{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T09:52:17Z","timestamp":1793613137619,"version":"4.5.0"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:00:00Z","timestamp":1792540800000},"content-version":"vor","delay-in-days":92,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Natural fracture networks govern subsurface fluid flow, rock-mass stability, and strain accommodation in the brittle crust, yet their automated delineation from outcrop imagery remains challenging due to multi-scale size variability, low contrast between fracture boundaries and host-rock texture, and scene clutter from vegetation, shadows, and blast artifacts. Standard encoder-decoder networks apply fixed-size receptive fields that inadequately span the fractal-like scale range of natural discontinuity networks, while gradient-based classical detectors lack the semantic context required to suppress non-structural scene edges. We introduce\n                    <jats:italic>GeoFractNet<\/jats:italic>\n                    : a dilated U-Net coupling ConvNeXt encoder blocks with multi-scale dilated convolutions (\n                    <jats:inline-formula>\n                      <jats:tex-math>$$d \\in \\{1,\\!2,\\!4,\\!8\\}$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    ), gated edge-aware skip connections fusing Scharr and Gabor filter responses, and a Sobel Edge-Aware (SEA) Loss that directly penalizes gradient misalignment at fracture boundaries. The model output is a binary semantic edge map (per-pixel classification of fracture-boundary pixels versus background) rather than a vectorized fracture trace network; conversion to discrete trace objects requires subsequent post-processing. Trained on\n                    <jats:italic>GeoCrack<\/jats:italic>\n                    , an open-access fracture edge dataset of 12,158 annotated patches from 49 structurally and lithologically diverse outcrops across five countries,\n                    <jats:italic>GeoFractNet<\/jats:italic>\n                    achieves mIoU\u00a0\n                    <jats:inline-formula>\n                      <jats:tex-math>$$= 0.91$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    , Dice\u00a0\n                    <jats:inline-formula>\n                      <jats:tex-math>$$= 0.92$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    , and Boundary F\n                    <jats:inline-formula>\n                      <jats:tex-math>$$_1 = 0.90$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    , outperforming all evaluated classical and deep-learning baselines. Compared to the best performing network in literature, YOLACT++,\n                    <jats:italic>GeoFractNet<\/jats:italic>\n                    reduces false positives by 38% and recovers 94% of long-range fracture edges missed by classical (Canny) edge detection on a curated hard-negative evaluation subset (420 patches containing vegetation, blast holes, and strong illumination gradients). Ablation studies confirm that the gated edge-aware skip connections and SEA Loss provide the largest incremental gains in boundary-sensitive metrics, with no architectural component degrading performance at any ablation step. Code, model weights, and the GeoCrack dataset are openly released, providing a reproducible benchmark for automated fracture characterization in structural geology, geomechanics, and reservoir analogue studies.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-58908-x","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T10:26:23Z","timestamp":1784629583000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Semantic edge detection of fractures in geological outcrops using edge aware dilated convolutional networks"],"prefix":"10.1038","volume":"16","author":[{"given":"Mohammed","family":"Yaqoob","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Ishaq","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed Yusuf","family":"Ansari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas