Comparison of Machine Learning Methods for Satellite Image Classification: A Case Study of Casablanca Using Landsat Imagery and Google Earth Engine

Authors

  • Hafsa Ouchra

    Laboratory of Information Technology and Modeling LTIM, Hassan II University, Faculty of Sciences Ben M'sik, Casablanca, 20670, Morocco
  • Abdessamad Belangour

    Laboratory of Information Technology and Modeling LTIM, Hassan II University, Faculty of Sciences Ben M'sik, Casablanca, 20670, Morocco
  • Allae Erraissi

    Chouaib Doukkali University, Polydisciplinary Faculty of Sidi Bennour, El Jadida, 24000, Morocco

DOI:

https://doi.org/10.30564/jees.v5i2.5928
Received: 27 August 2023 | Revised: 27 October 2023 | Accepted: 31 October 2023 | Published Online: 14 November 2023

Abstract

Satellite image classification is crucial in various applications such as urban planning, environmental monitoring, and land use analysis. In this study, the authors present a comparative analysis of different supervised and unsupervised learning methods for satellite image classification, focusing on a case study in Casablanca using Landsat 8 imagery. This research aims to identify the most effective machine-learning approach for accurately classifying land cover in an urban environment. The methodology used consists of the pre-processing of Landsat imagery data from Casablanca city, the authors extract relevant features and partition them into training and test sets, and then use random forest (RF), SVM (support vector machine), classification, and regression tree (CART), gradient tree boost (GTB), decision tree (DT), and minimum distance (MD) algorithms. Through a series of experiments, the authors evaluate the performance of each machine learning method in terms of accuracy, and Kappa coefficient. This work shows that random forest is the best-performing algorithm, with an accuracy of 95.42% and 0.94 Kappa coefficient. The authors discuss the factors of their performance, including data characteristics, accurate selection, and model influencing.

Keywords:

Supervised learning; Unsupervised learning; Satellite image classification; Machine learning; Google Earth Engine

References

[1] Ouchra, H., Belangour, A., Erraissi, A. (editors), 2023. An overview of GeoSpatial Artificial Intelligence technologies for city planning and development. 2023 Fifth International Conference on Electrical, Computer and Communication Technologies (ICECCT); 2023 Feb 22-24; Erode, India. New York: IEEE. p. 1-7. DOI: https://doi.org/10.1109/ICECCT56650.2023.10179796

[2] Ouchra, H., Belangour, A. (editors), 2021. Satellite image classification methods and techniques: A survey. 2021 IEEE International Conference on Imaging Systems and Techniques (IST); 2021 Aug 24-26; Kaohsiung, Taiwan. New York: IEEE. p. 1-6. DOI: https://doi.org/10.1109/IST50367.2021.9651454

[3] Ouchra, H., Belangour, A., Erraissi, A., 2022. A comparative study on pixel-based classification and object-oriented classification of satellite image. International Journal of Engineering Trends and Technology. 70(8), 206-215. DOI: https://doi.org/10.14445/22315381/IJETT-V70I8P221

[4] Ouchra, H., Belangour, A., Erraissi, A. (editors), 2022. Satellite data analysis and geographic information system for urban planning: A systematic review. 2022 International Conference on Data Analytics for Business and Industry (ICDABI); 2022 Oct 25-26; Sakhir, Bahrain. New York: IEEE. p. 558-564. DOI: https://doi.org/10.1109/ICDABI56818.2022.10041487

[5] Ouchra, H., Belangour, A., Erraissi, A. (editors), 2022. Spatial data mining technology for GIS: A review. 2022 International Conference on Data Analytics for Business and Industry (ICDABI); 2022 Oct 25-26; Sakhir, Bahrain. New York: IEEE. p. 655-659. DOI: https://doi.org/10.1109/ICDABI56818.2022.10041574

[6] Landsat Data Access [Internet]. U.S. Geological Survey [cited 2022 Aug 20]. Available from: https://www.usgs.gov/landsat-missions/landsat-data-access?qt-science_support_page_related_con=0#qt-science_support_page_related_con

[7] Ouchra, H., Belangour, A., Erraissi, A. (editors), 2022. Machine learning for satellite image classification: A comprehensive review. 2022 International Conference on Data Analytics for Business and Industry (ICDABI); 2022 Oct 25-26; Sakhir, Bahrain. New York: IEEE. p. 1-5. DOI: https://doi.org/10.1109/ICDABI56818.2022.10041606

