Land Cover Classification in Coastal Environments Using SMILE k-NN and Sentinel-2A Imagery: A Case Study in Muara Gembong, Indonesia

Anggun Purnama Edra, Rizki Ginting, Edmund Ucok Armin

Abstract


Muara Gembong, a coastal subdistrict in West Java, has experienced significant land cover changes driven by both anthropogenic activities and environmental dynamics. Accurate land cover classification is essential for sustainable coastal zone management and environmental planning. This study explicitly aims to produce a detailed, up-to-date land cover map for the year 2025 to support evidence-based decision-making in coastal spatial planning and environmental monitoring. The classification was conducted using multispectral Sentinel-2A imagery and the k-Nearest Neighbors (k-NN) algorithm implemented through the SMILE (Statistical Machine Intelligence and Learning Engine) library—a novel approach that leverages a scalable and cloud-based machine learning framework rarely applied in coastal zone contexts. Preprocessing steps included atmospheric correction, cloud masking, and the selection of relevant spectral bands and indices. Five land cover classes were defined: clouds, water bodies, vegetation, bare/open land, and built-up areas. A total of 100 sample points were collected, with 70% used for training and 30% for testing. The classification performance was evaluated using a confusion matrix, resulting in an overall accuracy of 87,24% and a Kappa coefficient of 0.84, indicating strong agreement between the classification results and ground truth data. The results demonstrate not only the effectiveness of the SMILE k-NN algorithm and Sentinel-2A imagery for accurate land cover mapping in dynamic coastal environments, but also provide actionable spatial data that can inform coastal zoning policies, particularly for balancing aquaculture, conservation, and urban expansion in Muara Gembong.

Keywords


Coastal Mapping ; K-Nearest Neighbors ; Land Cover Classification ; Machine Learning ; Muara Gembong ; Remote Sensing ; Sentinel-2A, SMILE

Full Text:

PDF

References


Alongi, D. M. (2008). Mangrove forests: resilience, protection from tsunamis, and responses to global climate change. Estuarine, Coastal and Shelf Science, 76(1), 1–13.

Campbell, J. B., & Wynne, R. H. (2011). Introduction to Remote Sensing (5th ed.). The Guilford Press.

Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37(1), 35–46. https://doi.org/10.1016/0034-4257(91)90048-B

Deng, Y., Wang, S., Bai, X., & Xiang, C. (2020). Land cover classification using machine learning algorithms: A case study in a coastal region of China. Remote Sensing, 12(3), 496. https://doi.org/10.3390/rs12030496

Foody, G. M., & Mathur, A. (2004). A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(6), 1335–1343.

Gascon, F., Bouzinac, C., Thépaut, O., Jung, M., Schröder, M., & Valorge, C. (2017). Copernicus Sentinel-2A calibration and products validation status. Remote Sensing, 9(6), 584. https://doi.org/10.3390/rs9060584

Haifeng, L. (2018). Smile: Statistical Machine Intelligence and Learning Engine [Software library]. Retrieved from https://haifengl.github.io/

Jiang, L., Ma, L., & Yang, X. (2020). Land cover classification using improved KNN with spatial–spectral constraints in high-resolution imagery. Remote Sensing, 12(11), 1856.

Jensen, J. R. (2016). Introductory Digital Image Processing: A Remote Sensing Perspective (4th ed.). Pearson.

Kusmana, C. (2014). Mangrove management and rehabilitation in Indonesia: A review. Ocean & Coastal Management, 103, 62–71.

Li, M., Zhang, H., & Wang, R. (2021). Comparative evaluation of machine learning classifiers in remote sensing image classification for land cover mapping. Sensors, 21(7), 2257.

Lillesand, T. M., Kiefer, R. W., & Chipman, J. W. (2015). Remote Sensing and Image Interpretation (7th ed.). Wiley.

McGranahan, G., Balk, D., & Anderson, B. (2005). The rising tide: assessing the risks of climate change and human settlements in low elevation coastal zones. Environment and Urbanization, 19(1), 17–37.

Peterson, J. T., et al. (2009). A comparison of classification techniques to predict habitat suitability for a rare forest-dwelling species using remote sensing and GIS. Ecological Modelling, 220(7), 1211–1220.

Rahmawati, A., Baiquni, M., & Winarso, H. (2017). Spatial dynamics and ecological crisis in North Coast of Java. Journal of Regional and City Planning, 28(1), 1–12.

Setiawan, Y., Imanda, I. D., & Sibarani, M. C. (2020). Land cover change and mangrove ecosystem degradation in Muara Gembong, Indonesia. IOP Conference Series: Earth and Environmental Science, 599, 012062.

Zhao, W., & Du, S. (2016). Learning multiscale and deep representations for classifying remotely sensed imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 113, 155–165. https://doi.org/10.1016/j.isprsjprs.2016.01.004




DOI: https://doi.org/10.17509/jpis.v34i1.84434

Refbacks



Copyright (c) 2025 Universitas Pendidikan Indonesia (UPI)

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.