Penerapan SAM-Geo untuk Delineasi Otomatis Batas Bidang Tanah Pertanian pada Ortofoto
Abstract
Accurate data on agricultural parcel boundaries are essential to support efficient and equitable agrarian management. Conventional methods such as terrestrial surveys and manual digitization are often costly, time-consuming, and inconsistent. Advances in artificial intelligence-based segmentation models, particularly the Segment Anything Model for Geospatial (SAM-Geo), offer new opportunities to accelerate the automatic delineation of agricultural land parcels. This study aims to evaluate the performance of SAM-Geo in extracting agricultural parcel boundaries from 3.98 cm resolution orthophotos in Sumberrahayu Village, Moyudan Subdistrict, Sleman Regency, Yogyakarta Special Region, Indonesia. The research process includes orthophoto preprocessing, SAM-Geo implementation, mask filtering, and accuracy assessment using both area-based metrics (precision, recall, F1-score, and IoU) and boundary-based metrics (boundary precision, recall, and F1-score) with a 1 m buffer tolerance. The results indicate that SAM-Geo can produce highly precise boundary delineation in homogeneous areas, achieving F1-score and IoU values above 96%, while performance declines in heterogeneous areas due to complex land cover conditions. Overall, this study provides one of the first empirical evaluations of SAM-Geo in agricultural landscapes in Indonesia and highlights its potential as an effective approach for agricultural parcel boundary mapping.
Ketersediaan data batas bidang tanah pertanian yang akurat menjadi prasyarat penting dalam mendukung pengelolaan agraria yang efisien dan berkeadilan. Metode konvensional seperti survei terestris dan digitasi manual seringkali memerlukan biaya tinggi, waktu lama, serta menghasilkan ketidakkonsistenan data. Perkembangan model segmentasi berbasis kecerdasan buatan, khususnya Segment Anything Model for Geospatial (SAM-Geo), membuka peluang baru untuk mempercepat delineasi batas bidang tanah pertanian secara otomatis. Penelitian ini bertujuan mengevaluasi kinerja SAM-Geo dalam mengekstraksi batas bidang pertanian dari ortofoto beresolusi 3,98 cm di Kalurahan Sumberrahayu, Kapanewon Moyudan, Kabupaten Sleman, D.I. Yogyakarta. Metode penelitian mencakup pra-pemrosesan ortofoto, penerapan SAM-Geo, mask filtering, serta evaluasi akurasi menggunakan metrik berbasis area (precision, recall, F1-score, and IoU) dan berbasis batas (boundary precision, recall, and F1-score) dengan toleransi buffer 1 m. Hasil penelitian menunjukkan SAM-Geo menghasilkan delineasi batas sangat presisi pada area homogen dengan F1-score dan IoU di atas 96%, sedangkan performa menurun pada area heterogen akibat kompleksitas tutupan lahan. Temuan ini menegaskan potensi SAM-Geo sebagai pendekatan efektif untuk pemetaan batas bidang pertanian di Indonesia.
