{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T06:24:06Z","timestamp":1787293446873,"version":"build-2736575974"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>Cracks in the mattic epipedon of alpine meadows are a key morphological indicator of ecosystem degradation. However, the accurate extraction of these minute and irregular crack features remains a significant challenge in complex natural environments characterized by vegetation cover, drastic fluctuations in light intensity, and soil texture interference. To address these challenges, a novel deep learning network, YOLO-AMSC, is proposed for the high-precision segmentation and morphological quantification of cracks in the mattic epipedon of alpine meadows under complex field environments. A Spatial to Depth Attention Fusion (SDAF-Block) module is proposed to preserve fine-grained spatial details of minute cracks without information loss and to reconstruct their broken topological continuity. Simultaneously, a Mixed Local Channel Attention (MLCA) mechanism is introduced to adaptively enhance crack textures while suppressing background noise. Furthermore, a hierarchical focused loss function, termed HFP-IoU (Hierarchical Focal-Penalty IoU), is designed to impose strict geometric constraints on the elongated crack boundaries via a non-monotonic focusing mechanism. The experimental results demonstrate that YOLO-AMSC achieves superior segmentation performance, improving mAP50 by 4.27%, 2.96%, 2.43%, 4.58%, 8.86%, 12.51%, 22.03%, 55.77%, and 52.19% compared with YOLOv5n-seg, YOLOv10n-seg, YOLO-hyper-seg, YOLOv12n-seg, SOLOv2, SparseInst, DeepCrack, CrackFormer-II, and CrackSegDiff, respectively. Using the high-fidelity segmentation masks from this model and a skeleton-based geometric constraint method for crack width estimation, the relative error relative to field measurements is less than 10%. Employing a system dynamics framework, this study quantitatively determines the topological width thresholds of 0.6 cm and 3.1 cm, which signify a sudden increase in connectivity and indicate an accelerated degradation process of alpine meadows. This method directly links pixel-level image analysis with regional early warning systems, delivering a cost-effective, non-destructive digital framework for dynamic ecological monitoring.<\/jats:p>","DOI":"10.3389\/fpls.2026.1895244","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T05:35:14Z","timestamp":1787290514000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on surface crack segmentation and quantitative degradation assessment in alpine meadows based on UAV imagery and the YOLO-AMSC model"],"prefix":"10.3389","volume":"17","author":[{"given":"Lihui","family":"Ma","sequence":"first","affiliation":[{"name":"College of Geological Engineering, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haili","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Geological Engineering, Qinghai University","place":["Xining, China"]},{"name":"Laboratory of Cenozoic Resources and Environment on the Northern Margin of the Qinghai-Tibet Plateau","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benfeng","family":"Li","sequence":"additional","affiliation":[{"name":"Academy of Animal and Veterinary Sciences, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuechen","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Civil Engineering and Water Resources, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengkai","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Geological Engineering, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqi","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Geological Engineering, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guorong","family":"Li","sequence":"additional","affiliation":[{"name":"College of Geological Engineering, Qinghai University","place":["Xining, China"]},{"name":"Laboratory of Cenozoic Resources and Environment on the Northern Margin of the Qinghai-Tibet Plateau","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabin","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Geological Engineering, Qinghai University","place":["Xining, China"]},{"name":"Laboratory of Cenozoic Resources and Environment on the Northern Margin of the Qinghai-Tibet Plateau","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/s11554-025-01843-3","article-title":"Efficient crack detection algorithm for concrete bridges based on improved YOLOv8n","volume":"23","author":"Bai","year":"2026","journal-title":"J. Real-Time Image Process."},{"key":"B2","doi-asserted-by":"publisher","first-page":"82","DOI":"10.3167\/np.2013.170207","article-title":"The roles of overgrazing, climate change and policy as drivers of degradation of China's grasslands","volume":"17","author":"Cao","year":"2013","journal-title":"Nomadic Peoples"},{"key":"B3","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.compag.2018.01.013","article-title":"Pixel based bruise region extraction of apple using Vis-NIR hyperspectral imaging","volume":"146","author":"Che","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"B4","doi-asserted-by":"publisher","first-page":"5265","DOI":"10.1016\/j.eswa.2010.01.013","article-title":"A novel multi-threshold segmentation approach based on differential evolution optimization","volume":"37","author":"Cuevas","year":"2010","journal-title":"Expert Syst. Appl."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1080\/15481603.2023.2257980","article-title":"Consistency-guided lightweight network for semi-supervised binary change detection of buildings in remote sensing images","volume":"60","author":"Ding","year":"2023","journal-title":"GIScience Remote Sens."