Version 1
: Received: 2 February 2023 / Approved: 6 February 2023 / Online: 6 February 2023 (10:53:10 CET)
How to cite:
Esteves, A.; Valente, N. Automatic Generation of a Portuguese Land Cover Map with Machine Learning. Preprints2023, 2023020102. https://doi.org/10.20944/preprints202302.0102.v1
Esteves, A.; Valente, N. Automatic Generation of a Portuguese Land Cover Map with Machine Learning. Preprints 2023, 2023020102. https://doi.org/10.20944/preprints202302.0102.v1
Esteves, A.; Valente, N. Automatic Generation of a Portuguese Land Cover Map with Machine Learning. Preprints2023, 2023020102. https://doi.org/10.20944/preprints202302.0102.v1
APA Style
Esteves, A., & Valente, N. (2023). Automatic Generation of a Portuguese Land Cover Map with Machine Learning. Preprints. https://doi.org/10.20944/preprints202302.0102.v1
Chicago/Turabian Style
Esteves, A. and Nuno Valente. 2023 "Automatic Generation of a Portuguese Land Cover Map with Machine Learning" Preprints. https://doi.org/10.20944/preprints202302.0102.v1
Abstract
The application of machine learning techniques to satellite imagery has been the subject of interest in recent years. The increase in quality and quantity of images, made available by Earth observation programs, such as the Copernicus program, led to the generation of large amounts of data. Among the various applications of this data is the creation of land cover maps. The present work aimed to create machine learning models capable of accurately segment and classify satellite images, to automatically generate a land cover map of the Portuguese territory. Several experiments were carried out with the spectral bands of the Sentinel-2 satellite, with vegetation indices, and with several sets of land cover classes. Three machine learning architectures were evaluated, which adopt two different techniques for image classification. One of the classification techniques follows an object-oriented approach, and in this case the architecture adopted in our models was a U-Net artificial neural network. The other classification technique is pixel-oriented, and the machine learning models tested were random forest and support vector machine. The overall accuracy of the results obtained ranged from 68.6% to 94.75%, depending strongly on the number of classes into which the land cover is classified. The result of 94.75% was obtained when classifying the land cover only into 5 classes. However, a very interesting accuracy of 92.37% was achieved by the model when trained to classify 8 classes. These results are superior to those reported in the related bibliography.
Keywords
machine learning; deep learning; remote sensing; land cover map
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
The commenter has declared there is no conflict of interests.
Comment:
Great work, Esteves and Valente! Your study on the automatic production of a Portuguese land cover map using machine learning techniques is interesting and novel. The emphasis on multiple spectral bands, vegetation indices, and land cover classes in your investigation is remarkable. The study's uniqueness is enhanced by the implementation of three different machine learning architectures and two classification algorithms. The accuracy attained while classifying land cover into five categories is excellent. Achieving 92.37% accuracy with eight classes is also a noteworthy achievement. The findings of your investigation outperformed those stated in the linked literature. Overall, your research contributes significantly to the field of machine learning and its application to satellite imagery for the development of land cover maps.
Commenter:
The commenter has declared there is no conflict of interests.