Daniel","family":"Seers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"58908_CR1","first-page":"4","volume":"18","author":"T Bratton","year":"2006","unstructured":"Bratton, T. et al. The nature of naturally fractured reservoirs. Oilfield Review 18, 4\u201323 (2006).","journal-title":"Oilfield Review"},{"key":"58908_CR2","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1002\/2017WR022159","volume":"54","author":"R March","year":"2018","unstructured":"March, R., Doster, F. & Geiger, S. Assessment of CO2 storage potential in naturally fractured reservoirs with dual-porosity models. Water Resour. Res. 54, 1650\u20131668 (2018).","journal-title":"Water Resour. Res."},{"key":"58908_CR3","doi-asserted-by":"publisher","first-page":"39606","DOI":"10.1016\/j.ijhydene.2022.09.116","volume":"47","author":"M Zamehrian","year":"2022","unstructured":"Zamehrian, M. & Sedaee, B. Underground hydrogen storage in a naturally fractured gas reservoir: The role of fracture. Int. J. Hydrog. Energy 47, 39606\u201339618 (2022).","journal-title":"Int. J. Hydrog. Energy"},{"key":"58908_CR4","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1144\/SP374.13","volume":"374","author":"TD Seers","year":"2014","unstructured":"Seers, T. D. & Hodgetts, D. Comparison of digital outcrop and conventional data collection approaches for the characterization of naturally fractured reservoir analogues. Geol. Soc. London Spec. Publ. 374, 51\u201377 (2014).","journal-title":"Geol. Soc. London Spec. Publ."},{"key":"58908_CR5","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1016\/j.petrol.2017.11.073","volume":"164","author":"S Ghosh","year":"2018","unstructured":"Ghosh, S., Galvis-Portilla, H. A., Klockow, C. M. & Slatt, R. M. An application of outcrop analogues to understanding the origin and abundance of natural fractures in the Woodford shale. J. Pet. Sci. Eng. 164, 623\u2013639 (2018).","journal-title":"J. Pet. Sci. Eng."},{"key":"58908_CR6","doi-asserted-by":"publisher","first-page":"1643","DOI":"10.5194\/se-11-1643-2020","volume":"11","author":"S Tavani","year":"2020","unstructured":"Tavani, S. et al. Transverse jointing in foreland fold-and-thrust belts: A remote sensing analysis in the eastern Pyrenees. Solid Earth 11, 1643\u20131651 (2020).","journal-title":"Solid Earth"},{"key":"58908_CR7","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.jsg.2016.06.007","volume":"89","author":"L Maerten","year":"2016","unstructured":"Maerten, L., Maerten, F., Lejri, M. & Gillespie, P. Geomechanical paleostress inversion using fracture data. J. Struct. Geol. 89, 197\u2013213 (2016).","journal-title":"J. Struct. Geol."},{"key":"58908_CR8","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.jrmge.2015.11.008","volume":"8","author":"L Zhang","year":"2016","unstructured":"Zhang, L. Determination and applications of rock quality designation (RQD). J. Rock Mech. Geotech. Eng. 8, 389\u2013397 (2016).","journal-title":"J. Rock Mech. Geotech. Eng."},{"key":"58908_CR9","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/s10064-022-02675-2","volume":"81","author":"S Alemdag","year":"2022","unstructured":"Alemdag, S., Sari, M. & Seren, A. Determination of rock quality designation (rqd) in metamorphic rocks: a case study (bayburt-k\u0131rklartepe dam). Bull. Eng. Geol. Environ. 81, 214 (2022).","journal-title":"Bull. Eng. Geol. Environ."},{"key":"58908_CR10","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1306\/0726171609317002","volume":"102","author":"F Fern\u00e1ndez-Ib\u00e1\u00f1ez","year":"2018","unstructured":"Fern\u00e1ndez-Ib\u00e1\u00f1ez, F., DeGraff, J. & Ibrayev, F. Integrating borehole image logs with core: A method to enhance subsurface fracture characterization. AAPG Bulletin 102, 1067\u20131090 (2018).","journal-title":"AAPG Bulletin"},{"key":"58908_CR11","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1080\/10916466.2021.2025072","volume":"40","author":"AA Babasafari","year":"2022","unstructured":"Babasafari, A. A., Chinelatto, G. F. & Vidal, A. C. Fault and fracture study by incorporating borehole image logs and supervised neural network applied to the 3d seismic attributes: A case study of pre-salt carbonate reservoir, santos basin, brazil. Pet. Sci. Technol. 