A detection-screening framework for karez (ancient underground irrigation system) using deep learning and geospatial analysis
Source abstract
Abstract
Karez, an ancient engineering marvel, utilizes gravity to transport underground water to the surface without external power. Typically, a karez comprises numerous shafts (vertical wells), and traditional mapping methods are both time-consuming and labor-intensive. To address these challenges, this study developed an integrated detection-screening framework for karez mapping. The karez shafts were detected by using high spatial resolution satellite imagery and deep learning architectures (Faster-RCNN, SSD, YoloV3, and MMDetection). Subsequently, a directed fan-shaped buffering method, combined with hierarchical clustering, was introduced to filter out misidentified shaft-like structures. Results showed that the MMDetection outperformed other models, achieving a mean average precision (mAP50-95) of 0.833. Field validation confirmed that the screening methods eliminated 90.20% of false shaft detections. This study has obtained the largest number of karez shafts to date in the study area, while providing a transferable technical framework for global applications in cultural heritage documentation and arid land water management.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Archaeological Research and Protection · Water management and technologies · Archaeology and Historical Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (68)
Show source-provided references
1. Abudu, S. et al. A karez system’s dilemma: a cultural heritage on a shelf or still a viable technique for water resiliency in arid regions, in Socio-Environmental Dynamics along the Historical Silk Road (eds Yang, L.E. et al.) 507–525 (Springer International Publishing, 2019).10.1007/978-3-030-00728-7_22 ↗
2. English, P. W. The Origin and Spread of Qanats in the Old World. 12 (1968).
3. Noori, R. et al. Anthropogenic depletion of Iran’s aquifers. Proc. Natl. Acad. Sci. USA 118, e2024221118 (2021).10.1073/pnas.2024221118 ↗
4. Hayes-Rich, E. et al. Searching for hidden waters: the effectiveness of remote sensing in assessing the distribution and status of a traditional, earthen irrigation system (khettara) in Morocco. J. Archaeol. Sci. Rep. 51, 104175 (2023).
5. Ebrahimi, A. et al. Kariz (Ancient Aqueduct) system: a review on geoengineering and environmental studies. Environ. Earth Sci. 80, 236 (2021).10.1007/s12665-021-09545-2 ↗
6. Faiz, M. E. & Ruf, T. An introduction to the khettara in Morocco: two contrasting cases. in Water and Sustainability in Arid Regions: Bridging the Gap Between Physical and Social Sciences, (eds. Schneier-Madanes G., Courel, M.-F.) 151–163 (Springer, 2010).10.1007/978-90-481-2776-4_10 ↗
7. Beraaouz, M. et al. Khettaras in the Tafilalet oasis (Morocco): contribution to the promotion of tourism and sustainable development. Built Herit. 6, 24 (2022).10.1186/s43238-022-00073-x ↗
8. Lightfoot, D. R. Moroccan khettara: traditional irrigation and progressive desiccation. Geoforum 27, 261–273 (1996).10.1016/0016-7185(96)00008-5 ↗
9. Palerm-Viqueira, J. Las galerías filtrantes o Qanats en México: introducción y tipología de técnicas. Agric. Soc. y. Desarro. 1, 133–145 (2004).
