Keywords
Machine learning
Vegetation classification
Satellite Images
U-Net
Random Forest
How to Cite
Abstract
This study implements a vegetation classification process in El Salvador using remote sensing techniques and machine learning algorithms. Satellite data from Santa María, Usulután, were analyzed using convolutional neural networks (U-Net) and the Random Forest model. The objective is to identify and segment agricultural fields and tree-covered areas using low and high-resolution satellite images. Multispectral and RGB data were processed, employing a ground truth-based training set to evaluate each model's effectiveness.
Results show that both models can classify vegetation with high accuracy. The U-Net model achieves higher precision in predictions, while Random Forest offers better interpretability with lower computational complexity. It is concluded that a combination of both approaches could enhance vegetation segmentation and detection in future studies.
References
S. Theodoridis and K. Koutroumbas, Pattern Recognition, 4th ed. Academic Press, 2009.
J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Morgan Kaufmann, 2011.
T. Lillesand, R. W. Kiefer, and J. Chipman, Remote Sensing and Image Interpretation, 7th ed. John Wiley & Sons, 2015.
Z. Zhu, S. Wang, and C. E. Woodcock, “Improvement and expansion of the Landsat Global Land Survey,” Remote Sensing of Environment, vol. 238, p. 111123, 2019.
M. 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.
L. Ma et al., "Deep learning in remote sensing applications: A meta-analysis and review," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 152, pp. 166–177, 2019.
P. Ghamisi, J. A. Benediktsson, and X. Zhu, "A review of machine learning approaches for hyperspectral image analysis," IEEE Geoscience and Remote Sensing Magazine, vol. 4, no. 2, pp. 99–119, 2016.
K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, "Machine learning in agriculture: A review," Sensors, vol. 18, no. 8, p. 2674, 2018.
C. D. Manning, P. Raghavan, and H. Schütze, Introduction to Information Retrieval, Cambridge University Press, 2008.
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, 2015.
A. Kamilaris and F. X. Prenafeta-Boldú, "Deep learning in agriculture: A survey" Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018.
F. Pedregosa et al., "Scikit-learn: Machine learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
R. A. Schowengerdt, Remote Sensing: Models and Methods for Image Processing, 3rd ed. Academic Press, 2007.
M. Abadi et al., "TensorFlow: Large-scale machine learning on heterogeneous distributed systems," in Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI), 2016, pp. 265–283.
J. D. Hunter, "Matplotlib: A 2D graphics environment," Computing in Science & Engineering, vol. 9, no. 3, pp. 90–95, 2007.
J. Li, J. Lewis, and A. Singh, "Remote sensing with artificial intelligence: A review," Remote Sensing Applications: Society and Environment, vol. 19, p. 100350, 2020.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Manuel Hernández, Henry Alexánder, Alejandro Cerón, César Archila (Autor/a)