},{"key":"B6","doi-asserted-by":"publisher","first-page":"14169","DOI":"10.1109\/TITS.2025.3540909","article-title":"Enhancing road maintenance through cyber-physical integration: the LEE-YOLO model for drone-assisted pavement crack detection","volume":"26","author":"Du","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.tust.2024.105713","article-title":"Tunnel lining crack detection model based on improved YOLOv5","volume":"147","author":"Duan","year":"2024","journal-title":"Tunnelling Underground Space Technol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"5900","DOI":"10.1109\/JSTARS.2026.3658553","article-title":"Towards cross-regional land cover mapping using regional consistency and certainty-based active domain adaptation with limited annotations","volume":"19","author":"Guo","year":"2026","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102875","article-title":"Mask R-CNN based automated identification and extraction of oil well sites","volume":"112","author":"He","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.09562","article-title":"Rethinking intersection over union for small object detection in few-shot regime","author":"Le Jeune","year":"2023","journal-title":"arXiv preprint arXiv:2307.09562"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2026.105113","article-title":"DGL-RSIS: Decoupling global spatial context and local class semantics for training-free remote sensing image segmentation","volume":"146","author":"Li","year":"2026","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.still.2025.106665","article-title":"Soil microbial resource limitation and use efficiency shift with turf transplantation and polygonal cracking in alpine meadows of the Tibetan Plateau","volume":"253","author":"Li","year":"2025","journal-title":"Soil Tillage Res."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2024.131913","article-title":"Mechanically and accurately calculate river width in vegetation areas by coupling Sentinel-1 and -2 imageries within land-water-mixed pixels","volume":"643","author":"Li","year":"2024","journal-title":"J. Hydrol."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2026.111613","article-title":"Growth monitoring of rice based on UAV hyperspectral images and improved deep learning method: The QRCNN-BIGRU-MLLA network","volume":"246","author":"Li","year":"2026","journal-title":"Comput. Electron. Agric."},{"key":"B15","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.jmsy.2023.05.027","article-title":"Multilayer Grad-CAM: An effective tool towards explainable deep neural networks for intelligent fault diagnosis","volume":"69","author":"Li","year":"2023","journal-title":"J. Manuf. Syst."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1122788","article-title":"Hybrid improved capuchin search algorithm for plant image thresholding","volume":"14","author":"Li","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/app12041838","article-title":"Real-time UAV trash monitoring system","volume":"12","author":"Liao","year":"2022","journal-title":"Appl. Sci."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2025.104748","article-title":"MT-CYP-Net: Multi-task network for pixel-level crop yield prediction under very few samples","volume":"143","author":"Liu","year":"2025","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1177114","article-title":"Research on multi-cluster green persimmon detection method based on improved Faster RCNN","volume":"14","author":"Liu","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3390\/app132011118","article-title":"Rotating target detection method of concrete bridge crack based on YOLO v5","volume":"13","author":"Liu","year":"2023","journal-title":"Appl. Sci."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102937","article-title":"SCoralDet: Efficient real-time underwater soft coral detection with YOLO","volume":"85","author":"Lu","year":"2025","journal-title":"Ecol. Inf."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3390\/s24092710","article-title":"Enhanced lightweight YOLOX for small object wildfire detection in UAV imagery","volume":"24","author":"Luan","year":"2024","journal-title":"Sensors"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.861534","article-title":"Leaf and stem-based dew detection algorithm via multi-convolutional edge detection networks","volume":"13","author":"Lv","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B24","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1016\/j.scitotenv.2018.08.164","article-title":"The Kobresia pygmaea ecosystem of the Tibetan highlands\u2013origin, functioning and degradation of the world's largest pastoral alpine ecosystem: Kobresia pastures of Tibet","volume":"648","author":"Miehe","year":"2019","journal-title":"Sci. Total Environ."},{"key":"B25","article-title":"Distribution, occurrence mechanism and ecological effects of cracks in alpine grassland on the eastern Qinghai-Tibet Plateau (in Chinese)","author":"Niu","year":"2020"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1002\/ldr.3312","article-title":"Overgrazing leads to soil cracking that later triggers the severe degradation of alpine meadows on the Tibetan Plateau","volume":"30","author":"Niu","year":"2019","journal-title":"Land Degrad. Dev."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2025.103505","article-title":"A pixel-twinning approach for assessing additionality: a case study of human-induced regeneration projects","volume":"92","author":"Orton","year":"2025","journal-title":"Ecol. Inf."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.104946","article-title":"One-stage 3D profile-based pavement crack detection and quantification","volume":"153","author":"Pan","year":"2023","journal-title":"Autom. Constr."