10. Al-Marshoudi, A. S. & Sulong. J. The Aflaj Systems in the Sultanate of Oman: its traditional-engineer construction and operation. In Proc. AWAM International Conference on Civil Engineering 2022 (Springer Nature, 2024).10.1007/978-981-99-6026-2_18 ↗
11. Remmington, G. Transforming tradition: the aflaj and changing role of traditional knowledge systems for collective water management. J. Arid Environ. 151, 134–140 (2018).10.1016/j.jaridenv.2017.10.003 ↗
12. Alsharhan, A. S. & Rizk, Z. E. Aflaj Systems: history and factors affecting recharge and discharge, in Water Resources and Integrated Management of the United Arab Emirates (eds Alsharhan A. S. & Rizk, Z. E.) 257–280 (Springer International Publishing, 2020).10.1007/978-3-030-31684-6_8 ↗
13. Boutadara, Y., Remini, B. & Benmamar, S. The foggaras of Bouda (Algeria): from drought to flood. Appl. Water Sci. 8, 162 (2018).10.1007/s13201-018-0822-7 ↗
14. Kendouci, M. A. et al. The impact of traditional irrigation (Foggara) and modern (drip, pivot) on the resource non-renewable groundwater in the Algerian Sahara. Energy Procedia 36, 154–162 (2013).10.1016/j.egypro.2013.07.018 ↗
15. Boualem, R., Bachir, A. M. S. & Rabah, K. The foggara: a traditional system of irrigation in arid regions. Geosci. Eng. 60, 30–37 (2014).10.2478/gse-2014-0011 ↗
16. Lasaponara, R., J. Lancho, R. & Masini, N. Puquios: the Nasca response to water shortage, in The Ancient Nasca World: New Insights from Science and Archaeology (eds Lasaponara, R., Masini, N., Orefici, G.) 279–327 (Springer International Publishing, 2016).10.1007/978-3-319-47052-8_13 ↗
17. Joji, V. S., Gayen, A. & Saha, D. Harvesting of water by tunnelling: a case study from lateritic terrains of Western Ghats, India. J. Earth Syst. Sci. 130, 202 (2021).10.1007/s12040-021-01687-y ↗
18. Mostafaeipour, A. Historical background, productivity and technical issues of qanats. Water Hist. 2, 61–80 (2010).10.1007/s12685-010-0018-z ↗
19. Kobori, I. Notes from the Turpan Basin: pioneering research on the karez. in Water and Sustainability in Arid Regions: Bridging the Gap Between Physical and Social Sciences (eds. Schneier-Madanes G., Courel, M.-F.) 139–149 (Springer, 2010).10.1007/978-90-481-2776-4_9 ↗
20. Maghrebi, M. et al. Anthropogenic decline of ancient, sustainable water systems: qanats. Groundwater 61, 139–146 (2023).10.1111/gwat.13248 ↗
21. Abudu, S. et al. Vitality of ancient karez systems in arid lands: a case study in Turpan region of China. Water Hist. 3, 213–225 (2011).10.1007/s12685-011-0044-5 ↗
22. Megdiche-Kharrat, F., Ragala, R. & Moussa, M. Mapping land use and dynamics of vegetation cover in Southeastern Arabia using remote sensing: the study case of Wilayat Nizwa (Oman) from 1987 to 2016. Arab. J. Geosci. 12, 450 (2019).10.1007/s12517-019-4596-5 ↗
23. Al-Kindi, K. M. et al. Assessing the impact of land use and land cover changes on Aflaj Systems over a 36-year period. Remote Sens. 15, 1787 (2023).10.3390/rs15071787 ↗
24. Barbaix, S. et al. The use of historical sources in a multi-layered methodology for karez research in Turpan, China. Water Hist. 12, 281–297 (2020).10.1007/s12685-020-00259-z ↗
25. Lou, H. et al. Quantitative reevaluation of the function of Karez using remote sensing technology. Ecol. Indic. 166, 112249 (2024).10.1016/j.ecolind.2024.112249 ↗
26. Al-Kindi, K. M. & Janizadeh, S. Machine learning and hyperparameters algorithms for identifying groundwater Aflaj potential mapping in semi-arid ecosystems using LiDAR, Sentinel-2, GIS data, and analysis. Remote Sens. 14, 5425 (2022).10.3390/rs14215425 ↗
27. Noori, R. et al. Decline in Iran’s groundwater recharge. Nat. Commun. 14, 6674 (2023).10.1038/s41467-023-42411-2 ↗
28. Maghrebi, M., Noori, R. & AghaKouchak, A. Iran: renovated irrigation network deepens water crisis. Nature 618, 238 (2023).10.1038/d41586-023-01851-y ↗
29. Gui, S. et al. Remote sensing object detection in the deep learning era—a review. Remote Sens. 16, 327 (2024).10.3390/rs16020327 ↗
30. Chai, J. et al. Deep learning in computer vision: a critical review of emerging techniques and application scenarios. Mach. Learn. Appl. 6, 100134 (2021).