[8] Awad, M. (editor), 2021. Google Earth Engine (GEE) cloud computing based crop classification using radar, optical images and Support Vector Machine Algorithm (SVM). 2021 IEEE 3rd International Multidisciplinary Conference on Engineering Technology (IMCET); 2021 Dec 8-10; Beirut, Lebanon. New York: IEEE. p. 71-76. DOI: https://doi.org/10.1109/IMCET53404.2021.9665519

[9] Magidi, J., Nhamo, L., Mpandeli, S., et al., 2021. Application of the random forest classifier to map irrigated areas using google earth engine. Remote Sensing. 13(5), 876. DOI: https://doi.org/10.3390/RS13050876

[10] Natekin, A., Knoll, A., 2013. Gradient boosting machines, a tutorial. Frontiers in Neurorobotics. 7, 21. DOI: https://doi.org/10.3389/fnbot.2013.00021

[11] Ali, I., Rehman, A.U., Khan, D.M., et al., 2022. Model selection using K-means clustering algorithm for the symmetrical segmentation of remote sensing datasets. Symmetry. 14(6), 1149. DOI: https://doi.org/10.3390/sym14061149

[12] Artelt, A., Hammer, B., 2019. Efficient computation of counterfactual explanations of LVQ models. arXiv preprint arXiv:1908.00735.

[13] Gorelick, N., Hancher, M., Dixon, M., et al., 2017. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment. 202, 18-27. DOI: https://doi.org/10.1016/j.rse.2017.06.031

[14] Ouchra, H.A.F.S.A., Belangour, A., Erraissi, A.L.L.A.E., 2023. Machine learning algorithms for satellite image classification using Google Earth Engine and Landsat satellite data: Morocco case study. IEEE Access. 11, 71127-71142. DOI: https://doi.org/10.1109/ACCESS.2023.3293828

[15] Hu, Y., Dong, Y., 2018. An automatic approach for land-change detection and land updates based on integrated NDVI timing analysis and the CVAPS method with GEE support. ISPRS Journal of Photogrammetry and Remote Sensing. 146, 347-359. DOI: https://doi.org/10.1016/J.ISPRSJPRS.2018.10.008

[16] Yang, L., Driscol, J., Sarigai, S., et al., 2022. Google Earth Engine and artificial intelligence (AI): A comprehensive review. Remote Sensing. 14(14), 3253. DOI: https://doi.org/10.3390/RS14143253

[17] Wahbi, M., El Bakali, I., Ez-zahouani, B., et al., 2023. A deep learning classification approach using high spatial satellite images for detection of built-up areas in rural zones: Case study of Souss-Massa region-Morocco. Remote Sensing Applications: Society and Environment. 29, 100898. DOI: https://doi.org/10.1016/J.RSASE.2022.100898

[18] Taji, K., Ait Abdelouahid, R., Ezzahoui, I., et al. (editors), 2021. Review on architectures of aquaponic systems based on the Internet of Things and artificial intelligence: Comparative study. Proceedings of the 4th International Conference on Networking, Information Systems & Security; 2021 Apr 1-2; KENITRA AA Morocco. New York: Association for Computing Machinery. p. 1-9. DOI: https://doi.org/10.1145/3454127.3457625

[19] Ouchra, H., Belangour, A., 2021. Object detection approaches in images: A survey. Thirteenth International Conference on Digital Image Processing (ICDIP 2021). 11878, 132-141. DOI: https://doi.org/10.1117/12.2601452

[20] Ouchra, H., Belangour, A., 2021. Object detection approaches in images: A weighted scoring model based comparative study. International Journal of Advanced Computer Science and Applications(IJACSA). 12(8).

