Segmentation and classification algorithms applied to sentinel-2A images for geological mapping: case of the Al Glo’a sheet (1/50000), Morocco

Year 2021, Volume: 166 Issue: 166, 113 - 125, 15.12.2021

Abdessamad El Atıllah Mouhssine El Atıllah Zine El Abidine El Morjanı Khalid El Fazazy Mustapha Souhassou

https://doi.org/10.19111/bulletinofmre.864492

Abstract

The multispectral image, of Landsat 7 and 8; Aster and Sentinel-2A, has good results in lithological, structural, hydrothermal and mineralogical alteration mapping. Segmentation and image classification are two complementary steps as they are allowed the most important operations in the field of image processing. In this sense, this work aims at evaluating the potential of segmentation and classification algorithms for the generation of surface geological maps, hydrothermal alterations and lineaments. Given the good resolution of the Sentinel 2A (10m), the three images, (11/12; 11/2; 11/8), 12.8.2, main component 1, 2 and 3 (11.12.2), processed by five algorithms (K-means, isodata, watershed, efficient graph-based image segmentation, thresholding) for geological mapping and then mining exploration. The study displayed that 1) Watershed algorithm can be used for topographic and hydraulic studies, it can be very useful in the preparation phase of geological and mining infrastructures; 2) threshold segmentation does not give good results in terms of geological discrimination since it divides each image into two parts; 3) the same thing for the effective thresholding and segmentation of graph-based images; 4) The Isodata and K-means algorithms show good geological discrimination.

Keywords

Segmentation Algorithms, Classification Algorithms, Sentinel 2A, Geological Mapping, Anti-Atlas.

References

• Bai, M., Urtasun, R. 2017. Deep watershed transform for instance segmentation. Toronto.
• Ball, G., Hall, D. 1965. A novel method of data analysis and pattern classification. Rapport technique, Menlo Park, CA, Stanford Research Insitute.
• Choubert, G. 1947. L'accident majeur de l'Anti-Atlas. Comptes Rendus de l’Academie des Sciemces 224, 16, 1172-1173.
• Cleuziou, G. 2004. Une méthode de classification non- supervisée pour l’apprentissage de règles et la recherche d’information. Université d’Orléans.
• Dhodhi, K. M., Saghri, J. A., Ahmad, I., Ul-Mustafa, R. 1999. D-ISODATA: A Distributed Algorithm for Unsupervised Classification of Remotely Sensed Data on Network of Workstations. Journal of Parallel and Distributed Computing, 59(2), 280-301.
• Ducrot, D. 2005. Méthodes d'analyse et d'interprétation d'images de télédétection multi-sources: Extraction de caractéristiques du paysage. Habilitation à diriger des recherches, INP TOULOUSE.
• Dupas, A. 2009. Opérations et Algorithmes pour la Segmentation Topologique d’Images 3D.
• Fahim, A. S. 2006. An efficient enhanced k-means clustering algorithm. J. Zhejiang Univ- Sci, A 7, 1626–1633. https://doi.org/10.1631/jzus.2006.A1626.
• Felzenszwalb, P., Huttenlocher, D. 2004. Efficient graph- based image segmentation. International Journal of Computer Vision 59(2).
• Huttenlocher, P. F. 2004. Efficient graph-based image segmentation. International Journal of Computer Vision.
• Khan, M. 2014. A Survey : Image segmentation techniques, Lahore. International Journal of Future Computer and Communication, 3.
• Maarir, A., Agnaou, I., Bouikhalene, B. 2014. Evaluation de Quelques Méthodes de Segmentation -Application aux Caractères Tifinagh, https://tal. ircam.ma/conference/docs/TICAM2014/1.pdf.
• MacQueen, J. 1967. Some methods of classification and analysis of multivariate observations. Berkeley Symposium on Mathematical Statistics and Probability, 81-297.
• Maacha, L., Elghorfi, M., Zouhair, M., Sadiqui, O., Soulaimani, A. 2014. Reconsidérations des systèmes métallogéniques de la Boutonnière de Bou Azzer-El Grâara (Anti-Atlas occidental). Maroc.
• Mrmint. 2018, 11, 26. algorithme-k-means. Retrieved from mrmint: https://mrmint.fr/algorithme-k-means.
• Oukassou, M. 2013. Mouvements verticaux de la bordure nord du craton ouest africain (anti-atlas central, maroc) apport de la thermochronologie basse temperature. thèse de Doctorat, Faculté des Sciences-Aïn Chock, Casablanca.
• Pavlidis, S., Horowitz, L., Theodosios. 1976. Picture segmentation by a tree traversal. Journal of ACM, 23 (2), 366-388.
• Serra, J. 2006. A lattice approach to image segmentation. Journal of Mathematical Imaging, 24.
• Simplilearn. Apprentissage profond. Retrieved from simplilearn: https://www.simplilearn.com/ tutorials/machine-learning-tutorial/k-means- clustering-algorithm. 13 July 2020.
• Soulaimani, A., Egal, E., Razin, P., Youbi, N., Admou, H., Blein, O., Anzar, C. 2013. Notice explicative de la carte géologique du maroc au 1/50 000 –feuille al glo’a-. Département de lEnergie et des Mines. éditions du service géologique du Maroc.Team, s.- i. d. (n.d.), from scikit-image: http://scikitimage. org/docs/dev/auto_examples/segmentation/ plot_marked_watershed.html?fbclid=IwAR2z YJ0VCkLBvsWUJuku-x9sGdzx7pz0W_O5- ho4O5KgPTVfsYl35flDFIc#sphx-glr-auto- examples-segmentation-plot-marked-watershed- py. 29 November 2018.
• Vialard, A. 2018. Segmentation et Analyse d’images (partie 1). LaBRI, Université Bordeaux 1.
• Vincent, L., Soille, P. 1991. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Transactions on Pattern