Comparison of SVM, K-NN, RF, CART, and GNB Algorithms for Water Bodies Detection Using Sentinel-2 Level-2a Imagery in Nakhon Pathom, Thailand
(1) Universitas Pendidikan Ganesha
(2) Universitas Pendidikan Ganesha
(3) Universitas Pendidikan Ganesha
(4) Universitas Pendidikan Ganesha
(5) Universitas Pendidikan Ganesha
(6) Universitas Pendidikan Ganesha
(7) Universitas Pendidikan Ganesha
(8) Universitas Pendidikan Ganesha
(*) Corresponding Author
Abstract
Satellite imagery is utilized in various fields, one of which is land use and land cover (LULC) analysis. This study aims to classify water bodies using machine learning models such as SVM, K-NN, RF, CART, and GNB. The data source is obtained from the Google Earth Engine (GEE) platform using Sentinel-2 Level-2A satellite imagery, with a dataset of 5,514 data points per year. The Pixel-Based approach is used as the main method for data extraction, while CRISP-DM is applied as a structured methodology for data management. The parameter indices used include the BSI, NDBI, MNDWI, NDVI and AWEIsh. The results of these calculations serve as dataset features for training algorithms in the model development and training process. Each model has its own parameters, making parameter selection crucial in the training process. Model evaluation is conducted using a confusion matrix. Based on confusion matrix analysis, accuracy, precision, recall, and F1-score are calculated. Among the five models, SVM achieves the highest accuracy at 87%, followed by RF and K-NN. This indicates that the SVM model performs better in binary classification. Ground truth analysis is also conducted using the QGIS platform, which visualizes the classification results, with SVM providing the best visualization.
Full Text:
PDFReferences
[1] A. G. S. Ramadhan, “Pemanfaatan Penginderaan Jauh Untuk Mengidentifikasi,” Geografi, vol. XX Nomor X, no. March, 2022.
[2] A. Tassi and M. Vizzari, “Object-oriented lulc classification in google earth engine combining snic, glcm, and machine learning algorithms,” Remote Sens (Basel), vol. 12, no. 22, pp. 1–17, Nov. 2020, doi: 10.3390/rs12223776.
[3] C. Avci, M. Budak, N. Yagmur, and F. B. Balcik, “Comparison between random forest and support vector machine algorithms for LULC classification,” International Journal of Engineering and Geosciences, vol. 8, no. 1, pp. 1–10, Feb. 2023, doi: 10.26833/ijeg.987605.
[4] H. Ghosh, M. A. Tusher, I. S. Rahat, S. Khasim, and S. N. Mohanty, “Water Quality Assessment Through Predictive Machine Learning,” in Lecture Notes in Networks and Systems, Springer Science and Business Media Deutschland GmbH, 2023, pp. 77–88. doi: 10.1007/978-981-99-3177-4_6.
[5] W. Jiang et al., “A new index for identifying water body from sentinel-2 satellite remote sensing imagery,” in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH, Aug. 2020, pp. 33–38. doi: 10.5194/isprs-Annals-V-3-2020-33-2020.
[6] H. Ouchra, A. Belangour, and A. Erraissi, “A Comparative Study on Pixel-based Classification and Object-Oriented Classification of Satellite Image,” International Journal of Engineering Trends and Technology, vol. 70, no. 8, pp. 206–215, Aug. 2022, doi: 10.14445/22315381/IJETT-V70I8P221.
[7] A. Dervisoglu et al., “Comparison of Pixel-Based and Object-Based Classification Methods in Determination of Wetland Coastline,” International Journal of Environment and Geoinformatics (IJEGEO), vol. 7, no. 2, pp. 213–219, 2020, doi: 10.30897/ijegeo.
[8] L. Qu, Z. Chen, M. Li, J. Zhi, and H. Wang, “Accuracy improvements to pixel-based and object-based LULC classification with auxiliary datasets from google earth engine,” Remote Sens (Basel), vol. 13, no. 3, Feb. 2021, doi: 10.3390/rs13030453.
