{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T18:09:12Z","timestamp":1789754952270,"version":"4.0.1"},"reference-count":72,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["PEPR SOLU-BIOD - Living Lab Ponant"],"award-info":[{"award-number":["PEPR SOLU-BIOD - Living Lab Ponant"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["PEPR SOLU-BIOD - Living Lab Ponant"],"award-info":[{"award-number":["PEPR SOLU-BIOD - Living Lab Ponant"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"\n In operational coastal monitoring of spatially fragmented intertidal habitats, labelled datasets are structurally constrained by the limited spatial extent of target species, yet the relative influence of training strategy versus architecture on segmentation performance remains poorly characterised. We present a systematic ablation study disentangling these contributions for automated detection of the invasive cordgrass\n Spartina<\/jats:italic>\n from very high resolution aerial imagery. Three segmentation architectures, U-Net, DeepLabV3\u2009+\u2009, and SegFormer-B2, were trained under twelve configurations spanning four training-strategy axes, each evaluated by five-fold cross-validation on 810 patches derived from aerial colour-infrared imagery and elevation data, yielding 180 training runs. Training strategy dominates architectural design: the gap between the best and worst strategy (\n \n \n \n \n \n ~<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n 10\u2009pts of overlap accuracy) exceeds the inter-architecture spread (<1\u2009pt) by an order of magnitude, and encoder freezing and the Tversky loss were systematically detrimental across all three architectures. The selected operational configuration achieves an F1-score of\n \n \n \n \n \n 86.8<\/mml:mn>\n \u00b1<\/mml:mo>\n 1.3<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n %, enabling wall-to-wall surface estimation across the Bay of Brest (44.3\u2009ha; uncertainty\n \n \n \n \n \n \u00b1<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n 10\u201315%). A channel ablation shows spectral information dominates: removing elevation costs only 1.7\u2009pts, whereas elevation alone still reaches\n \n \n \n \n \n 54.2<\/mml:mn>\n \u00b1<\/mml:mo>\n 3.1<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n %; this likely reflects limitations of fusing a heterogeneous modality into a photographically pre-trained encoder rather than the ecological irrelevance of elevation. A leave-one-site-out validation, withholding each labelled site in turn, yields a lower and more variable estimate (F1\n \n \n \n \n \n 77.8<\/mml:mn>\n \u00b1<\/mml:mo>\n 6.9<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n %, ranging 50.5\u201379.5% across sites), indicating the five-fold estimate is optimistic for genuinely new sites. On an independent site never used in training, predictions agree with manual photo-interpretation of the same imagery to within 2.4%, though independent field validation is still needed. Derived from routinely updated national imagery, this pipeline offers coastal managers a reproducible, annually updatable monitoring tool, best suited to sites resembling those already mapped.\n <\/jats:p>","DOI":"10.1371\/journal.pone.0358464","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T17:31:06Z","timestamp":1789752666000},"page":"e0358464","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Training strategy over architecture: A systematic ablation study for Spartina detection from aerial imagery with small geospatial datasets"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2554-6494","authenticated-orcid":true,"given":"Adrien","family":"Le Guillou","sequence":"first","affiliation":[{"name":"Univ Brest, Univ Nantes, Univ Rennes, CNRS, LETG UMR, IUEM","place":["Plouzan\u00e9, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manon","family":"Brehier","sequence":"additional","affiliation":[{"name":"Univ Brest, Univ Nantes, Univ Rennes, CNRS, LETG UMR, IUEM","place":["Plouzan\u00e9, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00e9r\u00f4me","family":"Ammann","sequence":"additional","affiliation":[{"name":"Geo-Ocean, UMR