often slow, expensive, and ineffective for large or remote geographical regions. This paper presents GreenVisionAI, an artificial intelligence (AI)-powered environmental monitoring framework that utilizes multispectral Sentinel-2 satellite imagery accessed through Google Earth Engine for automated detection of deforestation and illegal mining activities. The proposed system integrates a random forest classifier for forest cover mapping and temporal deforestation analysis with a U-Net convolutional neural network for pixel-wise mining region segmentation. The framework is implemented as an interactive web application using Flask, React.js, and Mapbox visualization tools, enabling users to analyze environmental changes in near-real-time. Experimental evaluations demonstrated significant forest cover reduction from 83% to 25% between 2017 and 2024 over the selected study area, representing approximately 70% forest loss. The system also successfully identified mining activity in the Jharia Coal Mine region of Jharkhand using deep learning-based segmentation and probability heatmaps. Comparative analysis showed that the proposed models outperformed conventional baseline methods in both classification accuracy and segmentation performance. The proposed framework provides a scalable, cost-effective, and accessible solution for environmental surveillance, sustainable forest governance, and rapid regulatory decision-making.
Keywords
References (11)
- Pan Y, Birdsey RA, Fang J, Houghton R, Kauppi PE, Kurz WA, et al. A large and persistent carbon sink in the world's forests. Science. 2011;333(6045):988-93. doi:10.1126/science.1201609.
- Potapov P, Hansen MC, Laestadius L, Turubanova S, Yaroshenko A, Thies C, et al. The last frontiers of wilderness: tracking loss of intact forest landscapes from 2000 to 2013. Sci Adv. 2017;3(1):e1600821. doi:10.1126/sciadv.1600821.
- Drusch M, Del Bello U, Carlier S, Colin O, Fernandez V, Gascon F, et al. Sentinel-2: ESA's optical high-resolution mission for GMES operational services. Remote Sens Environ. 2012;120:25-36. doi:10.1016/j.rse.2011.11.026.
- Tucker CJ, Townshend JR, Goff TE. African land-cover classification using satellite data. Science. 1985;227(4685):369-75. doi:10.1126/science.227.4685.369.
- Hansen MC, Potapov PV, Moore R, Hancher M, Turubanova SA, Tyukavina A, et al. High-resolution global maps of 21st-century forest cover change. Science. 2013;342(6160):850-3. doi:10.1126/science.1244693.
- Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention—MICCAI 2015. Cham: Springer International Publishing; 2015. p. 234-41. doi:10.1007/978-3-319-24574-4_28.
- Bischke B, Helber P, Folz J, Borth D, Dengel A. Multi-task learning for segmentation of building footprints with deep neural networks. In: Proceedings of the IEEE International Conference on Image Processing (ICIP); 2019. p. 1480-4. doi:10.1109/ICIP.2019.8803050.
- Ghaffarian S, Ghaffarian S. Automatic building detection based on supervised classification using high-resolution Google Earth images. Int Arch Photogramm Remote Sens Spatial Inf Sci. 2014;XL-3:101-6. doi:10.5194/isprsarchives-XL-3-101-2014.
- Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R. Google Earth Engine: planetary-scale geospatial analysis for everyone. Remote Sens Environ. 2017;202:18-27. doi:10.1016/j.rse.2017.06.031.
- Hansen MC, Krylov A, Tyukavina A, Potapov PV, Turubanova S, Zutta B, et al. Humid tropical forest disturbance alerts using Landsat data. Environ Res Lett. 2016;11(3):034008. doi:10.1088/1748-9326/11/3/034008.
- Shimada M, Itoh T, Motooka T, Watanabe M, Shiraishi T, Thapa R, et al. New global forest/non-forest maps from ALOS PALSAR data (2007-2010). Remote Sens Environ. 2014;155:13-31. doi:10.1016/j.rse.2014.04.014.