[9] D. W. Triscowati and A. W. Wijayanto, “PELUANG DAN TANTANGAN DALAM PEMANFAATAN TEKNOLOGI PENGINDERAAN JAUH DAN MACHINE LEARNING UNTUK PREDIKSI DATA TANAMAN PANGAN YANG LEBIH AKURAT,” Seminar Nasional Official Statistics, vol. 2019, no. 1, 2020, doi: 10.34123/semnasoffstat.v2019i1.230.
[10] F. Traoré, S. Palé, A. Zaré, M. K. Traoré, B. Ouédraogo, and J. Bonkoungou, “A Comparative Analysis of Random Forest and Support Vector Machines for Classifying Irrigated Cropping Areas in The Upper-Comoé Basin, Burkina Faso,” Indian J Sci Technol, vol. 17, no. 8, pp. 713–722, Feb. 2024, doi: 10.17485/IJST/v17i8.78.
[11] D. M. Abdullah and A. M. Abdulazeez, “Machine Learning Applications based on SVM Classification: A Review,” Qubahan Academic Journal, vol. 3, no. 4, pp. 206–218, Nov. 2023, doi: 10.48161/Issn.2709-8206.
[12] M. C. R. Cordeiro, J.-M. Martinez, and S. Peña-Luque, “Remote Sensing of Environment,” vol. 253, p. 112209, 2021, doi: 10.1016/j.rse.2020.112209ï.
[13] D. Danuri and M. Mohd Pozi, “Machine Learning Approaches for Fish Pond Water Quality Classification: Random Forest, Gaussian Naive Bayes, and Decision Tree Comparison,” European Alliance for Innovation n.o., Feb. 2024. doi: 10.4108/eai.21-9-2023.2342964.
[14] H. R. Bittencourt and R. T. Clarke, “Use of Classification and Regression Trees (CART) to Classify Remotely-Sensed Digital Images,” in International Geoscience and Remote Sensing Symposium (IGARSS), 2003, pp. 3751–3753. doi: 10.1109/igarss.2003.1295258.
[15] S. Bayas, S. Sawant, I. Dhondge, P. Kankal, and A. Joshi, “Land Use Land Cover Classification Using Different ML Algorithms on Sentinel-2 Imagery,” in Lecture Notes in Electrical Engineering, Springer Science and Business Media Deutschland GmbH, 2022, pp. 761–777. doi: 10.1007/978-981-19-0840-8_59.
[16] E. M. Sellami and H. Rhinane, “A NEW APPROACH FOR MAPPING LAND USE / LAND COVER USING GOOGLE EARTH ENGINE: A COMPARISON OF COMPOSITION IMAGES,” in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, International Society for Photogrammetry and Remote Sensing, Feb. 2023, pp. 343–349. doi: 10.5194/isprs-archives-XLVIII-4-W6-2022-343-2023.
[17] C. Schröer, F. Kruse, and J. M. Gómez, “A systematic literature review on applying CRISP-DM process model,” in Procedia Computer Science, Elsevier B.V., 2021, pp. 526–534. doi: 10.1016/j.procs.2021.01.199.
[18] U. Bhangale, S. More, T. Shaikh, S. Patil, and N. More, “Analysis of Surface Water Resources Using Sentinel-2 Imagery,” in Procedia Computer Science, Elsevier B.V., 2020, pp. 2645–2654. doi: 10.1016/j.procs.2020.04.287.
[19] W. Jiang et al., “A new index for identifying water body from sentinel-2 satellite remote sensing imagery,” in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH, Aug. 2020, pp. 33–38. doi: 10.5194/isprs-Annals-V-3-2020-33-2020.
[20] S. Praticò, F. Solano, S. Di Fazio, and G. Modica, “Machine learning classification of mediterranean forest habitats in google earth engine based on seasonal sentinel-2 time-series and input image composition optimisation,” Remote Sens (Basel), vol. 13, no. 4, pp. 1–28, Feb. 2021, doi: 10.3390/rs13040586.
DOI: https://doi.org/10.24071/ijasst.v7i1.11608
Refbacks
- There are currently no refbacks.
Publisher : Faculty of Science and Technology
Society/Institution : Sanata Dharma University
This work is licensed under a Creative Commons Attribution 4.0 International License.