CNRS-IFREMER-UBO-UBS, IUEM, University of Brest","place":["Plouzan\u00e9, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Dauvergne","sequence":"additional","affiliation":[{"name":"Laboratoire G\u00e9oarchitecture: Territoires, Urbanisation, Biodiversit\u00e9, Environnement, Universit\u00e9 de Brest","place":["Brest, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7975-2149","authenticated-orcid":true,"given":"Pierre","family":"St\u00e9phan","sequence":"additional","affiliation":[{"name":"Univ Brest, Univ Nantes, Univ Rennes, CNRS, LETG UMR, IUEM","place":["Plouzan\u00e9, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"pone.0358464.ref001","first-page":"331","article-title":"The geomorphological and botanical changes in Kernic Bay (Brittany, France): influence on coastal management","author":"MC Guenegou","year":"1991","journal-title":"Journal of Coastal Research"},{"key":"pone.0358464.ref002","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/s00606-002-0251-8","article-title":"Genetic evidence for hybridization between the native Spartina maritima and the introduced Spartina alterniflora (Poaceae) in South-West France: Spartina \u00d7 neyrautii re-examined","volume":"237","author":"A Baumel","year":"2003","journal-title":"Plant Systematics and Evolution"},{"issue":"8","key":"pone.0358464.ref003","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1038\/nclimate3062","article-title":"Erratum: Corrigendum: The role of coastal plant communities for climate change mitigation and adaptation","volume":"6","author":"CM Duarte","year":"2016","journal-title":"Nature Clim Change"},{"issue":"10","key":"pone.0358464.ref004","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1890\/110004","article-title":"A blueprint for blue carbon: toward an improved understanding of the role of vegetated coastal habitats in sequestering CO 2","volume":"9","author":"E Mcleod","year":"2011","journal-title":"Frontiers in Ecol & Environ"},{"key":"pone.0358464.ref005","doi-asserted-by":"crossref","first-page":"104623","DOI":"10.1016\/j.apor.2025.104623","article-title":"Tall salt marshes play a crucial role in the long-term geomorphic evolution of the Jiuduansha wetland, Yangtze estuary, China","volume":"159","author":"H Ma","year":"2025","journal-title":"Applied Ocean Research"},{"key":"pone.0358464.ref006","first-page":"94","article-title":"SM21: Suaeda vera-Limonium binervosum salt-marsh community","volume-title":"British Plant Communities","author":"CD Pigott","year":"2000"},{"issue":"1","key":"pone.0358464.ref007","doi-asserted-by":"crossref","first-page":"95","DOI":"10.2307\/2403612","article-title":"Rates of Change in the Numbers of Dunlin, Calidris alpina, Wintering in British Estuaries in Relation to the Spread of Spartina anglica","volume":"25","author":"JD Goss-Custard","year":"1988","journal-title":"The Journal of Applied Ecology"},{"key":"pone.0358464.ref008","doi-asserted-by":"crossref","first-page":"127652","DOI":"10.1016\/j.jenvman.2025.127652","article-title":"Rapid change in structural stability of tidal flats in response to large-scale eradication of Spartina alterniflora: evidence from dense time-series PlanetScope satellite imagery","volume":"395","author":"J Yang","year":"2025","journal-title":"J Environ Manage"},{"key":"pone.0358464.ref009","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.ecoleng.2011.12.014","article-title":"Distribution of Spartina spp. along China\u2019s coast","volume":"40","author":"P Zuo","year":"2012","journal-title":"Ecological Engineering"},{"key":"pone.0358464.ref010","doi-asserted-by":"crossref","first-page":"118483","DOI":"10.1016\/j.marpolbul.2025.118483","article-title":"Research hotspots and trends in Spartina alterniflora studies (1970-2023): A bibliometric analysis","volume":"221","author":"D Yan","year":"2025","journal-title":"Mar Pollut Bull"},{"issue":"11","key":"pone.0358464.ref011","doi-asserted-by":"crossref","first-page":"6601","DOI":"10.5194\/essd-17-6601-2025","article-title":"National-scale sub-meter