Sentinel-2 Satellite Image Processing using Machine Learning Algorithms of the Manombo Nature Reserve

Valerien Eugene Tsaramanana

doi:10.22146/jgise.94152

Sentinel-2 Satellite Image Processing using Machine Learning Algorithms of the Manombo Nature Reserve

https://doi.org/10.22146/jgise.94152

Valerien Eugene Tsaramanana^(1*)

(1) University Fianarantsoa Madagascar
(*) Corresponding Author

Abstract

This paper is based on the fields of satellite image processing and analysis using Sentinel-2 satellite images with machine learning algorithms under Google Earth Engine for the study of land cover evolution in the Manombo Madagascar, nature reserve. The objectives of the study are to identify the elements that occupy the land in the reserve. During our experiments, we compared the best machine learning algorithm using CART, Random Forest, Naive Bayes, SVM to determine the best machine learning algorithm for our Sentinel-2 data. So, we have proposed a methodology to do the treatment and in the end we have treatment results. From our treatments, we can conclude that the use of Random Forest classifier gave the most accuracy on the correct classification.

Keywords

Land use; Sentinel2; Supervised Classification; machine learning; satellite images.

Full Text:

PDF

References

Ah-Pine J. (2019). Machine Learning, University of Lyon 2

Akodéwou, A., Oszwald, J., Akpavi, S., Gazull, L., Akpagana, K., & Gond, V. (2019). Problem of invasive plants in southern Togo (West Africa): contribution of landscape systemic analysis and remote sensing. Biotechnologie, Agronomie, Société et Environnement/Biotechnology, Agronomy, Society and Environment, 23.

Ayoubi S. (2017). « Reunion | Mapping the island's land cover | GeoDev". Available on: http://www.theia-land.art-geodev.fr/la-reunion-cartographie-de-loccupation-des-sols-de-lile/

Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.

Breiman, L., Friedman, J., Olshen, R., & Stone, C. (1984). Cart. Classification and regression trees.

CIRAD. (2018). "Land Use Mapping 2017 Antananarivo", July 12, 2018 9:52 a.m., License: CC BY: Attribution (CC BY, "LEGENDE Project | GeoDev". https://www.theia_land.art-geodev.fr/projets/legend/

Delalay, M., Tiwari, V., Ziegler, A. D., Gopal, V., & Passy, P. (2019). Land-use and land-cover classification using Sentinel-2 data and machine-learning algorithms: operational method and its implementation for a mountainous area of Nepal. Journal of Applied Remote Sensing, 13(1), 014530-014530.

Dupuy, S., Le Mézo, L., & Gaetano, R. (2018). Reunion Island: 2017 land use map

Inglada, J. (2016). Mapping of land cover from optical images. Remote Sensing Observation of Continental Surfaces: Agriculture and Forestry, ISTE Editions, London.

Lawton G. (2020). Supervised and unsupervised learning, https://www.lemagit.fr/conseil/Apprentissage-supervise-et-non-supervise-les-differencier-et-les-combiner , Published on: 14 Oct 2020

Mutanga, O., & Kumar, L. (2019). Google Earth Engine Applications. Remote Sensing, 11(5), 591. https://doi.org/10.3390/rs11050591

Rakotoarison, T. R., Hajalalaina, A. R., & Safidinirina, E. N. (2021). Forest Dynamics with Sentinel 2 in Antanambe between 2005 and 2016 with the Snap Tool. Advances in Remote Sensing, 10(3), 92-101.

Razafinimaro et al. (2022) Land cover classification based optical satellite images using machine learning algorithms, International Journal of Advances in Intelligent Informatics, Vol. 8, No. 3, November 2022, pp. 362-380, https://doi.org/10.26555/ijain.v8i3.803

Rish, I. (2001, August). An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence (Vol. 3, No. 22, pp. 41-46).

Salperwyck, C., Lemaire, V., & Hue, C. (2014). Classifieur naïf de Bayes pondéré pour flux de données. In EGC (pp. 275-286).

Santosa, P. B. (2016). Evaluation of satellite image correction methods caused by differential terrain illumination. Jurnal Forum Geografi. Vol. 30, No. 1 (2016). https://doi.org/10.23917/forgeo.v30i1.1768

Shelestov, Andrii (02/2017). "Exploring Google Earth Engine Platform for Big Data Processing: Classification of Multi-Temporal Satellite Imagery for Crop Mapping". Frontiers in Earth Science (2296-6463), 5 , p. 232994.

Soofi, A. A., & Awan, A. (2017). Classification techniques in machine learning: applications and issues. Journal of Basic & Applied Sciences, 13(1), 459-465, https://doi.org/10.6000/1927-5129.2017.13.76

Weston, J., & Watkins, C. (1998). Multi-class support vector machines (pp. 98-04). Technical Report CSD-TR-98-04, Department of Computer Science, Royal Holloway, University of London, May.

DOI: https://doi.org/10.22146/jgise.94152