References
Aina, D. S. (2025). Pelindungan lahan pertanian: Studi komparatif sistem administrasi pertanahan di Indonesia dan India. Tunas Agraria, 8(1), 92–112. https://doi.org/10.31292/jta.v8i1.407
Amin, G., Oberlin, T., & Demarez, V. (2025). Early season delineation of agricultural fields using a fully convolutional multi-task network and satellite images. Science of Remote Sensing, 12, 100256. https://doi.org/10.1016/j.srs.2025.100256
Arham, I., Sjaf, S., & Darusman, D. (2019). Strategi pembangunan pertanian berkelanjutan di pedesaan berbasis citra drone (Studi kasus Desa Sukadamai Kabupaten Bogor). Jurnal Ilmu Lingkungan, 17(2), 245–255. https://doi.org/10.14710/jil.17.2.245-255
Baroroh, A., & Harintaka, H. (2025). Ekstraksi otomatis tapak bangunan (building footprint) pada ortofoto menggunakan Segment Anything Model (SAM). Elipsoida: Jurnal Geodesi dan Geomatika, 8(1), 52–59. https://doi.org/10.14710/elipsoida.2025.25145
Cao, Y., Liu, C., Wu, Z., Zhang, L., & Yang, L. (2025). Remote sensing image segmentation using Vision Mamba and multi-scale multi-frequency feature fusion. Remote Sensing, 17(8), 1–23. https://doi.org/10.3390/rs17081390
D’Andrimont, R., Claverie, M., Kempeneers, P., Muraro, D., Yordanov, M., Peressutti, D., Batič, M., & Waldner, F. (2023). AI4Boundaries: An open AI-ready dataset to map field boundaries with Sentinel-2 and aerial photography. Earth System Science Data, 15(1), 317–329. https://doi.org/10.5194/essd-15-317-2023
Fariz, T. R., Jatmiko, R. H., Mei, E. T. W., Arnanto, A., & Ramlah, M. F. R. (2020). Pemanfaatan foto udara format kecil untuk pemetaan bidang tanah di Sub DAS Bompon. Jurnal Tunas Geografi, 9(1). https://www.academia.edu/download/96923506/13933.pdf
Gounari, O., Karakizi, C., & Karantzalos, K. (2022). Filtering LPIS data for building trustworthy training datasets for crop type mapping: A case study in Greece. ISPRS Archives, 43(B3-2022), 871–877. https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-871-2022
Hattula, E., Raninen, J., & Zhu, L. (2025). Segment Anything Model with LiDAR-based images for building segmentation in forest areas. ISPRS Archives, 48(M-7–2025), 13–19. https://doi.org/10.5194/isprs-archives-XLVIII-M-7-2025-13-2025
Heimann, C., Minnie, S., & Abrams, M. C. (2025). UMGCINI – Empowering rural communities through geospatial data and digital connectivity. ISPRS Archives, 48(5), 59–64. https://doi.org/10.5194/isprs-archives-XLVIII-M-5-2024-59-2025
Hetang, C., Xue, H., Le, C., Yue, T., Wang, W., & He, Y. (2024). Segment Anything Model for road network graph extraction. IEEE CVPR Workshops, 2556–2566. https://doi.org/10.1109/CVPRW63382.2024.00262
Huang, Z., Yang, X., Liu, Y., Wang, Z., Ma, Y., Jing, H., & Liu, X. (2025). Multi-type change detection and distinction of cultivated land parcels in high-resolution remote sensing images based on Segment Anything Model. Remote Sensing, 17(5). https://doi.org/10.3390/rs17050787
Ji, Y., Wu, W., Wan, G., Zhao, Y., Wang, W., Yin, H., Tian, Z., & Liu, S. (2024). Segment Anything Model-based building footprint extraction for residential complex spatial assessment using LiDAR data and very high-resolution imagery. Remote Sensing, 16(14). https://doi.org/10.3390/rs16142661
Jucker, T., Gosper, C. R., Wiehl, G., Yeoh, P. B., Raisbeck-Brown, N., Fischer, F. J., Langley, H., Newchurch, W., O’Donnell, A. J., Page, G. F. M., Zdunic, K., & Prober, S. M. (2023). Using multi-platform LiDAR to guide the conservation of the world’s largest temperate woodland. Remote Sensing of Environment, 296, 113745. https://doi.org/10.1016/j.rse.2023.113745
Kim, H. S., Olaniyi, I., Chang, A., & Jung, J. (2025). Developing a Segment Anything Model-based framework for automated plot extraction. Precision Agriculture, 26(3), 1–21. https://doi.org/10.1007/s11119-025-10249-x
Kim, J., & Kim, Y. (2024). Integrated framework for unsupervised building segmentation with Segment Anything Model-based pseudo-labeling and weakly supervised learning. Remote Sensing, 16(3). https://doi.org/10.3390/rs16030526
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., & Lo, W.-Y. (2023). Segment Anything. arXiv preprint arXiv:2304.02643. https://arxiv.org/abs/2304.02643
