Ekstraksi Tutupan Lahan Kota Pesisir dari Band Visible dan Perhitungan Indeks Spektral dari Citra Sentinel-2 dengan Arsitektur U-NET
(Studi Kasus: Kota Pekalongan dan Kota Cirebon)
DOI:
https://doi.org/10.31315/imagi.v6i1.16607Keywords:
Ekstraksi Tutupan Lahan, Kota Pesisir, Sentinel-2, Indeks Spektral, U-NetAbstract
Wilayah pesisir merupakan zona peralihan darat dan laut yang mengalami perubahan pemanfaatan lahan sehingga memerlukan data tutupan lahan yang mutakhir untuk mendukung pemutakhiran peta dasar. Kota pesisir di Pantai Utara Jawa seperti Kota Pekalongan dan Kota Cirebon menunjukkan perubahan penggunaan lahan dalam beberapa tahun terakhir. Ekstraksi tutupan lahan dilakukan menggunakan citra Sentinel-2 dengan memanfaatkan kombinasi band visible (Red, Green, Blue), Near Infrared (NIR), serta perhitungan indeks spektral berupa Normalized Difference Vegetation Index (NDVI), Urban Index (UI), dan Modified Normalized Difference Water Index (MNDWI) yang akan menghasilkan single band untuk masing-masing indeks. Band visible dan band hasil perhitungan indeks diolah menggunakan arsitektur U-Net untuk ekstraksi tutupan lahan. Data dianalisis pada Mei dan Juli 2025 dengan perbedaan variasi curah hujan. Model dikembangkan melalui skema encoder dan decoder dengan skip connection, hybrid loss, dan data latih berbasis tile 64×64 piksel yang mewakili seluruh kelas tutupan lahan. Penerapan model di Kota Pekalongan menghasilkan rata-rata F1-score 0,95404 dan IoU 0,91228, sedangkan fine tuning di Kota Cirebon dengan penambahan kelas hutan bakau menghasilkan rata-rata F1-score 0,93835 dan IoU 0,88470. Perbedaan waktu akuisisi menunjukkan variasi respons spektral terutama pada kelas vegetasi, sementara kelas perairan dan terbangun relatif stabil.
References
Davis, J. J. O. N., & States, U. (2006). The relationship between Precision-Recall and ROC curves The Relationship Between Precision-Recall and ROC Curves. Proceedings of the 23rd International Conference on Machine Learning, ICML ’06(June 2006), 23–240. https://doi.org/10.1145/1143844.1143874
Dzaikra, Y. J. (2022). Analisis Ketersediaan Ruang Terbuka Hijau Melalui Metode Object Based Image Analysis (Studi Kasus: Kota Administrasi Jakarta Timur). Jurnal Ilmiah Geomatika, 2(1), 1–15. https://doi.org/10.31315/imagi.v2i1.7847
Gibson, P., Power, C. H. (2000). Introductory Remote Sensing Principles and Concepts (1st ed.) (S. E. Press (ed.)). https://doi.org/https://doi.org/10.4324/9780203714522
Kawamura, M., Jayamanna, S., & Tsujiko, Y. (1996). Relation Between Social and Environmental Conditions in Colombo, Sri Lanka and The Urban Index Estimated by Satellite Remote Sensing Data. International Archives of the Photogrammetry and Remote Sensing, XXXI(Part B7), 321–326.
Kristal, A., H. (2022). Analisis Kehandalan Ekstraksi Garis Tepi Bangunan dari Data Foto Udara Menggunakan Pendekatan Deep Learning Berbasis Mask R-CNN. Geoid, 17(2), 273–285.
Pablo, J., Ibarra, G., Javier, F., & De, C. (2025). Evaluation of the Effectiveness of the UNet Model with Different Backbones in the Semantic Segmentation of Tomato Leaves and Fruits. Horticulturae, 11(514), 1–19. https://doi.org/https:// doi.org/10.3390/horticulturae11050514
Rezatofighi, H., Tsoi, N., Gwak, J., Reid, I., & Savarese, S. (2019). Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 658–666.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation.
Roswintiarti, O., Indriasari, N., Halim, F., Inggit, R., Sari, L., & Hengki, K. (2025). On the Use of Remote Sensing Data for Monitoring NDVI Anomalies and Correlations with Rainfall Anomalies in West Java Province , Indonesia : Addressing Sustainable Development Goal 2. Remote Sensing in Earth Systems Sciences, 8(2), 815–833. https://doi.org/10.1007/s41976-025-00222-7
Sinha, P., Kumar, L., & Reid, N. (2012). Seasonal Variation in Land-Cover Classification Accuracy in a Diverse Region. Photogrammetric Engineering & Remote Sensing, 78(3), 271–280.
Solórzano, J. V, Mas, J. F., Gao, Y., & Gallardo-Cruz, J. A. (2021). Land Use Land Cover Classification with U-Net : Advantages of Combining Sentinel-1 and Sentinel-2 Imagery. MDPI, 13(3600), 1–23. https://doi.org/doi.org/10.3390/rs13183600 Academic
Tjiptanto, G., Sulistiyowati, Endah, S., & Umaroh. (2025a). BULETIN INFORMASI IKLIM EDISI AGUSTUS 2025. Badan Meteorologi, Klimatologi, Dan Geofisika (BMKG), 17–21.
Tjiptanto, G., Sulistiyowati, Endah, S., & Umaroh. (2025b). BULETIN INFORMASI IKLIM EDISI JUNI 2025. Badan Meteorologi, Klimatologi, Dan Geofisika (BMKG), 17–22.
Tucker, C. J. (1979). Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 8(2), 127–150. https://doi.org/https://doi.org/10.1016/0034-4257(79)90013-0
Xu, H. (2006). Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14), 3025–3033. https://doi.org/10.1080/01431160600589179
Yaloveha, V., & Hlavcheva, D. (2021). Spectral Indexes Evaluation for Satellite Images Classification using CNN. JIOS, 45(2), 435–449.
Yang, Z., Calderer, A., He, S., Sotiropoulos, F., Doyle, J. D., Flagg, D. D., MacMahan, J., Wang, Q., Haus, B. K., Graber, H. C., & Shen, L. (2018). Numerical study on the effect of air-sea-land interaction on the atmospheric boundary layer in coastal area. Atmosphere, 9(2), 1–12. https://doi.org/10.3390/atmos9020051
Yeung, M., Sala, E., Schonlieb, C.-B., & Rundo, L. (2022). Computerized Medical Imaging and Graphics Unified Focal loss : Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation. Computerized Medical Imaging and Graphics, 95(November 2021), 1–13. https://doi.org/10.1016/j.compmedimag.2021.102026
Zhu, W. (2023). Effects of Atmospheric Correction on Remote Sensing Statistical Inference in an Aquatic Environment. Remote Sensing, 15(1907), 1–9.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Almaas Syifaa Ardanti, Catur Aries Rokhmana
This work is licensed under a Creative Commons Attribution 4.0 International License.