},{"key":"B29","unstructured":"Assessment of the Degradation Status of Alpine Kobresia Pygmaea Meadow (DB63\/T 1413-2015)\n          \n          \n          \n          2015"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2025.127071","article-title":"Structure-sensitive carbon emission mechanisms in urban morphology: Grad-CAM guided nonlinear modeling and attention-based sectoral diagnosis","volume":"402","author":"Ren","year":"2026","journal-title":"Appl. Energy"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2025.114734","article-title":"Advances in crack dataset development and deep learning-based detection models","volume":"116","author":"Song","year":"2025","journal-title":"J. Build. Eng."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3390\/infrastructures10050102","article-title":"Research on intelligent identification technology for bridge cracks","volume":"10","author":"Su","year":"2025","journal-title":"Infrastructures"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3390\/app15158610","article-title":"Segmentation of stone slab cracks based on an improved YOLOv8 algorithm","volume":"15","author":"Tian","year":"2025","journal-title":"Appl. Sci."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110308","article-title":"Enhancing green guava segmentation with texture consistency loss and reverse attention mechanism under complex background","volume":"235","author":"Wang","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2025.103142","article-title":"TDXAI: An MR interaction responsiveness enhancement method based on target detection and explainable artificial intelligence","volume":"90","author":"Wang","year":"2025","journal-title":"Displays"},{"key":"B36","doi-asserted-by":"publisher","first-page":"2835","DOI":"10.5194\/tc-14-2835-2020","article-title":"Soil respiration of alpine meadow is controlled by freeze\u2013thaw processes of active layer in the permafrost region of the Qinghai\u2013Tibet Plateau","volume":"14","author":"Wang","year":"2020","journal-title":"Cryosphere"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1290845","article-title":"Brandt\u2019s vole hole detection and counting method based on deep learning and unmanned aircraft system","volume":"15","author":"Wu","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B38","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/s40333-024-0100-5","article-title":"Characterization of alpine meadow surface crack and its correlation with root-soil properties","volume":"16","author":"Wu","year":"2024","journal-title":"J. Arid. Land"},{"key":"B39","doi-asserted-by":"publisher","first-page":"8821","DOI":"10.1002\/ldr.70699","article-title":"Synergistic degradation relationship between root\u2013soil properties and the evolution of mattic epipedon cracks in alpine meadows","volume":"37","author":"Wu","year":"2026","journal-title":"Land Degrad. Dev."},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127834","article-title":"Crack segmentation and quantification in concrete structures using a lightweight YOLO model based on pruning and knowledge distillation","volume":"283","author":"Xu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B41","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1002\/tee.20244","article-title":"Image\u2013based crack detection for real concrete surfaces","volume":"3","author":"Yamaguchi","year":"2008","journal-title":"IEEJ Trans. Electr. Electron. Eng."},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1724501","article-title":"Study on automatic detection of wheat spike grain number based on deep learning","volume":"17","author":"Zang","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B43","doi-asserted-by":"publisher","first-page":"3961","DOI":"10.1109\/JIOT.2024.3485765","article-title":"An interpretability optimization method for deep learning networks based on Grad-CAM","volume":"12","author":"Zhang","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"B44","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1007\/s40333-025-0100-0","article-title":"Mechanical properties of surface soil in alpine meadow and its relationship with soil cracking in Qinghai Province, China","volume":"17","author":"Zhang","year":"2025","journal-title":"J. Arid. Land"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113485","article-title":"Surveying coconut trees using high-resolution satellite imagery in remote atolls of the Pacific Ocean","volume":"287","author":"Zheng","year":"2023","journal-title":"Remote Sens. Environ."},{"key":"B46","doi-asserted-by":"publisher","first-page":"31","DOI":"10.3390\/grasses2010004","article-title":"Alpine grassland degradation and its restoration in the Qinghai\u2013Tibet Plateau","volume":"2","author":"Zhou","year":"2023","journal-title":"Grasses"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1779621","article-title":"RAM-UNet: an improved U-Net\u2013based semantic segmentation model for the main stem of mature soybean plants","volume":"17","author":"Zhu","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1701817","article-title":"GrapeUL-YOLO: bidirectional cross-scale fusion with elliptical anchors for robust grape detection in orchards","volume":"16","author":"Zhu","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2025.103188","article-title":"Identification of glass eel capture equipment in the Yangtze River estuary based on high-spatial-resolution imagery and an improved YOLOv8 model","volume":"89","author":"Zhu","year":"2025","journal-title":"Ecol. Inf."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1895244\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T05:35:15Z","timestamp":1787290515000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1895244\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":49,"alternative-id":["10.3389\/fpls.2026.1895244"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1895244","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]},"article-number":"1895244"}}