A Comparison among Different Machine Learning Algorithms in Land Cover Classification Based on the Google Earth Engine Platform: The Case Study of Hung Yen Province, Vietnam

Authors

  • Le Thi Lan

    1. Faculty of Natural Resources and Environment, Vietnam National University of Agriculture, Trau Quy, Gia Lam, Ha Noi 100000, Vietnam; 2. Faculty of Land Management, Hanoi University of Natural Resources and Environment, Phu Dien, Bac Tu Liem, Ha Noi 100000, Vietnam
  • Tran Quoc Vinh

    Faculty of Natural Resources and Environment, Vietnam National University of Agriculture, Trau Quy, Gia Lam, Ha Noi 100000, Vietnam
  • Pham Quy Giang

    Faculty of Environment, Ha Long University, Uong Bi City, Quang Ninh Province 200000, Vietnam

DOI:

https://doi.org/10.30564/jees.v7i1.6652
Received: 20 May 2024 | Revised: 20 October 2024 | Accepted: 24 October 2024 | Published Online: 19 November 2024

Abstract

Based on the Google Earth Engine cloud computing data platform, this study employed three algorithms including Support Vector Machine, Random Forest, and Classification and Regression Tree to classify the current status of land covers in Hung Yen province of Vietnam using Landsat 8 OLI satellite images, a free data source with reasonable spatial and temporal resolution. The results of the study show that all three algorithms presented good classification for five basic types of land cover including Rice land, Water bodies, Perennial vegetation, Annual vegetation, Built-up areas as their overall accuracy and Kappa coefficient were greater than 80% and 0.8, respectively. Among the three algorithms, SVM achieved the highest accuracy as its overall accuracy was 86% and the Kappa coefficient was 0.88. Land cover classification based on the SVM algorithm shows that Built-up areas cover the largest area with nearly 31,495 ha, accounting for more than 33.8% of the total natural area, followed by Rice land and Perennial vegetation which cover an area of over 30,767 ha (33%) and 15,637 ha (16.8%), respectively. Water bodies and Annual vegetation cover the smallest areas with 8,820 (9.5%) ha and 6,302 ha (6.8%), respectively. The results of this study can be used for land use management and planning as well as other natural resource and environmental management purposes in the province.

Keywords:

Google Earth Engine; Land Cover; Landsat; Machine Learning Algorithm

References

[1] Fischer, M., Arthur, G., 2010. Handbook of applied spatial analysis: Software tools, methods and applications. Springer: Berlin, Germany. pp. 125–134.

[2] Rajan, M., Navin, S., Loganathan, A., et al., 2020. Survey on Land Use/Land Cover (LU/LC) change analysis in remote sensing and GIS environment: Techniques and Challenges. Environmental Science and Pollution Research. 27(24), 29900−29926.

[3] Sellami, E.L.M., Rhinane, H., 2022. 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.

[4] Ouchra, H., Belangour, A., Erraissi, A., 2023. Machine learning algorithms for satellite image classification using Google Earth Engine and Landsat satellite data: Morocco case study. IEEE Access. 11, 71127−71142.

[5] Ramachandra, T.V., Mondal, T., Setturu, B., 2023. Relative performance evaluation of machine learning algorithms for land use classification using multispectral moderate resolution data. SN Applied Sciences. 5, 274.

[6] Hamad, R., 2020. An assessment of artificial neural networks support vector machines and decision trees for land cover classification using sentinel-2A. Data Science. 8, 459.

[7] Yuh, Y.G., Tracz, W., Matthews, H.D., et al., 2023. Application of machine learning approaches for land cover monitoring in northern Cameroon. Ecological Informatics. 74, 101955.

[8] Cai, Y., Guan, K., Peng, J., et al., 2018. A high-performance and in-season classification system of field-level crop types using time-series Landsat data and a machine learning approach. Remote Sensing of Environment. 210, 35.

[9] Biswas, J., Jobaer, M.A., Haque, S.F., et al., 2023. Mapping and monitoring land use land cover dynamics employing Google Earth Engine and machine learning algorithms on Chattogram, Bangladesh. Heliyon. 9(11), e21245.

[10] Mhanna, S., Halloran, L.J.S., Zwahlen, F., et al., 2023. Using machine learning and remote sensing to track land use/land cover changes due to armed conflict. Science of The Total Environment. 898, 165600.