[21] Phan, T.N., Kuch, V., Lehnert, L.W., 2020. Land cover classification using Google Earth Engine and random forest classifier—The role of image composition. Remote Sensing. 12(15), 2411. DOI: https://doi.org/10.3390/RS12152411

[22] Mahyoub, S., Rhinane, H., Fadil, A., et al. (editors), 2020. Using of open access remote sensing data in google earth engine platform for mapping built-up area in Marrakech City, Morocco. 2020 IEEE International Conference of Moroccan Geomatics, MORGEO; 2020 May 11-13; Casablanca, Morocco. New York: IEEE. DOI: https://doi.org/10.1109/MORGEO49228.2020.9121912

[23] Sellami, E.M., Rhinane, H.A.S.S.A.N., 2023. A new approach for mapping land use/land cover using Google Earth Engine: A comparison of composition images. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 48, 343-349. DOI: https://doi.org/10.5194/isprs-archives-XLVIII-4-W6-2022-343-2023

[24] Chemchaoui, A., Brhadda, N., Alaoui, H.I., et al. 2023. Accuracy assessment and uncertainty of the 2020 10-meter resolution land use land cover maps at local scale. Case: talassemtane national park, Morocco. DOI: https://doi.org/10.21203/rs.3.rs-2953599/v2

[25] Pérez-Cutillas, P., Pérez-Navarro, A., Conesa-García, C., et al., 2023. What is going on within google earth engine? A systematic review and meta-analysis. Remote Sensing Applications: Society and Environment. 29, 100907. DOI: https://doi.org/10.1016/j.rsase.2022.100907

[26] Jamali, A., 2019. Evaluation and comparison of eight machine learning models in land use/land cover mapping using Landsat 8 OLI: A case study of the northern region of Iran. SN Applied Sciences. 1(11), 1448. DOI: https://doi.org/10.1007/s42452-019-1527-8

[27] Duda, T., Canty, M., 2002. Unsupervised classification of satellite imagery: Choosing a good algorithm. International Journal of Remote Sensing. 23(11), 2193-2212. DOI: https://doi.org/10.1080/01431160110078467

[28] Celik, T., 2009. Unsupervised change detection in satellite images using principal component analysis and k-means clustering. IEEE Geoscience and Remote Sensing Letters. 6(4), 772-776. DOI: https://doi.org/10.1109/LGRS.2009.2025059

[29] Zurqani, H.A., Post, C.J., Mikhailova, E.A., et al., 2019. Mapping urbanization trends in a forested landscape using Google Earth Engine. Remote Sensing in Earth Systems Sciences. 2, 173-182. DOI: https://doi.org/10.1007/s41976-019-00020-y

[30] Masek, J.G., Huang, C., Wolfe, R., et al., 2008. North American forest disturbance mapped from a decadal Landsat record. Remote Sensing of Environment. 112(6), 2914-2926. DOI: https://doi.org/10.1016/j.rse.2008.02.010

[31] Duro, D.C., Franklin, S.E., Dubé, M.G., 2012. A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery. Remote Sensing of Environment. 118, 259-272. DOI: https://doi.org/10.1016/j.rse.2011.11.020

[32] Madhura, M., Venkatachalam, S., 2015. Comparison of supervised classification methods on remote sensed satellite data: An application in Chennai, South India. International Journal of Science and Research. 4(2), 1407-1411.

[33] Rozenstein, O., Karnieli, A., 2011. Comparison of methods for land-use classification incorporating remote sensing and GIS inputs. Applied Geography. 31(2), 533-544. DOI: https://doi.org/10.1016/J.APGEOG.2010.11.006

[34] Kalra, K., Goswami, A.K., Gupta, R., 2013. A comparative study of supervised image classification algorithms for satellite images. International Journal of Electrical, Electronics and Data Communication. 1(10), 10-16.

[35] Akgün, A., Eronat, A.H., Türk, N., 2004. Comparing different satellite image classification methods: an application in Ayvalik District, Western Turkey [Internet]. Available from: https://www.isprs.org/PROCEEDINGS/XXXV/congress/comm4/papers/505.pdf

[36] Niknejad, M., Zadeh, V.M., Heydari, M., 2014. Comparing different classifications of satellite imagery in forest mapping (case study: Zagros forests in Iran). International Research Journal of Applied and Basic Sciences. 8(9), 1407-1415.

[37] Ouchra, H., Belangour, A., Erraissi, A., 2022. A comprehensive study of using remote sensing and geographical information systems for urban planning Internetworking Indonesia Journal. 14(1), 15-20.