Mena, F., Pathak, D., Najjar, H., Sanchez, C., Helber, P., Bischke, B., Habelitz, P., Miranda, M., Siddamsetty, J. M., Charfuelan, M., Arenas, D., & Vollmer, M. (2025). Adaptive fusion of multi-modal remote sensing data for optimal sub-field crop yield prediction. Remote Sensing of Environment, 318, 114547. https://doi.org/10.1016/j.rse.2024.114547
Minaee, S., Boykov, Y., Porikli, F., Plaza, A., Kehtarnavaz, N., & Terzopoulos, D. (2021). Image segmentation using deep learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7), 3523–3542. https://doi.org/10.1109/TPAMI.2021.3059964
Obialero, M., & Boccardo, P. (2025). Segmentation of multitemporal PlanetScope data to improve the land parcel identification system (LPIS). Remote Sensing, 17(12). https://doi.org/10.3390/rs17121962
Osco, L. P., Wu, Q., de Lemos, E. L., Gonçalves, W. N., Ramos, A. P. M., Li, J., & Marcato, J. (2023). The Segment Anything Model (SAM) for remote sensing applications: From zero to one shot. International Journal of Applied Earth Observation and Geoinformation, 124, 103540. https://doi.org/10.1016/j.jag.2023.103540
Sultan, R. I., Li, C., Zhu, H., Khanduri, P., Brocanelli, M., & Zhu, D. (2023). GeoSAM: Fine-tuning SAM with sparse and dense visual prompting for automated segmentation of mobility infrastructure. arXiv preprint arXiv:2311.11319. https://arxiv.org/abs/2311.11319
Tripathy, P., Baylis, K., Wu, K., Watson, J., & Jiang, R. (2024). Investigating the Segment Anything foundation model for mapping smallholder agriculture field boundaries without training labels. arXiv preprint arXiv:2407.01846. https://arxiv.org/abs/2407.01846
Vafaeinejad, A., Alimohammadi, N., Sharifi, A., & Safari, M. M. (2025). Super-resolution AI-based approach for extracting agricultural cadastral maps: Form and content validation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 5204–5216. https://doi.org/10.1109/JSTARS.2025.3530714
Vallejo Orti, M., Anders, K., Ajayi, O., Bubenzer, O., & Höfle, B. (2024). Integrating multi-user digitising actions for mapping gully outlines using a combined approach of Kalman filtering and machine learning. ISPRS Open Journal of Photogrammetry and Remote Sensing, 12, 100059. https://doi.org/10.1016/j.ophoto.2024.100059
Valman, S. J., Boyd, D. S., Carbonneau, P. E., Johnson, M. F., & Dugdale, S. J. (2024). An AI approach to operationalise global daily PlanetScope satellite imagery for river water masking. Remote Sensing of Environment, 301, 113932. https://doi.org/10.1016/j.rse.2023.113932
Wu, Q., & Osco, L. P. (2023). Samgeo: A Python package for segmenting geospatial data with the Segment Anything Model (SAM). Journal of Open Source Software, 8(89), 5663. https://doi.org/10.21105/joss.05663
Xie, Y., Wu, H., Tong, H., Xiao, L., Zhou, W., Li, L., & Wanger, T. C. (2025). fabSAM: A farmland boundary delineation method based on the Segment Anything Model. arXiv preprint arXiv:2501.12487. https://arxiv.org/abs/2501.12487
Zhang, Z., Shu, D., Liao, C., Liu, C., Zhao, Y., Wang, R., Huang, X., Zhang, M., & Gong, J. (2025). FlexiSAM: A flexible SAM-based semantic segmentation model for land cover classification using high-resolution multimodal remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 227, 594–612. https://doi.org/10.1016/j.isprsjprs.2025.05.028
Zhao, H., Wu, B., Zhang, M., Long, J., Tian, F., Xie, Y., Zeng, H., Zheng, Z., Ma, Z., Wang, M., & Li, J. (2025). A large-scale VHR parcel dataset and a novel hierarchical semantic boundary-guided network for agricultural parcel delineation. ISPRS Journal of Photogrammetry and Remote Sensing, 221, 1–19. https://doi.org/10.1016/j.isprsjprs.2025.01.034
Zheng, J., Ye, Z., Wen, Y., Huang, J., Zhang, Z., Li, Q., Hu, Q., Xu, B., Zhao, L., & Fu, H. (2025). A comprehensive review of agricultural parcel and boundary delineation from remote sensing images: Recent progress and future perspectives. arXiv preprint arXiv:2508.14558. https://arxiv.org/abs/2508.14558
Copyright (c) 2025 Fauzia Aristalindra, Abdul Basith
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
