Slope-driven edge analysis of high-resolution LiDAR data for automated detection of cultural terraces in Slovenia
Abstract
Cultural terraces were often constructed to improve agriculture. Some terraces are still in use, while others have been abandoned. Knowledge of their locations is important for their preservation or potential reuse. There have been several attempts worldwide to create a register of terraces. In Slovenia, a suitable register has not yet been created due to heavy overgrowth and significant differences in cultural terrace types across different regions of the country. This research proposes detecting terraces using a LiDAR digital elevation model, geoinformation tools, and additional spatial data. The method detects sharp changes in slope data and creates polygons where such changes are detected in close proximity. The main advantage of the method is that it does not require any training samples yet still provides accurate results despite the diversity of terraced areas. We applied the method in Slovenia and achieved an accuracy of 91 percent, a precision of 76 percent, and a recognition value of 66 percent in one test area, and 92, 47, and 65 percent in another designated test area. To achieve higher accuracy, the input settings can be adapted to regional characteristics, which confirms earlier findings that terraces in Slovenia exhibit high diversity.
References
ABDI, A.M. 2020. Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data. GIScience & Remote Sensing 57. (1): 1–20. https://doi.org/10.1080/15481603.2019.1650447
ASAL, F.F.F. 2019. Comparative analysis of the digital terrain models extracted from airborne LiDAR point clouds using different filtering approaches in residential landscapes. Advances in Remote Sensing 8. 51–75. https://doi.org/10.4236/ars.2019.82004
AŽMAN MOMIRSKI, L. and KLADNIK, D. 2009. Terraced landscapes in Slovenia. Acta geographica Slovenica 49. (1): 7–37. https://doi.org/10.3986/AGS49101
BERČIČ, T. 2016. Discovering terraced areas in Slovenia: Reliable detection with LiDAR. Annales. Series historia et sociologia 26. (3): 449–468. https://doi.org/10.19233/ASHS.2016.35
BERČIČ, T. and AŽMAN MOMIRSKI, L. 2023. Inventory of dry-stone terraced landscape in the Vipava Valley. Geodetski vestnik 67. (4): 427–441. https://doi.org/10.15292/geodetski-vestnik.2023.04.427-441
CAPOLUPO, A., KOOISTRA, L. and BOCCIA, L. 2018. A novel approach for detecting agricultural terraced landscapes from historical and contemporaneous photogrammetric aerial photos. International Journal of Applied Earth Observation and Geoinformation 73. 800–810. https://doi.org/10.1016/j.jag.2018.08.008
CIGLIČ, R., GLUŠIČ, A., ŠTAUT, L. and ČEHOVIN ZAJC, L. 2024. Towards the deep learning recognition of cultivated terraces based on LiDAR data: The case of Slovenia. Moravian Geographical Reports 32. (1): 66–78. https://doi.org/10.2478/mgr-2024-0006
DAI, W., HU, G., HUANG, N., ZHANG, P., YAN, X. and TANG, G. 2019. A contour-directional detection for deriving terrace ridge from open source images and digital elevation models. IEEE Access 7. 129215–129224. https://doi.org/10.1109/ACCESS.2019.2940437
DE REU, J., BOURGEOIS, J., BATS, M., ZWERTVAEGHER, A., GELORINI, V., DE SMEDT, P., CHU, W., ANTROP, M., DE MAEYER, P., FINKE, P., VAN MEIRVENNE, M., VERNIERS, J. and CROMBE, P. 2013. Application of the topographic position index to heterogeneous landscapes. Geomorphology 186. 39–49. https://doi.org/10.1016/j.geomorph.2012.12.015
DIAZ-VARELA, R.A, ZARCO-TEJADA, P.J, ANGILERI, V. and LOUDJANI, P. 2014. Automatic identification of agricultural terraces through object-oriented analysis of very high resolution DSMs and multispectral imagery obtained from an unmanned aerial vehicle. Journal of Environmental Management 134. 117–126. https://doi.org/10.1016/j.jenvman.2014.01.006
DROBNJAK, V, 1990. Fizičnogeografski pomen kulturnih teras (Physicalgeography significance of cultural terraces). In Primorje – Zbornik 15. zborovanja slovenskih geografov. Ed.: OROŽEN ADAMIČ, M., Ljubljana, Zveza geografov Slovenije, 139–144.