mapping of Spartina alterniflora in mainland China 2020","volume":"17","author":"B Zhou","year":"2025","journal-title":"Earth Syst Sci Data"},{"key":"pone.0358464.ref012","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/978-3-031-54321-0_9","article-title":"Semantic Segmentation of Remote Sensing Images: Definition, Methods, Datasets and Applications","volume-title":"ICT Innovations 2023. Learning: Humans, Theory, Machines, and Data","author":"V Spasev","year":"2024"},{"key":"pone.0358464.ref013","doi-asserted-by":"crossref","first-page":"100046","DOI":"10.1016\/j.ophoto.2023.100046","article-title":"Automatic labelling for semantic segmentation of VHR satellite images: Application of airborne laser scanner data and object-based image analysis","volume":"9","author":"K Karila","year":"2023","journal-title":"ISPRS Open Journal of Photogrammetry and Remote Sensing"},{"issue":"1","key":"pone.0358464.ref014","article-title":"A review of remote sensing image segmentation by deep learning methods","volume":"17","author":"J Li","year":"2024","journal-title":"International Journal of Digital Earth"},{"key":"pone.0358464.ref015","doi-asserted-by":"crossref","first-page":"104904","DOI":"10.1016\/j.jag.2025.104904","article-title":"A layer-wise classification framework for coastal wetlands mapping using SAR time series and locally optimal spatiotemporal features","volume":"144","author":"Z Li","year":"2025","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"pone.0358464.ref016","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015"},{"key":"pone.0358464.ref017","first-page":"833","article-title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","volume-title":"Lecture Notes in Computer Science","author":"L-C Chen","year":"2018"},{"key":"pone.0358464.ref018","unstructured":"Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. In: Advances in Neural Information Processing Systems, 2021. 12077\u201390."},{"key":"pone.0358464.ref019","doi-asserted-by":"crossref","unstructured":"Osco LP, Wu Q, de Lemos EL, Gon\u00e7alves WN, Ramos APM, Li J. The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot. 2023. https:\/\/doi.org\/arXiv:2306.16623","DOI":"10.1016\/j.jag.2023.103540"},{"key":"pone.0358464.ref020","doi-asserted-by":"crossref","unstructured":"Szwarcman D, Roy S, Fraccaro P, \u00deorsteinn El\u00ed G, Blumenstiel B, Ghosal R, et al. Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications. 2025. https:\/\/doi.org\/arXiv:2412.02732","DOI":"10.1109\/TGRS.2025.3642610"},{"key":"pone.0358464.ref021","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2020.12.010","article-title":"Review on Convolutional Neural Networks (CNN) in vegetation remote sensing","volume":"173","author":"T Kattenborn","year":"2021","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0358464.ref022","doi-asserted-by":"crossref","first-page":"114417","DOI":"10.1016\/j.eswa.2020.114417","article-title":"A review of deep learning methods for semantic segmentation of remote sensing imagery","volume":"169","author":"X Yuan","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"pone.0358464.ref023","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.isprsjprs.2021.01.020","article-title":"Remote Sensing Image Segmentation Advances: A Meta-Analysis","volume":"173","author":"I Kotaridis","year":"2021","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0358464.ref024","doi-asserted-by":"crossref","first-page":"102035","DOI":"10.1016\/j.media.2021.102035","article-title":"Loss odyssey in medical image segmentation","volume":"71","author":"J Ma","year":"2021","journal-title":"Med Image Anal"},{"key":"pone.0358464.ref025","volume-title":"Document d\u2019objectifs Natura 2000 \u2013 Rade de Brest, estuaire de l\u2019Aulne","author":"Parc Naturel R\u00e9gional d\u2019Armorique","year":"2014"},{"issue":"05","key":"pone.0358464.ref026","doi-asserted-by":"crossref","first-page":"227","DOI":"10.4236\/oje.2015.55019","article-title":"Marine Species Introduced on the French Channel-Atlantic Coasts: A Review of Main Biological Invasions and Impacts","volume":"05","author":"V Stiger-Pouvreau","year":"2015","journal-title":"OJE"},{"key":"pone.0358464.ref027","first-page":"101","article-title":"Vingt ans de suivi et de conservation du Limonium humile Miller en rade de Brest","volume":"23","author":"E Qu\u00e9r\u00e9","year":"2010","journal-title":"ERICA"},{"key":"pone.0358464.ref028","unstructured":"St\u00e9phan P, Fichaut B, Suanez S. Les sillons de la rade de Brest et les marais maritimes associ\u00e9s. 2012."