40, 1492\u20131511 (2022).","journal-title":"Pet. Sci. Technol."},{"key":"58908_CR12","doi-asserted-by":"publisher","first-page":"5920716","DOI":"10.1109\/TGRS.2024.3427364","volume":"62","author":"S Dong","year":"2024","unstructured":"Dong, S. et al. A deep learning object detection method for fracture identification using conventional well logs. IEEE Trans. Geosci. Remote Sens. 62, 5920716. https:\/\/doi.org\/10.1109\/TGRS.2024.3427364 (2024).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"58908_CR13","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1306\/A967340A-1738-11D7-8645000102C1865D","volume":"84","author":"PH Hennings","year":"2000","unstructured":"Hennings, P. H., Olson, J. E. & Thompson, L. B. Combining outcrop data and three-dimensional structural models to characterize fractured reservoirs: An example from wyoming. AAPG bulletin 84, 830\u2013849 (2000).","journal-title":"AAPG bulletin"},{"key":"58908_CR14","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.marpetgeo.2019.01.039","volume":"103","author":"E Ukar","year":"2019","unstructured":"Ukar, E., Laubach, S. E. & Hooker, J. N. Outcrops as guides to subsurface natural fractures: Example from the nikanassin formation tight-gas sandstone, grande cache, alberta foothills, canada. Mar. Pet. Geol. 103, 255\u2013275 (2019).","journal-title":"Mar. Pet. Geol."},{"key":"58908_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsg.2024.105222","volume":"186","author":"S Tavani","year":"2024","unstructured":"Tavani, S., Corradetti, A., Rizzo, R. & Seers, T. Best practices towards the digitization of 3d traces from virtual outcrop models. J. Struct. Geol. 186, 105222 (2024).","journal-title":"J. Struct. Geol."},{"key":"58908_CR16","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.marpetgeo.2012.01.010","volume":"35","author":"JF I\u00f1igo","year":"2012","unstructured":"I\u00f1igo, J. F., Laubach, S. E. & Hooker, J. N. Fracture abundance and patterns in the subandean fold and thrust belt, devonian huamampampa formation petroleum reservoirs and outcrops, argentina and bolivia. Mar. Pet. Geol. 35, 201\u2013218 (2012).","journal-title":"Mar. Pet. Geol."},{"key":"58908_CR17","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1130\/GES01276.1","volume":"12","author":"TD Seers","year":"2016","unstructured":"Seers, T. D. & Hodgetts, D. Extraction of three-dimensional fracture trace maps from calibrated image sequences. Geosphere 12, 1323\u20131340 (2016).","journal-title":"Geosphere"},{"key":"58908_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.enggeo.2022.106848","volume":"309","author":"L Yu","year":"2022","unstructured":"Yu, L. et al. Estimation of the representative elementary volume of three-dimensional fracture networks based on permeability and trace map analysis: A case study. Eng. Geol. 309, 106848 (2022).","journal-title":"Eng. Geol."},{"key":"58908_CR19","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.jsg.2015.02.001","volume":"72","author":"H Watkins","year":"2015","unstructured":"Watkins, H., Bond, C. E., Healy, D. & Butler, R. W. Appraisal of fracture sampling methods and a new workflow to characterise heterogeneous fracture networks at outcrop. J. Struct. Geol. 72, 67\u201382 (2015).","journal-title":"J. Struct. Geol."},{"key":"58908_CR20","doi-asserted-by":"publisher","first-page":"487","DOI":"10.5194\/se-10-487-2019","volume":"10","author":"BJ Andrews","year":"2019","unstructured":"Andrews, B. J. et al. How do we see fractures? quantifying subjective bias in fracture data collection. Solid Earth 10, 487\u2013516 (2019).","journal-title":"Solid Earth"},{"key":"58908_CR21","doi-asserted-by":"publisher","first-page":"17","DOI":"10.3390\/fractalfract3020017","volume":"3","author":"R Basirat","year":"2019","unstructured":"Basirat, R., Goshtasbi, K. & Ahmadi, M. Determination of the fractal dimension of the fracture network system using image processing technique. Fractal and Fractional 3, 17 (2019).","journal-title":"Fractal and Fractional"},{"key":"58908_CR22","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10064-022-02638-7","volume":"81","author":"YJ Kashtiban","year":"2022","unstructured":"Kashtiban, Y. J., Shahriar, K. & Bakhtavar, E. Assessment of blasting impacts on the discontinuities in a salt stope and pillar mine using a developed image processing. Bull. Eng. Geol. Environ. 