[11] Mollick, T., Azam, M.G., Karim, S., 2023. Geospatial-based machine learning techniques for land use and land cover mapping using a high-resolution unmanned aerial vehicle image. Remote Sensing Applications: Society and Environment. 9, 100859.

[12] Bui, T.H.T., Trinh, T.T., 2020. Classification of surface cover extraction objects in the Non nuoc Cao Bang global geopark area based on cloud computing platform. Journal of Natural Resources and Environmental Sciences. 31, 65.

[13] Dang, T.T., 2021. Online exploitation of satellite image databases, comparison of machine learning algorithms on land cover classification on Google Earth Engine platform. In Proceedings of the National Conference on Solutions to Connect and Share Database Systems for Training and Management in the Field of Natural Resources and Environment; 21 December 2021; Hanoi University of Natural Resources and Environment: Ha Noi, Vietnam. p. 192.

[14] Nguyen, T.T., Phan, V.T., Nguyen, V.Q., et al., 2022. Using Sentinel 2 satellite images and machine learning algorithm to establish the current status map of forests in Bu Dang District, Binh Phuoc Province. Can Tho University Journal of Science. 58(6B), 150.

[15] Abdi, A.M., 2020. Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data. GIScience Remote Sensing. 57, 1.

[16] Visa, S., Ramsay, B., Ralescu, A.L., et al., 2011. Confusion matrix-based feature selection. Proceedings of the 22nd Midwest Artificial Intelligence and Cognitive Science Conference; Cincinnati, OH, USA; 16–17 April 2011. p. 120.

[17] Zhewen, Z., Fakhrul, I., Liaqat, A.W., et al., 2024. Comparison of three machine learning algorithms using Google Earth Engine for Land Use Land Cover classification. Rangeland Ecology & Management. 92, 129.

[18] Gong, P., Howarth, P.J., 1990. An assessment of some factors influencing multispectral land-cover classification. Photogrammetric Engineering & Remote Sensing. 56, 597.

[19] Foody, G.M., Mathur, A., Sanchez-Hernandez, C., et al., 2006. Training set size requirements for the classification of a specific class. Remote Sensing of the Environment. 104, 1–14.

[20] Van Niel, T., Mcvicar, T., Datt, B., 2005. On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification. Remote Sensing of the Environment. 98, 468.

[21] Zhang, H., He, J., Chen, S., et al., 2023. Comparing three methods of selecting training samples in supervised classification of multispectral remote sensing images. Sensors. 23(20), 8530.

[22] Phinzi, K., Ngetar, N.S., Pham, Q.B., et al., 2023. Understanding the role of training sample size in the uncertainty of high-resolution LULC mapping using random forest. Earth Science Informatics. 16, 3667.

[23] Li, C., Wang, J., Wang, L., et al., 2014. Comparison of classification algorithms and training sample sizes in urban land classification with Landsat thematic mapper imagery. Remote Sensing. 6(2), 964.

[24] May, F.P., Santos, R.A., Toledo, G.R., et al., 2022. Mapping of land cover with optical images, supervised algorithms, and Google Earth Engine. Sensors. 22(13), 4729.

[25] Kamusoko, C., 2022. Land cover classification accuracy assessment. In: Kamusoko, C. (Ed.). Optical and SAR Remote Sensing of Urban Areas: A Practical Guide (Springer Geography). Springer: Singapore. p. 105.

[26] Chen, M., Sun, Z., Newell, B.H., et al., 2020. Missing pixel reconstruction on Landsat 8 Analysis Ready Data Land Surface Temperature image patches using Source-Augmented Partial Convolution. Remote Sensing. 12(19), 3143.

[27] General Statistics Office of Vietnam, 2023. Statistical yearbook of 2022. Statistical Publishing House: Hanoi, Vietnam. pp. 41–100.

Downloads

How to Cite

Lan, L. T., Vinh, T. Q., & Pham Quy, G. (2025). A Comparison among Different Machine Learning Algorithms in Land Cover Classification Based on the Google Earth Engine Platform: The Case Study of Hung Yen Province, Vietnam. Journal of Environmental & Earth Sciences, 7(1), 132–139. https://doi.org/10.30564/jees.v7i1.6652

Issue

Vol. 7 , Iss. 1 (January 2025): In Progress

Article Type

Article

License

Copyright © 2025 Le Thi Lan, Tran Quoc Vinh, Pham Quy Giang

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