},{"issue":"4","key":"pone.0358464.ref029","first-page":"27","article-title":"\u00c9volution de la v\u00e9g\u00e9tation des pr\u00e9s-sal\u00e9s en rade de Brest de 1952 \u00e0 2004","volume":"41","author":"L Sparfel","year":"2005","journal-title":"Photo-Interpr\u00e9tation \u2013 European Journal of Applied Remote Sensing"},{"key":"pone.0358464.ref030","volume-title":"Cartographie de la spartine en rade de Brest: campagne 2014","author":"V Hourd\u00e9","year":"2014"},{"key":"pone.0358464.ref031","volume-title":"Actualisation diachronique de la colonisation par Spartina alterniflora en rade de Brest","author":"P Le Meur","year":"2024"},{"key":"pone.0358464.ref032","volume-title":"Cartographie des habitats de l\u2019estuaire de l\u2019Elorn","author":"C Bougault","year":"2004"},{"key":"pone.0358464.ref033","volume-title":"Suivi de la v\u00e9g\u00e9tation des marais de l\u2019Elorn","author":"C Bougault","year":"2005"},{"key":"pone.0358464.ref034","doi-asserted-by":"crossref","first-page":"103303","DOI":"10.1016\/j.ecoinf.2025.103303","article-title":"Monitoring the dynamics of coastal wetlands ecosystems in Brittany (France) using LANDSAT time series and machine learning","volume":"90","author":"A Le Guillou","year":"2025","journal-title":"Ecological Informatics"},{"key":"pone.0358464.ref035","volume-title":"LiDAR HD \u2013 Descriptif de contenu","author":"Institut National de l\u2019Information G\u00e9ographique et Foresti\u00e8re","year":"2023"},{"key":"pone.0358464.ref036","doi-asserted-by":"crossref","first-page":"100018","DOI":"10.1016\/j.ophoto.2022.100018","article-title":"Spatially autocorrelated training and validation samples inflate performance assessment of convolutional neural networks","volume":"5","author":"T Kattenborn","year":"2022","journal-title":"ISPRS Open Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0358464.ref037","doi-asserted-by":"crossref","first-page":"109885","DOI":"10.1016\/j.petrol.2021.109885","article-title":"Fair train-test split in machine learning: Mitigating spatial autocorrelation for improved prediction accuracy","volume":"209","author":"JJ Salazar","year":"2022","journal-title":"Journal of Petroleum Science and Engineering"},{"key":"pone.0358464.ref038","doi-asserted-by":"crossref","first-page":"102741","DOI":"10.1016\/j.softx.2026.102741","article-title":"SemanticSeg4EO: An open-source unified framework and QGIS plugin for semantic segmentation in Earth Observation","volume":"34","author":"A Le Guillou","year":"2026","journal-title":"SoftwareX"},{"key":"pone.0358464.ref039","doi-asserted-by":"crossref","first-page":"105069","DOI":"10.1016\/j.jag.2025.105069","article-title":"Modular and adaptive implementation of Semantic Segmentation Models for Satellite Images and Open Source tools suitable for complex geographical contexts","volume":"146","author":"A Le Guillou","year":"2026","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"pone.0358464.ref040","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 770\u20138. https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"pone.0358464.ref041","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing","volume":"57","author":"Y Benjamini","year":"1995","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"pone.0358464.ref042","volume-title":"Mod\u00e9lisation de la pr\u00e9sence de Spartina alterniflora \u2014 Rade de Brest","author":"A Le Guillou","year":"2024"},{"key":"pone.0358464.ref043","doi-asserted-by":"crossref","unstructured":"Jadon S. A survey of loss functions for semantic segmentation. In: 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), 2020. 