81, 151 (2022).","journal-title":"Bull. Eng. Geol. Environ."},{"key":"58908_CR23","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.cageo.2014.04.012","volume":"69","author":"Y Vasuki","year":"2014","unstructured":"Vasuki, Y., Holden, E.-J., Kovesi, P. & Micklethwaite, S. Semi-automatic mapping of geological structures using uav-based photogrammetric data: An image analysis approach. Comput. Geosci. 69, 22\u201332 (2014).","journal-title":"Comput. Geosci."},{"key":"58908_CR24","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.5194\/se-10-2137-2019","volume":"10","author":"R Prabhakaran","year":"2019","unstructured":"Prabhakaran, R., Bruna, P.-O., Bertotti, G. & Smeulders, D. An automated fracture trace detection technique using the complex shearlet transform. Solid Earth 10, 2137\u20132166 (2019).","journal-title":"Solid Earth"},{"key":"58908_CR25","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1029\/1999RG000074","volume":"39","author":"E Bonnet","year":"2001","unstructured":"Bonnet, E. et al. Scaling of fracture systems in geological media. Rev. Geophys. 39, 347\u2013383 (2001).","journal-title":"Rev. Geophys."},{"key":"58908_CR26","doi-asserted-by":"crossref","unstructured":"Xie, S. & Tu, Z. Holistically-nested edge detection. In Proceedings of the IEEE international conference on computer vision, 1395\u20131403 (2015).","DOI":"10.1109\/ICCV.2015.164"},{"key":"58908_CR27","doi-asserted-by":"crossref","unstructured":"Vondrick, C. & Torralba, A. Generating the future with adversarial transformers. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1020\u20131028 (2017).","DOI":"10.1109\/CVPR.2017.319"},{"key":"58908_CR28","doi-asserted-by":"crossref","unstructured":"Luo, B., Shen, J., Cheng, S., Wang, Y. & Pantic, M. Shape constrained network for eye segmentation in the wild. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision, 1952\u20131960 (2020).","DOI":"10.1109\/WACV45572.2020.9093483"},{"key":"58908_CR29","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, 234\u2013241 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"58908_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrmms.2021.104745","volume":"142","author":"J Chen","year":"2021","unstructured":"Chen, J., Zhou, M., Huang, H., Zhang, D. & Peng, Z. Automated extraction and evaluation of fracture trace maps from rock tunnel face images via deep learning. Int. J. Rock Mech. Min. Sci. 142, 104745 (2021).","journal-title":"Int. J. Rock Mech. Min. Sci."},{"key":"58908_CR31","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1007\/s12145-021-00650-1","volume":"14","author":"H Byun","year":"2021","unstructured":"Byun, H., Kim, J., Yoon, D., Kang, I.-S. & Song, J.-J. A deep convolutional neural network for rock fracture image segmentation. Earth Sci. Inform. 14, 1937\u20131951 (2021).","journal-title":"Earth Sci. Inform."},{"key":"58908_CR32","doi-asserted-by":"publisher","DOI":"10.1029\/2020JB021269","volume":"126","author":"L Matt\u00e9o","year":"2021","unstructured":"Matt\u00e9o, L. et al. Automatic fault mapping in remote optical images and topographic data with deep learning. J. Geophys. Res.: Solid Earth 126, e2020JB021269 (2021).","journal-title":"J. Geophys. Res.: Solid Earth"},{"key":"58908_CR33","first-page":"1101","volume":"43","author":"I Yalcin","year":"2022","unstructured":"Yalcin, I., Can, R., Kocaman, S. & Gokceoglu, C. A cnn architecture for discontinuity determination of rock masses with close range images. nt. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 43, 1101\u20131108 (2022).","journal-title":"nt. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"58908_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Bai, L., Yang, Y. & Ma, Q. Application of an improved u-net neural network on fracture segmentation from outcrop images. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium, 3512\u20133515 (IEEE, 2022).","DOI":"10.1109\/IGARSS46834.2022.9883208"},{"key":"58908_CR35","doi-asserted-by":"crossref","unstructured":"Zhu, W., Khirevich, S. & Patzek, T. Fracture recognition with u-net and pixel-based automatic fracture detection. In Fourth naturally fractured reservoir workshop, vol. 2020, 1\u20135 (European Association of Geoscientists & Engineers, 2020).","DOI":"10.3997\/2214-4609.2020622013"},{"key":"58908_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2023.105463","volume":"182","author":"B Chudasama","year":"2024","unstructured":"Chudasama, B. et al. Automated mapping of bedrock-fracture traces from uav-acquired images using u-net convolutional neural networks. Comput. Geosci. 182, 105463 (2024).","journal-title":"Comput. Geosci."},{"key":"58908_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.enggeo.2024.107874","volume":"345","author":"Y Ji","year":"2025","unstructured":"Ji, Y. et al. Automatic identification of rock fractures based on deep learning. Eng. Geol. 345, 107874 (2025).","journal-title":"Eng. Geol."},{"key":"58908_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrmms.2021.104981","volume":"149","author":"Y-K Lee","year":"2022","unstructured":"Lee, Y.-K., Kim, J., Choi, C.-S. & Song, J.-J. Semi-automatic calculation of joint trace length from digital images based on deep learning and data structuring techniques. Int. J. Rock Mech. Min. Sci. 149, 104981 (2022).","journal-title":"Int. J. Rock Mech. Min. Sci."},{"key":"58908_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-024-04107-0","volume":"11","author":"M Yaqoob","year":"2024","unstructured":"Yaqoob, M. et al. Geocrack: A high-resolution dataset for segmentation of fracture edges in geological outcrops. Sci. Data 11, 1\u201313 (2024).","journal-title":"Sci. Data"},{"key":"58908_CR40","doi-asserted-by":"publisher","first-page":"1073211","DOI":"10.3389\/feart.2023.1073211","volume":"11","author":"Y Shi","year":"2023","unstructured":"Shi, Y. et al. Semi-universal geo-crack detection by machine learning. Front. Earth Sci. 11, 1073211. https:\/\/doi.org\/10.3389\/feart.2023.1073211 (2023).","journal-title":"Front. Earth Sci."},{"key":"58908_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.compgeo.2022.104997","volume":"152","author":"W Zhu","year":"2022","unstructured":"Zhu, W. et al. Enhancing fracture network characterization: A data-driven, outcrop-based analysis. Comput. Geotech. 152, 104997. https:\/\/doi.org\/10.1016\/j.compgeo.2022.104997 (2022).","journal-title":"Comput. Geotech."},{"key":"58908_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsg.2021.104405","volume":"150","author":"R Prabhakaran","year":"2021","unstructured":"Prabhakaran, R., Urai, J. L., Bertotti, G., Weism\u00fcller, C. & Smeulders, D. M. J. Large-scale natural fracture network patterns: Insights from automated mapping in the Lilstock (Bristol Channel) limestone outcrops. J. Struct. Geol. 150, 104405. https:\/\/doi.org\/10.1016\/j.jsg.2021.104405 (2021).","journal-title":"J. Struct. Geol."},{"key":"58908_CR43","doi-asserted-by":"publisher","unstructured":"Liu, Z. et al. A ConvNet for the 2020s. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11976\u201311986, https:\/\/doi.org\/10.1109\/CVPR52688.2022.01167 (2022).","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"58908_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106960","volume":"159","author":"H Zhang","year":"2023","unstructured":"Zhang, H. et al. BCU-Net: Bridging ConvNeXt and U-Net for medical image segmentation. Comput. Biol. Med. 159, 106960. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.106960 (2023).","journal-title":"Comput. Biol. Med."},{"key":"58908_CR45","unstructured":"Oktay, O. Attention U-Net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)."