ESRI 2025. How Slope works. ArcGIS Pro 3.4 by Environmental Systems Research Institute. Redlands, CA, USA, ESRI Inc. Available at https://pro.arcgis.com/en/pro-app/3.4/tool-reference/spatial-analyst/how-slope-works.htm
FERRARESE, F., PAPPALARDO, S.E., COSNER, A., BRUGNARO, S., ALUM, K., DAL POZZO, A. and DE MARCHI, M. 2019. Mapping agricultural terraces in Italy. Methodologies applied in the MAPTER project. World Terraced Landscapes: History, Environment, Quality of Life 9. 179–194. https://doi.org/10.1007/978-3-319-96815-5_11
FISHER, J.R.B., ACOSTA, E.A., DENNEDY‐FRANK, P.J., KROEGER, T. and BOUCHER, T.M. 2018. Impact of satellite imagery spatial resolution on land use classification accuracy and modelled water quality. Remote Sensing in Ecology and Conservation 4. (2): 137–149. https://doi.org/10.1002/rse2.61
GLUŠIČ, A., CIGLIČ, R. and ČEHOVIN ZAJC, L. 2021. Zaznavanje terasiranih pokrajin kot semantična segmentacija digitalnega modela višin (Detection of terraced landscapes as semantic segmentation of a digital elevation model). Zbornik mednarodne Elektrotehniške in računalniške conference, Portorož, Slovenija, ERK’2021. 378–381. http://www.dlib.si/?URN=URN:NBN:SI:DOC-BMENDE0Q
HICKS, S.A., STRÜMKE. I., THAMBAWITA, V., HAMMOU, M., RIEGLER, M.A., HALVORSEN, P. and PARASA, S. 2022. On evaluation metrics for medical applications of artificial intelligence. Scientific Reports 12. (1): 5979. https://doi.org/10.1038/s41598-022-09954-8
JACCARD, P. 1912. The distribution of the flora in the Alpine zone. New Phytologist 11. (2): 37–50. https://doi.org/10.1111/j.1469-8137.1912.tb05611.x
KADYROV, R., STATSENKO, E. and NGUYEN, T.H. 2024. Integrating μCT imaging of core plugs and transfer learning for automated reservoir rock characterization and tomofacies identification. Marine and Petroleum Geology 168. 107014. https://doi.org/10.1016/j.marpetgeo.2024.107014
KLADNIK, D., CIGLIČ, R., GERŠIČ, M., KOKALJ, Ž., VOLK BAHUN, M., PERKO, D., LENARČIČ, M., KERBLER, B.K., OROŽEN ADAMIČ, M. and VOVK, A. 2016. Terasirane pokrajine: ob sedemdesetletnici Geografskega inštituta Antona Melika ZRC SAZU (Terraced landscapes: on the occasion of the seventieth anniversary of the Anton Melik Geographical Institute ZRC SAZU). Ljubljana, Založba ZRC.
KLADNIK, D. 2017. Terraced Landscapes. Ljubljana, Založba ZRC. https://doi.org/10.3986/9789610500193
KOENDERS, R., LINDENBERGH, R.C. STORMS, J.E.A. and MENENT, M. 2014. Multiscale curvatures for identifying channel locations from DEMs. Computers & Geosciences 68. 11–21. https://doi.org/10.1016/j.cageo.2014.03.016
KRIŽAJ SMRDEL, H. 2010. Kulturne terase v slovenskih pokrajinah (Cultural terraces in Slovenian landscapes). Dela 34. 39–60. https://doi.org/10.4312/dela.34.39-60
LU, Y., LI, X., XIN, L., SONG, H. and WANG, X. 2023. Mapping the terraces on the Loess Plateau based on a deep learning-based model at 1.89 m resolution. Scientific Data 10. (1): 115. https://doi.org/10.1038/s41597-023-02005-5
Ministry of Agriculture, Forestry and Food 2025. Evidenca dejanske rabe kmetijskih in gozdnih zemljišč (Records of actual use of agricultural and forest land). Ljubljana, MKGP.
PERKO, D., CIGLIČ, R. and HRVATIN, M. 2021. Landscape macrotypologies and microtypologies of Slovenia. Acta geographica Slovenica 61. (3): 7–89. https://doi.org/10.3986/AGS.10384
PIJL, A., REUTER, L.E.H., QUARELLA, E., VOGEL, T.A. and TAROLLI, P. 2020. GIS-based soil erosion modelling under various steep-slope vineyard practices. CATENA 193. 104604. https://doi.org/10.1016/j.catena.2020.104604
PIJL, A., QUARELLA, E., VOGEL, T.A., D’AGOSTINO, V. and TAROLLI, P. 2021. Remote sensing vs. field-based monitoring of agricultural terrace degradation. International Soil and Water Conservation Research 9. (1): 1–10. https://doi.org/10.1016/j.iswcr.2020.09.001
PIPAN, P. and KOKALJ, Ž. 2017. Transformation of the Jeruzalem Hills cultural landscape with modern vineyard terraces. Acta geographica Slovenica 57. (2): 149–162. https://doi.org/10.3986/AGS.4629
Slovenia Forest Service 2025. Evidenca gozdnih vlak – interno delovno gradivo Zavoda za gozdove Slovenije (Records of forest tracks – internal working material of the Slovenian Forest Service). Ljubljana, ZGS.