31. Pathak, R. et al. An object detection approach for detecting damages in heritage sites using 3-D point clouds and 2-D visual data. J. Cult. Herit. 48, 74–82 (2021).10.1016/j.culher.2021.01.002 ↗
32. Chu, Y.-C. et al. Automated wall moisture detection in heritage sites based on convolutional neural network (CNN) for infrared imagery. Appl. Sci. 15, 6495 (2025).10.3390/app15126495 ↗
33. Gao, C. et al. Applying optimized YOLOv8 for heritage conservation: enhanced object detection in Jiangnan traditional private gardens. Herit. Sci. 12, 31 (2024).10.1186/s40494-024-01144-1 ↗
34. Huo, D., Yang, S. & Hou, M. Using the improved YOLOv7-Seg model to segment symbols from rock art images. npj Herit. Sci. 13, 16 (2025).10.1038/s40494-025-01620-2 ↗
35. Tang, H. et al. Application of object detection algorithm for efficient damages identification of the conservation of heritage buildings. Archaeol. Prospect. 31, 233–247 (2024).10.1002/arp.1947 ↗
36. Shen, J. et al. An algorithm based on lightweight semantic features for ancient mural element object detection. npj Herit. Sci. 13, 70 (2025).10.1038/s40494-025-01565-6 ↗
37. Anand, Dravid. T., Jayanth, J. T. Deep learning applications for identifying and detecting heritage sites. In Proc. International Conference on Inventive Computation Technologies (ICICT) (IEEE, 2024).10.1109/ICICT60155.2024.10544486 ↗
38. Trier, Ø. D., Reksten, J. H. & Løseth, K. Automated mapping of cultural heritage in Norway from airborne lidar data using faster R-CNN. Int. J. Appl. Earth Obs.Geoinf. 95, 102241 (2021).
39. Soroush, M. et al. Deep learning in archaeological remote sensing: automated qanat detection in the Kurdistan region of Iraq. Remote Sens. 12, 500 (2020).10.3390/rs12030500 ↗
40. Li, Q. et al. Automatic mapping of karez in Turpan Basin based on Google Earth images and the YOLOv5 Model. Remote Sens. 14, 3318 (2022).10.3390/rs14143318 ↗
41. Li, Q. et al. Impact analysis of land use and land cover change on karez in Turpan Basin of China. Remote Sens. 15, 2146 (2023).10.3390/rs15082146 ↗
42. Buławka, N., Orengo, H. A. & Berganzo-Besga, I. Deep learning-based detection of qanat underground water distribution systems using HEXAGON spy satellite imagery. J. Archaeol. Sci. 171, 106053 (2024).10.1016/j.jas.2024.106053 ↗
43. Liqiang, H. Four Ancient Projects Added to WHIS (China Daily, accessed 6th October 2024) https://www.chinadaily.com.cn/a/202409/04/WS66d7b55ea3108f29c1fc9ff2.html#:~:text=Conveying%20water%20from%20deep%20underground%20to%20the%20surface%20and.
44. Cultural Relics Bureau of Xinjiang Uygur Autonomous Region, X. Immovable Cultural Relics: Turpan District Volume (Xinjiang Fine Arts Photography Publishing House, 2015)
45. Amjoud, A. B. & Amrouch, M. Object detection using deep learning, CNNs and vision transformers: a review. IEEE Access 11, 35479–35516 (2023).10.1109/ACCESS.2023.3266093 ↗
46. Ren, S. et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 1137–1149 (2017).10.1109/TPAMI.2016.2577031 ↗
47. Liu, W. et al. SSD: Single Shot MultiBox Detector. in Computer Vision – ECCV 2016. 2016. Cham: Springer International Publishing.10.1007/978-3-319-46448-0_2 ↗
48. Redmon, J. & Farhadi A. YOLOv3: an incremental improvement. https://doi.org/10.48550/arXiv.1804.02767 (2018).10.48550/arXiv.1804.02767 ↗
49. Chen, K. et al. MMDetection: open MMLab detection toolbox and benchmark. https://doi.org/10.48550/arXiv.1906.07155 (2019).10.48550/arXiv.1906.07155 ↗
50. Ran, X. et al. Comprehensive survey on hierarchical clustering algorithms and the recent developments. Artif. Intell. Rev. 56, 8219–8264 (2023).10.1007/s10462-022-10366-3 ↗
51. Manning, C.D. & Schütze, H. Foundations of Statistical Natural Language Processing (The MIT Press, 1999)
52. Manning, C. D., Raghavan, P. & Schütze, H. Introduction to Information Retrieval (Cambridge University Press, 2008).10.1017/CBO9780511809071 ↗
53. Barbaix, S. et al. An integrated approach to modelling the interaction of the natural landscape and the karez water system in Turpan (Xinjiang, P.R.C.). Landsc. Res. 47, 1–19 (2022).10.1080/01426397.2022.2104828 ↗
54. Liu, X. & Yilihan, A. Watching the Karez: A Documentary of the First Phase of the Repair and Reinforcement Project (Xinjiang People’s Publishing House, 2012).