},{"key":"58908_CR46","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1522730","volume":"8","author":"L Mochurad","year":"2025","unstructured":"Mochurad, L. Approach for enhancing the accuracy of semantic segmentation of chest X-ray images by edge detection and deep learning integration. Front. Artif. Intell. 8, 1522730. https:\/\/doi.org\/10.3389\/frai.2025.1522730 (2025).","journal-title":"Front. Artif. Intell."},{"key":"58908_CR47","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI), vol. 9351 of LNCS, 234\u2013241, https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"58908_CR48","doi-asserted-by":"publisher","unstructured":"Chen, L., Zhu, Y., Papandreou, G., Schroff, F. & Adam, H. Encoder\u2013decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), 833\u2013851, https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49 (2018).","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"58908_CR49","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P. & Girshick, R. Mask r-cnn. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961\u20132969, https:\/\/doi.org\/10.1109\/ICCV.2017.322 (2017).","DOI":"10.1109\/ICCV.2017.322"},{"key":"58908_CR50","doi-asserted-by":"publisher","first-page":"10540","DOI":"10.1109\/TPAMI.2020.3014297","volume":"44","author":"D Bolya","year":"2022","unstructured":"Bolya, D., Zhou, C., Xiao, F. & Lee, Y. J. YOLACT++: Better real?time instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 44, 10540\u201310554. https:\/\/doi.org\/10.1109\/TPAMI.2020.3014297 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"58908_CR51","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E. et al. SegFormer: Simple and efficient design for semantic segmentation with transformers. Adv. Neural Inf. Process. Syst. 34, 12077\u201312090 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"58908_CR52","doi-asserted-by":"publisher","unstructured":"Cao, H. et al. Swin-Unet: Unet-like pure transformer for medical image segmentation. In Computer Vision \u2013 ECCV 2022 Workshops, vol. 13803 of Lecture Notes in Computer Science, 205\u2013218, https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9 (Springer, 2023).","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"58908_CR53","unstructured":"Sobel, I. & Feldman, G. A $$3\\times 3$$ isotropic gradient operator for image processing. In Stanford Artificial Intelligence Project (SAIL) Technical Report (1968). Presented at SAIL; widely cited as Sobel operator\u201d."},{"key":"58908_CR54","unstructured":"Prewitt, J. M. S. Object enhancement and extraction. In Picture Processing and Psychophysics 75\u2013149 (Academic Press, 1970)."},{"key":"58908_CR55","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1098\/rspb.1980.0020","volume":"207","author":"D Marr","year":"1980","unstructured":"Marr, D. & Hildreth, E. Theory of edge detection. Proc. R. Soc. Lond. B, Biol. Sci. 207, 187\u2013217. https:\/\/doi.org\/10.1098\/rspb.1980.0020 (1980).","journal-title":"Proc. R. Soc. Lond. B, Biol. Sci."},{"key":"58908_CR56","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"8","author":"J Canny","year":"1986","unstructured":"Canny, J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679\u2013698. https:\/\/doi.org\/10.1109\/TPAMI.1986.4767851 (1986).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"58908_CR57","doi-asserted-by":"publisher","first-page":"SX63","DOI":"10.1190\/INT-2015-0004.1","volume":"3","author":"J Ruiu","year":"2015","unstructured":"Ruiu, J., Caumon, G. & Viseur, S. Semiautomatic interpretation of 3d sedimentological structures on geologic images: An object-based approach. Interpretation 3, SX63\u2013SX74 (2015).","journal-title":"Interpretation"},{"key":"58908_CR58","unstructured":"Hall, J., Ponzi, M., Gonfalini, M. & Maletti, G. Automatic extraction and characterisation of geological features and textures front borehole images and core photographs. In SPWLA Annual Logging Symposium, SPWLA\u20131996 (SPWLA, 1996)."