Slovenian Environmental Agency 2015. Lasersko skeniranje Slovenije (Laser scanning of Slovenia). Ljubljana, Agencija za Okolje, Republika Slovenija.
SOFIA, G., BAILLY, J.S., CHEHATA, N., TAROLLI, P. and LEVAVASSEUR, F. 2016. Comparison of pleiades and LiDAR digital elevation models for terraces detection in farmlands. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 9. (4): 1567–1576. https://doi.org/10.1109/JSTARS.2016.2516900
SPANÒ, A., SAMMARTANO, G., CALCAGNO TUNIN, F., CERISE, S. and POSSI, G. 2018. GIS-based detection of terraced landscape heritage: comparative tests using regional DEMs and UAV data. Applied Geomatics 10. (2): 77–97. https://doi.org/10.1007/s12518-018-0205-7
ŠTAUT, L. 2025. Agricultural terraces in Slovenia. Zenodo 1 October, Online publication. https://doi.org/10.5281/zenodo.17242982
SUN, W., ZHANG, Y., MU, X., LI, J., GAO, P., ZHAO, G., DANG, T. and CHIEW, F. 2019. Identifying terraces in the hilly and gully regions of the Loess Plateau in China. Land Degradation & Development 30. (17): 2126-2138. https://doi.org/10.1002/ldr.3405
Surveying and Mapping Authority of the Republic of Slovenia 2025a. Digitalni model reliefa (Digital elevation model). Ljubljana, Geodetska Uprava, Republika Slovenija.
Surveying and Mapping Authority of the Republic of Slovenia 2025b. Gospodarska javna infrastruktura (Public infrastructure cadastre). Ljubljana, Geodetska Uprava, Republika Slovenija.
SUSLADKAR, O., DESHMUKH, G., NAG, S., MANTRAVADI, A., MAKWANA, D., RAVICHANDRAN, S., CHANDRA TEJA, R.S., H CHAVHAN, G., MOHAN, C.K. and MITTAL, S. 2022. ClarifyNet: A high-pass and low-pass filtering based CNN for single image dehazing. Journal of Systems Architecture 132. 102736. https://doi.org/10.1016/j.sysarc.2022.102736
TITL, J. 1965. Socialnogeografski problemi na koprskem podeželju (Socio-geographical problems in the Koper countryside). Koper, Lipa.
TRIGLAV ČEKADA, M. and BRIC, V. 2015. Končan je projekt laserskega skeniranja Slovenije (The project of laser scanning of Slovenia is completed). Geodetski vestnik 59. (3): 586–592.
VAN COILLIE, F.M.B., GARDIN, S., ANSEEL, F., DUYCK, W., VERBEKE, L.P.C. and DE WULF, R.R. 2014. Variability of operator performance in remote-sensing image interpretation: the importance of human and external factors. International Journal of Remote Sensing 35. (2): 754–778. https://doi.org/10.1080/01431161.2013.873152
VERBOVŠEK, T., POPIT, T. and KOKALJ, Ž. 2019. VAT method for visualization of mass movement features: An alternative to hill-shaded DEM. Remote Sensing 11. (24): 2946. https://doi.org/10.3390/rs11242946
YU, M., RUI, X., XIE, W., XU, X. and WEI, W. 2022. Research on automatic identification method of terraces on the Loess Plateau based on deep transfer learning. Remote Sensing 14. (10): 2446. https://doi.org/10.3390/rs14102446
ZAKŠEK, K., OŠTIR, K. and KOKALJ, Ž. 2011. Sky-view factor as a relief visualization technique. Remote Sensing 3. (2): 398–415. https://doi.org/10.3390/rs3020398
ZHANG, Y., SHI, M., ZHAO, X., WANG, X., LUO, Z. and ZHAO, Y. 2017. Methods for automatic identification and extraction of terraces from high spatial resolution satellite data (China-GF-1). International Soil and Water Conservation Research 5. (1): 17–25. https://doi.org/10.1016/j.iswcr.2017.02.002
ZHAO, F., XIONG, L., WANG, C., WANG, H., WEI, H. and TANG, G. 2021. Terraces mapping by using deep learning approach from remote sensing images and digital elevation models. Transactions in GIS 25. (5): 2438–2454. https://doi.org/10.1111/tgis.12824
Copyright (c) 2026 Lenart Štaut, Rok Ciglič, Blaž Repe
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
