Citation :

Somagari Archana, Kantepudi Ajay Kumar, Gone Anish Reddy, Raghavendra Gowda, 2026. "Intelligent Forest Cover Analysis and Plant Species Recognition Using Remote Sensing and MobileNetV2" ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 4, Issue 2: 22-30.

Abstract :

Understanding and monitoring various types of ecosystems and vegetation play an important role in the protection of the natural world and the sustainable management of land. This paper presents a dual approach artificial intelligence system for the analysis of satellite remote sensing data and the application of deep learning techniques to identify changes in forest cover and classify leaf types. This system has two components: the first examines changes in forest cover and uses multi-band data to determine loss, gain, or stability of vegetation, and the second identifies various plant species via leaf images. The latter employs a transfer learning approach using MobileNetV2. Analysis from testing shows that the method described can detect minor variations in the state of the forest and classify species at the leaf level, even with limited training data. The system merges unsupervised learning methods applicable for broad-scale forest tracking and deep learning methods for fine-scale species recognition. The framework exemplifies the potential of lightweight AI models for operational ecological monitoring.

References :

[1] A. Javed, S. Ahmed, and M. Khan, “Forest cover change detection using deep learning and satellite imagery,” Remote Sensing, vol. 15, no. 6, p. 1452, 2023.

[2] T. Bai, Z. Li, and H. Zhang, “Land-use and land-cover change analysis using unsupervised machine learning,” Geo-spatial Information Science, vol. 26, no. 4, pp. 512–526, 2023.

[3] Y. Shen, Q. Liu, and X. Wang, “Deep learning-based vegetation monitoring from multi-temporal remote sensing data,” Remote Sensing, vol. 16, no. 2, p. 389, 2024.

[4] M. Aziz, F. Rahman, and M. Hossain, “Automated forest loss detection using satellite imagery and clustering techniques,” Scientific Reports, vol. 14, p. 10234, 2024.

[5] M. Jelas, N. Noor, and Z. Hamzah, “Remote sensing approaches for sustainable forest management,” Frontiers in Forests and Global Change, vol. 7, p. 128945, 2024.

[6] G. Sartor, R. Benedetti, and L. Rossi, “High-resolution forest monitoring using machine learning models,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 203, pp. 112–125, 2025.

[7] M. Hossain and P. Debnath, “Machine learning applications in environmental monitoring: A review,” SSRN Electronic Journal, 2024.

[8] A. Alzoubi and R. Ahmed, “Deep learning for vegetation classification using satellite imagery,” Issues in Information Systems, vol. 25, no. 1, pp. 45–56, 2024.

[9] Y. Li, J. Zhou, and D. Chen, “Unsupervised clustering for land-cover mapping using multispectral data,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 8765–8778, 2023.

[10] S. Wang, L. Zhang, and Y. Hu, “Forest dynamics analysis using multi-source remote sensing data,” Environmental Monitoring and Assessment, vol. 195, p. 841, 2023.

[11] R. Singh, K. Patel, and P. Mehta, “Deep learning-based plant species recognition using leaf images,” Computers and Electronics in Agriculture, vol. 216, p. 108534, 2024.

[12] X. Chen, H. Li, and Y. Zhao, “Lightweight convolutional neural networks for vegetation classification,” Expert Systems with Applications, vol. 234, p. 120123, 2024.

[13] A. Kumar, S. Verma, and R. Gupta, “Remote sensing and AI-based approaches for forest health monitoring,” Ecological Informatics, vol. 75, p. 101982, 2023.

[14] J. Lopez, D. Martinez, and F. Garcia, “Satellite-based forest change detection using machine learning,” Journal of Environmental Management, vol. 345, p. 118624, 2024.

[15] T. Nguyen, H. Pham, and Q. Le, “Land-cover classification using deep neural networks and remote sensing,” Applied Soft Computing, vol. 137, p. 110061, 2023.

[16] M. Rahman, S. Islam, and T. Chowdhury, “AI-driven monitoring of deforestation using satellite imagery,” Sustainability, vol. 16, no. 3, p. 1324, 2024.

[17] Y. Zhang, S. Liu, and J. Huang, “Multi-temporal satellite image analysis for forest change detection,” Remote Sensing Applications: Society and Environment, vol. 33, p. 101067, 2024.

[18] P. Roy, S. Ghosh, and A. Banerjee, “K-means clustering for vegetation pattern analysis,” International Journal of Remote Sensing, vol. 44, no. 12, pp. 4567–4585, 2023.

[19] N. Islam, M. Rahim, and R. Hasan, “Deep learning techniques for biodiversity assessment,” Artificial Intelligence Review, vol. 57, p. 89, 2024.

[20] R. Meena, V. Sharma, and P. Jain, “Integrating remote sensing and deep learning for sustainable forestry,” Journal of Cleaner Production, vol. 418, p. 140345, 2025.

Keywords :

Forest Cover Change Detection, Remote Sensing, Deep Learning, Plant Species Classification, Environmental Monitoring