55. Chen, J. A Preliminary Study of The Fourth National Cultural Heritage Survey (Hakka Cultural Heritage Vision, 2024).
56. Endreny, T. A. & Gokcekus, H. Ancient eco-technology of qanats for engineering a sustainable water supply in the Mediterranean Island of Cyprus. Environ. Geol. 57, 249–257 (2009).10.1007/s00254-008-1274-4 ↗
57. Ebrahimi, A., Dehghan, M. J. & Ashtari, A. Contribution of gravity and Bristow methods for Karez (aqueduct) detection. J. Appl. Geophys. 161, 37–44 (2019).10.1016/j.jappgeo.2018.12.005 ↗
58. Yenigun, K. et al. Ancient karez systems in Şanlıurfa, Türkiye: detection, analysis, and sustainability of historical water supply networks. Spat. Inf. Res. 33, 22 (2025).10.1007/s41324-025-00623-2 ↗
59. Baghban Golpasand, M.-R., Do, N. A. & Dias, D. Impact of pre-existent Qanats on ground settlements due to mechanized tunneling. Transport. Geotech. 21, 100262 (2019).10.1016/j.trgeo.2019.100262 ↗
60. Wang, N. et al. UAV-based remote sensing using visible and multispectral indices for the estimation of vegetation cover in an oasis of a desert. Ecol. Indic. 141, 109155 (2022).10.1016/j.ecolind.2022.109155 ↗
61. Sun, Y. et al. Application of remote sensing technology in water quality monitoring: from traditional approaches to artificial intelligence. Water Res. 267, 122546 (2024).10.1016/j.watres.2024.122546 ↗
62. Dindaroğlu, T. et al. Multispectral UAV and satellite images for digital soil modeling with gradient descent boosting and artificial neural network. Earth Sci. Inform. 15, 2239–2263 (2022).10.1007/s12145-022-00876-7 ↗
63. Adamopoulos, E. Learning-based classification of multispectral images for deterioration mapping of historic structures. J. Build. Pathol. Rehab. 6, 41 (2021).10.1007/s41024-021-00136-z ↗
64. Li, Y. et al. 3D LiDAR and multi-technology collaboration for preservation of built heritage in China: a review. Int. J. Appl. Earth Observ. Geoinf. 116, 103156 (2023).
65. Liu, Z., Zhang, Z. & Hu, W. Multi-level feature fusion and high-fidelity information transfer algorithm for mural inpainting. npj Herit. Sci. 13, 269 (2025).10.1038/s40494-025-01810-y ↗
66. Biswas, S. et al. Attention-enabled hybrid convolutional neural network for enhancing human–robot collaboration through hand gesture recognition. Comput. Electr. Eng. 123, 110020 (2025).10.1016/j.compeleceng.2024.110020 ↗
67. Zhang, Q. et al. A Mamba-based vision transformer for fine-grained image segmentation of mural figures. npj Herit. Sci. 13, 204 (2025).10.1038/s40494-025-01682-2 ↗
68. Badamasi, H. A review of GIS-based hydrological models for sustainable groundwater management. in Current Directions in Water Scarcity Research (ed. Zakwan, M. et al.) (Elsevier, 2022).