},{"key":"58908_CR59","doi-asserted-by":"publisher","first-page":"1031","DOI":"10.1016\/j.conbuildmat.2018.08.011","volume":"186","author":"S Dorafshan","year":"2018","unstructured":"Dorafshan, S., Thomas, R. J. & Maguire, M. Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Constr. Build. Mater. 186, 1031\u20131045 (2018).","journal-title":"Constr. Build. Mater."},{"key":"58908_CR60","unstructured":"Argialas, D. & Mavrantza, O. Comparison of edge detection and hough transform techniques for the extraction of geologic features. nt. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 34 (2004)."},{"key":"58908_CR61","first-page":"1","volume":"404","author":"AK Turner","year":"2006","unstructured":"Turner, A. K., Kemeny, J., Slob, S. & Hack, R. Evaluation and management of unstable rock slopes by 3-d laser scanning. IAEG 404, 1\u201311 (2006).","journal-title":"IAEG"},{"key":"58908_CR62","doi-asserted-by":"publisher","first-page":"1584","DOI":"10.1016\/j.cageo.2011.03.007","volume":"37","author":"D Garc\u00eda-Sell\u00e9s","year":"2011","unstructured":"Garc\u00eda-Sell\u00e9s, D. et al. Supervised identification and reconstruction of near-planar geological surfaces from terrestrial laser scanning. Comput. Geosci. 37, 1584\u20131594 (2011).","journal-title":"Comput. Geosci."},{"key":"58908_CR63","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.ijrmms.2018.06.023","volume":"109","author":"T Drews","year":"2018","unstructured":"Drews, T. et al. Validation of fracture data recognition in rock masses by automated plane detection in 3d point clouds. Int. J. Rock Mech. Min. Sci. 109, 19\u201331 (2018).","journal-title":"Int. J. Rock Mech. Min. Sci."},{"key":"58908_CR64","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.cageo.2012.07.026","volume":"51","author":"G Umili","year":"2013","unstructured":"Umili, G., Ferrero, A. & Einstein, H. A new method for automatic discontinuity traces sampling on rock mass 3d model. Comput. Geosci. 51, 182\u2013192 (2013).","journal-title":"Comput. Geosci."},{"key":"58908_CR65","doi-asserted-by":"crossref","unstructured":"Lee, T.\u00a0H. & Moon, W.\u00a0M. Lineament extraction from landsat tm, jers-1 sar, and dem for geological applications. In IEEE International Geoscience and Remote Sensing Symposium, vol.\u00a06, 3276\u20133278 (IEEE, 2002).","DOI":"10.1109\/IGARSS.2002.1027154"},{"key":"58908_CR66","first-page":"67","volume":"13","author":"UC Nugroho","year":"2016","unstructured":"Nugroho, U. C. & Tjahjaningsih, A. Lineament density information extraction using dem srtm data to predict the mineral potential zones. Int. J. Remote Sens, Earth Sci. 13, 67\u201374 (2016).","journal-title":"Int. J. Remote Sens, Earth Sci."},{"key":"58908_CR67","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.cageo.2016.03.015","volume":"92","author":"J \u0160ilhav\u1ef3","year":"2016","unstructured":"\u0160ilhav\u1ef3, J., Min\u00e1r, J., Mentl\u00edk, P. & Sl\u00e1dek, J. A new artefacts resistant method for automatic lineament extraction using multi-hillshade hierarchic clustering (mhhc). Comput. Geosci. 92, 9\u201320 (2016).","journal-title":"Comput. Geosci."},{"key":"58908_CR68","doi-asserted-by":"publisher","first-page":"23109","DOI":"10.52202\/068431-1679","volume":"35","author":"M Heo","year":"2022","unstructured":"Heo, M., Hwang, S., Oh, S. W., Lee, J.-Y. & Kim, S. J. Vita: Video instance segmentation via object token association. Adv. Neural Inf. Process. Syst. 35, 23109\u201323120 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"58908_CR69","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103994","volume":"133","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., Yin, X. & Yan, Z. Rapid data annotation for sand-like granular instance segmentation using mask-rcnn. Autom. Constr. 133, 103994 (2022).","journal-title":"Autom. Constr."},{"key":"58908_CR70","doi-asserted-by":"publisher","DOI":"10.1016\/j.earscirev.2024.104888","volume":"257","author":"DJ Sanderson","year":"2024","unstructured":"Sanderson, D. J., Peacock, D. C. & Nixon, C. W. Fracture sets and sequencing. Earth-Sci. Rev. 257, 104888 (2024).","journal-title":"Earth-Sci. Rev."