[38] Landsat 8 Bands [Internet]. Landsat Science [cited 2023 Oct 26]. Available from: https://landsat.gsfc.nasa.gov/satellites/landsat-8/landsat-8-bands/#

[39] Borra, S., Thanki, R., Dey, N., 2019. Satellite image analysis: Clustering and classification. Springer: Singapore.

[40] Jayaswal, V., 2020. Performance Metrics: Confusion Matrix, Precision, Recall, and F1 Score [Internet]. Towards Data Science [cited 2023 Aug 10]. Available from: https://towardsdatascience.com/performance-metrics-confusion-matrix-precision-recall-and-f1-score-a8fe076a2262

[41] Heydarian, M., Doyle, T.E., Samavi, R., 2022. MLCM: Multi-label confusion matrix. IEEE Access. 10, 19083-19095. DOI: https://doi.org/10.1109/ACCESS.2022.3151048

[42] Coefficient Kappa de Cohen (K) [Internet] [cited 2023 Aug 10]. Available from: https://www.irdp.ch/institut/coefficient-kappa-cohen-2039.html

[43] Abbas, A.W., Minallh, N., Ahmad, N., et al., 2016. K-Means and ISODATA clustering algorithms for landcover classification using remote sensing. Sindh University Research Journal-SURJ (Science Series). 48(2), 315-318.

[44] Mfondoum, A.H.N., Etouna, J., Nongsi, B.K., et al., 2016. Assessment of land degradation status and its impact in arid and semi-arid areas by correlating spectral and principal component analysis neo-bands. International Journal. 5(2), 1539-1560.

[45] NDBI—ArcGIS Pro [Internet] [cited 2023 May 19]. Available from: https://pro.arcgis.com/en/pro-app/latest/arcpy/spatial-analyst/ndbi.htm

[46] Shafaey, M.A., Salem, M.A.M., Ebied, H.M., et al. (editors), 2018. Deep learning for satellite image classification. International Conference on Advanced Intelligent Systems and Informatics; 2018 Sep 1-3; Cairo, Egypt. Cham: Springer International Publishing. p. 383-391. DOI: https://doi.org/10.1007/978-3-319-99010-1_35

[47] Warf, B., 2014. Supervised classification. Encyclopedia of Geography. Sage: Thousand Oaks, California. DOI: https://doi.org/10.4135/9781412939591.n1101

[48] Würsch, L., Hurni, K., Heinimann, A., 2017. Google Earth Engine Image Pre-processing Tool: User Guide [Internet] [cited 2022 Dec 13]. Available from: https://www.cde.unibe.ch/e65013/e542846/e707304/e707386/e707390/CDE_Pre-processingTool-UserGuide_eng.pdf

[49] El Imanni, H.S., El Harti, A., Bachaoui, E.M., et al., 2023. Multispectral UAV data for detection of weeds in a citrus farm using machine learning and Google Earth Engine: Case study of Morocco. Remote Sensing Applications: Society and Environment. 30, 100941. DOI: https://doi.org/10.1016/J.RSASE.2023.100941

[50] Chen, H., Yunus, A.P., Nukapothula, S., et al., 2022. Modelling Arctic coastal plain lake depths using machine learning and Google Earth Engine. Physics and Chemistry of the Earth, Parts A/B/C. 126, 103138. DOI: https://doi.org/10.1016/J.PCE.2022.103138

[51] Amani, M., Ghorbanian, A., Ahmadi, S.A., et al., 2020. Google earth engine cloud computing platform for remote sensing big data applications: A comprehensive review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 13, 5326-5350. DOI: https://doi.org/10.1109/JSTARS.2020.3021052

[52] Tassi, A., Vizzari, M., 2020. Object-oriented lulc classification in google earth engine combining snic, glcm, and machine learning algorithms. Remote Sensing. 12(22), 3776. DOI: https://doi.org/10.3390/rs12223776

Downloads

How to Cite

Ouchra, H., Belangour, A., & Erraissi, A. (2023). Comparison of Machine Learning Methods for Satellite Image Classification: A Case Study of Casablanca Using Landsat Imagery and Google Earth Engine. Journal of Environmental & Earth Sciences, 5(2), 118–134. https://doi.org/10.30564/jees.v5i2.5928

Issue

Vol. 5 , Iss. 2 (October 2023)

Article Type

Article

License

Copyright © 2023 Author(s)

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC