Preliminary Study on Land Cover Mapping in Village on Transitional Volcanic Landscape Using Deep Learning with UAV Orthophoto

Authors

  • Trida Ridho Fariz Universitas Negeri Semarang Author
  • Fathia Lutfiananda The University of Edinburgh Author

Keywords:

deep learning, Land Cover Mapping, DEEPNESS, UAV orthophoto

Abstract

This preliminary study explores the use of DEEPNESS, a deep learning tool via QGIS, for land cover mapping in the Tubansari Sub-Village - Bompon Watershed, a transitional volcanic landscape with complex human and environmental dynamics. The region faces challenges such as rapid land cover changes, landslides, erosion, and unsustainable land use driven by population growth and agricultural expansion. DEEPNESS efficiently processed 85.1 hectares of 10 cm resolution UAV orthophoto in about 5 seconds. However, its segmentation accuracy was unsatisfactory for village areas, mainly due to the model's training on datasets from regions like Poland, which differ in key features like building types and roof structures. Despite this, the study highlights the potential of deep learning for large-scale land cover mapping. Future work should focus on fine-tuning the model with localized data, exploring urban areas, and using higher-resolution or multi-spectral imagery to improve accuracy. This research lays the foundation for advancing land cover mapping to support sustainable land management, disaster mitigation, and environmental conservation in similar volcanic landscapes.

Author Biography

  • Fathia Lutfiananda, The University of Edinburgh

    School of GeoSciences

References

Adzima, A. F., Setiawan, M. A., & Mardiatno, D. (2020). Classification of anthropogenic landforms in the rural area: study case Bompon catchment, Central Java. IOP Conference Series: Earth and Environmental Science, 451(1), 12039. IOP Publishing.

Alhassan, V., Henry, C., Ramanna, S., & Storie, C. (2020). A deep learning framework for land-use/land-cover mapping and analysis using multispectral satellite imagery. Neural Computing and Applications, 32, 8529–8544.

Aliyyah, H. L., Pulungan, N., & Sartohadi, J. (2022). Soil water availability for crops on landslide deposits in Bompon Sub-Watershed, Magelang. IOP Conference Series: Earth and Environmental Science, 974(1), 12042. IOP Publishing.

Aszkowski, P., & Ptak, B. (2022). QGIS: Deepness: Deep Neural Remote Sensing. Retrieved from https://qgis-plugin-deepness.readthedocs.io/en/latest/index.html

Aszkowski, P., Ptak, B., Kraft, M., Pieczyński, D., & Drapikowski, P. (2023). Deepness: Deep neural remote sensing plugin for QGIS. SoftwareX, 23, 101495.

Fariz, T. R., Jatmiko, R. H., & Mei, E. T. W. (2023). Pemanfaatan Foto Udata UAV untuk Pemetaan Kerentanan Fisik Rumah Terhadap Longsor di Sub-DAS Bompon. Jurnal Ilmu Lingkungan, 21(4), 819–829.

Fariz, T. R., Jatmiko, R. H., Mei, E. T. W., Arnanto, A., Ramlah, R., & Ramadhan, M. F. (2020). Pemanfaatan foto udara format kecil untuk pemetaan bidang tanah di Sub DAS Bompon. Jurnal Tunas Geografi Vol, 9(01).

Fariz, T. R., Jatmiko, R. H., Mei, E. T. W., & Lutfiananda, F. (2023). Interpretation on aerial photography for house identification on landslide area at Bompon sub-watershed. AIP Conference Proceedings, 2683(1). AIP Publishing.

Isnaini, R. (2019). Analisis bencana tanah longsor di wilayah Jawa Tengah. Islamic Management and Empowerment Journal, 1(2), 144–145.

Karra, K., Kontgis, C., Statman-Weil, Z., Mazzariello, J. C., Mathis, M., & Brumby, S. P. (2021). Global land use / land cover with Sentinel 2 and deep learning. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 4704–4707. https://doi.org/10.1109/IGARSS47720.2021.9553499

Kumar, M., Bhattacharya, B. K., Pandya, M. R., & Handique, B. K. (2024). Machine learning based plot level rice lodging assessment using multi-spectral UAV remote sensing. Computers and Electronics in Agriculture, 219, 108754.

Maes, J., Kervyn, M., de Hontheim, A., Dewitte, O., Jacobs, L., Mertens, K., … Poesen, J. (2017). Landslide risk reduction measures: A review of practices and challenges for the tropics. Progress in Physical Geography, 41(2), 191–221.

Marfai, M. A., King, L., Singh, L. P., Mardiatno, D., Sartohadi, J., Hadmoko, D. S., & Dewi, A. (2008). Natural hazards in central Java province, Indonesia: an overview. Environmental Geology, 56, 335–351.

Nhindyasari, P. D., Maulanda, E., Setiawan, O., Sartohadi, J., & Pulungan, N. A. H. J. (2024). The Role of Slope Position on Soil Erosion Acceleration in the Tertiary-Quaternary Volcanic Landscape. Ecological Engineering & Environmental Technology (EEET), 25(12).

Noviyanto, A., Sartohadi, J., & Purwanto, B. H. (2020). The distribution of soil morphological characteristics for landslide-impacted Sumbing Volcano, Central Java-Indonesia. Geoenvironmental Disasters, 7(1), 25.

Pradhita, J. Y., Rachmawati, T. A., & Usman, F. (2022). Pemetaan Risiko Bencana Tanah Longsor di Kecamatan Dawe, Kabupaten Kudus. Planning for Urban Region and Environment Journal (PURE), 11(2), 69–76.

Purwaningsih, R., Sartohadi, J., & Setiawan, M. A. (2020). Trees and crops arrangement in the agroforestry system based on slope units to control landslide reactivation on volcanic foot slopes in Java, Indonesia. Land, 9(9), 327.

Rahmi, M., Setiawan, M. A., & Mardiatno, D. (2019). Analisis Kekeringan Berdasarkan Bentuklahan Di DAS Bompon. Media Komunikasi Geografi, 20(2), 90–100.

Sambodo, A. P., & Arpornthip, T. (2021). Increasing the efficiency of detailed soil resource mapping on transitional volcanic landforms using a geomorphometric approach. Applied and Environmental Soil Science, 2021(1), 8867647.

Sambodo, A. P., Setiawan, M. A., & Rokhmaningtyas, R. P. (2018). The evaluation of modified productivity index method on the transitional volcanic-tropical landscape. IOP Conference Series: Earth and Environmental Science, 200(1), 12011. IOP Publishing.

Sartohadi, J., Rahma, A. D., & Nugraha, S. S. (2024). Productive conservation at the landslide prone area under the threat of rapid land cover changes. Open Geosciences, 16(1), 20220700.

Setyawan, B., Sartohadi, J., & Hadmoko, D. S. (2016). Analysis of Building Position and Orientation to Assess the Building Vulnerability to Landslide Through the Interpretation of 2D Small Format Aerial Photo (Case Study in Bompon Catchment, Magelang Regency). 1st International Conference on Geography and Education (ICGE 2016), 239–243. Atlantis Press.

Trimasukmana, D. J. (2019). Upaya Restrukturisasi Kawasan Hutan Gunung Lio Kabupaten Brebes Pasca Bencana Tanah Longsor Berbasis Kearifan Lokal Melalui Community Development. Indonesian Journal of Conservation, 7(1).

Zhao, J., Kumar, A., Banoth, B. N., Marathi, B., Rajalakshmi, P., Rewald, B., … Guo, W. (2022). Deep-learning-based multispectral image reconstruction from single natural color RGB image—Enhancing UAV-based phenotyping. Remote Sensing, 14(5), 1272.

Zhou, H., Huang, F., Lou, W., Gu, Q., Ye, Z., Hu, H., & Zhang, X. (2025). Yield prediction through UAV-based multispectral imaging and deep learning in rice breeding trials. Agricultural Systems, 223, 104214.

Downloads

Published

2025-08-23

Article ID

13252

Issue

Section

Articles