},{"key":"58908_CR71","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1016\/j.jrmge.2023.07.010","volume":"16","author":"M Zhao","year":"2024","unstructured":"Zhao, M. et al. A method to interpret fracture aperture of rock slope using adaptive shape and unmanned aerial vehicle multi-angle nap-of-the-object photogrammetry. J. Rock Mech. Geotech. Eng. 16, 924\u2013941 (2024).","journal-title":"J. Rock Mech. Geotech. Eng."},{"key":"58908_CR72","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1016\/j.tecto.2013.07.024","volume":"608","author":"T Wiatr","year":"2013","unstructured":"Wiatr, T., Reicherter, K., Papanikolaou, I., Fern\u00e1ndez-Steeger, T. & Mason, J. Slip vector analysis with high resolution t-lidar scanning. Tectonophysics 608, 947\u2013957 (2013).","journal-title":"Tectonophysics"},{"key":"58908_CR73","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1130\/B35661.1","volume":"133","author":"A Corradetti","year":"2021","unstructured":"Corradetti, A., Zambrano, M., Tavani, S., Tondi, E. & Seers, T. D. The impact of weathering upon the roughness characteristics of a splay of the active fault system responsible for the massive 2016 seismic sequence of the central apennines, italy. GSA Bulletin 133, 885\u2013896 (2021).","journal-title":"GSA Bulletin"},{"key":"58908_CR74","doi-asserted-by":"publisher","DOI":"10.1016\/j.enggeo.2019.105332","volume":"264","author":"A Buyer","year":"2020","unstructured":"Buyer, A., Aichinger, S. & Schubert, W. Applying photogrammetry and semi-automated joint mapping for rock mass characterization. Eng. Geol. 264, 105332 (2020).","journal-title":"Eng. Geol."},{"key":"58908_CR75","first-page":"1","volume":"61","author":"R Zhang","year":"2023","unstructured":"Zhang, R., Zhang, G., Yin, J., Jia, X. & Mian, A. Mesh-based dgcnn: Semantic segmentation of textured 3-d urban scenes. IEEE Trans. Geosci. Remote Sens. 61, 1\u201312 (2023).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"58908_CR76","doi-asserted-by":"publisher","first-page":"5324","DOI":"10.3390\/rs15225324","volume":"15","author":"G Zhang","year":"2023","unstructured":"Zhang, G. & Zhang, R. Meshnet-sp: A semantic urban 3d mesh segmentation network with sparse prior. Remote Sens. 15, 5324 (2023).","journal-title":"Remote Sens."},{"key":"58908_CR77","doi-asserted-by":"publisher","first-page":"4670","DOI":"10.1109\/JSTARS.2023.3276977","volume":"16","author":"Y Yang","year":"2023","unstructured":"Yang, Y., Tang, R., Xia, M. & Zhang, C. A texture integrated deep neural network for semantic segmentation of urban meshes. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 16, 4670\u20134684 (2023).","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"58908_CR78","doi-asserted-by":"crossref","unstructured":"Riemenschneider, H., B\u00f3dis-Szomor\u00fa, A., Weissenberg, J. & Van Gool, L. Learning where to classify in multi-view semantic segmentation. In European Conference on Computer Vision, 516\u2013532 (Springer, 2014).","DOI":"10.1007\/978-3-319-10602-1_34"},{"key":"58908_CR79","volume":"121","author":"JM Adam","year":"2023","unstructured":"Adam, J. M. et al. Deep learning-based semantic segmentation of urban-scale 3d meshes in remote sensing: A survey. Int. J. Appl. Earth Obs. Geoinf. 121, 103365 (2023).","journal-title":"Int. J. Appl. Earth Obs. Geoinf."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58908-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58908-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58908-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T12:02:17Z","timestamp":1792584137000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58908-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":79,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["58908"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-58908-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"assertion":[{"value":"28 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"33124"}}