1\u20137. https:\/\/doi.org\/10.1109\/cibcb48159.2020.9277638","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"key":"pone.0358464.ref044","doi-asserted-by":"crossref","first-page":"103569","DOI":"10.1016\/j.jag.2023.103569","article-title":"Ten deep learning techniques to address small data problems with remote sensing","volume":"125","author":"A Safonova","year":"2023","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"pone.0358464.ref045","doi-asserted-by":"crossref","unstructured":"Chiu MT, Xu X, Wei Y, Huang Z, Schwing AG, Brunner R, et al. Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 2825\u201335. https:\/\/doi.org\/10.1109\/cvpr42600.2020.00290","DOI":"10.1109\/CVPR42600.2020.00290"},{"issue":"20","key":"pone.0358464.ref046","doi-asserted-by":"crossref","first-page":"5003","DOI":"10.3390\/rs15205003","article-title":"Mapping Coastal Wetlands and Their Dynamics in the Yellow River Delta over Last Three Decades: Based on a Spectral Endmember Space","volume":"15","author":"K Tan","year":"2023","journal-title":"Remote Sensing"},{"key":"pone.0358464.ref047","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint. 2020. https:\/\/doi.org\/10.48550\/arXiv.2010.11929"},{"key":"pone.0358464.ref048","unstructured":"Raghu M, Unterthiner T, Kornblith S, Zhang C, Dosovitskiy A. In: Advances in Neural Information Processing Systems, 2021. 12116\u201328. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/652cf38361a209088302ba2b8b7f51e0-Paper.pdf"},{"key":"pone.0358464.ref049","doi-asserted-by":"crossref","first-page":"103333","DOI":"10.1016\/j.jag.2023.103333","article-title":"WetMapFormer: A unified deep CNN and vision transformer for complex wetland mapping","volume":"120","author":"A Jamali","year":"2023","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"pone.0358464.ref050","unstructured":"Neumann M, Pinto AS, Zhai X, Houlsby N. In-domain representation learning for remote sensing. 2019. https:\/\/doi.org\/arXiv:1911.06721"},{"key":"pone.0358464.ref051","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.isprsjprs.2019.02.006","article-title":"Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks","volume":"150","author":"M Wurm","year":"2019","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0358464.ref052","doi-asserted-by":"crossref","unstructured":"Sharif Razavian A, Azizpour H, Sullivan J, Carlsson S. CNN features off-the-shelf: An astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2014.","DOI":"10.1109\/CVPRW.2014.131"},{"key":"pone.0358464.ref053","unstructured":"Steiner A, Kolesnikov A, Zhai X, Wightman R, Uszkoreit J, Beyer L. How to train your ViT? Data, augmentation, and regularization in vision transformers. In: 2022. https:\/\/doi.org\/arXiv:2106.10270"},{"key":"pone.0358464.ref054","unstructured":"Chen X, Hsieh CJ, Gong B. When vision transformers outperform ResNets without pre-training or strong data augmentations. In: 2022. https:\/\/doi.org\/arXiv:2106.01548"},{"key":"pone.0358464.ref055","first-page":"379","article-title":"Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks","volume-title":"Lecture Notes in Computer Science","author":"SSM Salehi","year":"2017"},{"key":"pone.0358464.ref056","doi-asserted-by":"crossref","unstructured":"Abraham N, Khan NM. A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 2019. 683\u20137. https:\/\/doi.org\/10.1109\/isbi.2019.8759329","DOI":"10.1109\/ISBI.2019.8759329"},{"key":"pone.0358464.ref057","doi-asserted-by":"crossref","first-page":"102026","DOI":"10.1016\/j.compmedimag.2021.102026","article-title":"Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation","volume":"95","author":"M Yeung","year":"2022","journal-title":"Comput Med Imaging Graph"},{"key":"pone.0358464.ref058","unstructured":"MMSegmentation Contributors. MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark. 2020. https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"pone.0358464.ref059","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/B978-0-32-385787-1.00017-8","article-title":"Semantic scene segmentation for robotics","volume-title":"Deep Learning for Robot Perception and Cognition","author":"JV Hurtado","year":"2022"},{"key":"pone.0358464.ref060","doi-asserted-by":"crossref","unstructured":"El Madawi K, Rashed H, El Sallab A, Nasr O, Kamel H, Yogamani S. RGB and LiDAR fusion based 3D Semantic Segmentation for Autonomous Driving. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 2019. 7\u201312. https:\/\/doi.org\/10.1109\/itsc.2019.8917447","DOI":"10.1109\/ITSC.2019.8917447"},{"key":"pone.0358464.ref061","unstructured":"Xiong Z, Chen S, Wang Y, Mou L, Zhu XX. GAMUS: A geometry-aware multi-modal semantic segmentation benchmark for remote sensing data. 2023. https:\/\/doi.org\/10.48550\/arXiv.2305.14914"},{"issue":"8","key":"pone.0358464.ref062","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1111\/ecog.02881","article-title":"Cross\u2010validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure","volume":"40","author":"DR Roberts","year":"2017","journal-title":"Ecography"},{"issue":"1","key":"pone.0358464.ref063","doi-asserted-by":"crossref","first-page":"4540","DOI":"10.1038\/s41467-020-18321-y","article-title":"Spatial validation reveals poor predictive performance of large-scale ecological mapping models","volume":"11","author":"P Ploton","year":"2020","journal-title":"Nat Commun"},{"key":"pone.0358464.ref064","doi-asserted-by":"crossref","DOI":"10.3389\/frsen.2025.1531097","article-title":"Choosing blocks for spatial cross-validation: lessons from a marine remote sensing case study","volume":"6","author":"A Stock","year":"2025","journal-title":"Front Remote Sens"},{"issue":"11","key":"pone.0358464.ref065","doi-asserted-by":"crossref","first-page":"6601","DOI":"10.5194\/essd-17-6601-2025","article-title":"National-scale sub-meter mapping of Spartina alterniflora in mainland China 2020","volume":"17","author":"B Zhou","year":"2025","journal-title":"Earth Syst Sci Data"},{"issue":"1","key":"pone.0358464.ref066","article-title":"Lessons from the invasion of Spartina alterniflora in coastal China","volume":"104","author":"M Nie","year":"2023","journal-title":"Ecology"},{"key":"pone.0358464.ref067","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3168697","article-title":"Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images","volume":"60","author":"L Ding","year":"2022","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0358464.ref068","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.isprsjprs.2022.06.008","article-title":"UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery","volume":"190","author":"L Wang","year":"2022","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0358464.ref069","article-title":"Practical Bayesian Optimization of Machine Learning Algorithms","volume-title":"Advances in Neural Information Processing Systems","author":"J Snoek","year":"2012"},{"key":"pone.0358464.ref070","doi-asserted-by":"crossref","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 2023. 4015\u201326. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00371","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"pone.0358464.ref071","doi-asserted-by":"crossref","unstructured":"Jakubik J, Roy S, Phillips CE, Fraccaro P, Godwin D, Zadrozny B. Foundation Models for Generalist Geospatial Artificial Intelligence. In: 2023. https:\/\/doi.org\/arXiv:231018660","DOI":"10.2139\/ssrn.4804009"},{"issue":"1","key":"pone.0358464.ref072","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/S0034-4257(01)00295-4","article-title":"Status of land cover classification accuracy assessment","volume":"80","author":"GM Foody","year":"2002","journal-title":"Remote Sensing of Environment"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T17:31:26Z","timestamp":1789752686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358464"}},"subtitle":[],"editor":[{"given":"Judi Hewitt","family":"Hewitt","sequence":"first","affiliation":[{"name":"The University of Auckland - City Campus: University of Auckland","place":["NEW ZEALAND"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":72,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0358464","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]}}}