{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T04:06:53Z","timestamp":1775102813014,"version":"3.50.1"},"reference-count":57,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union\u2019s HE programme","award":["101091959"],"award-info":[{"award-number":["101091959"]}]},{"name":"European Union\u2019s HE programme","award":["UIDB\/50014\/2020"],"award-info":[{"award-number":["UIDB\/50014\/2020"]}]},{"name":"European Union\u2019s HE programme","award":["2021.08715.BD"],"award-info":[{"award-number":["2021.08715.BD"]}]},{"name":"FCT","award":["101091959"],"award-info":[{"award-number":["101091959"]}]},{"name":"FCT","award":["UIDB\/50014\/2020"],"award-info":[{"award-number":["UIDB\/50014\/2020"]}]},{"name":"FCT","award":["2021.08715.BD"],"award-info":[{"award-number":["2021.08715.BD"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMSE"],"abstract":"<jats:p>Climate change has led to the need to transition to clean technologies, which depend on an number of critical metals. These metals, such as nickel, lithium, and manganese, are essential for developing batteries. However, the scarcity of these elements and the risks of disruptions to their supply chain have increased interest in exploiting resources on the deep seabed, particularly polymetallic nodules. As the identification of these nodules must be efficient to minimize disturbance to the marine ecosystem, deep learning techniques have emerged as a potential solution. Traditional deep learning methods are based on the use of convolutional layers to extract features, while recent architectures, such as transformer-based architectures, use self-attention mechanisms to obtain global context. This paper evaluates the performance of representative models from both categories across three tasks: detection, object segmentation, and semantic segmentation. The initial results suggest that transformer-based methods perform better in most evaluation metrics, but at the cost of higher computational resources. Furthermore, recent versions of You Only Look Once (YOLO) have obtained competitive results in terms of mean average precision.<\/jats:p>","DOI":"10.3390\/jmse13020344","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T08:01:19Z","timestamp":1739433679000},"page":"344","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluation of Deep Learning Models for Polymetallic Nodule Detection and Segmentation in Seafloor Imagery"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6496-232X","authenticated-orcid":false,"given":"Gabriel","family":"Loureiro","sequence":"first","affiliation":[{"name":"INESCTEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5734-075X","authenticated-orcid":false,"given":"Andr\u00e9","family":"Dias","sequence":"additional","affiliation":[{"name":"INESCTEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"},{"name":"ISEP\u2014School of Engineering, Polytechnic Institute of Porto, Rua Dr. Ant\u00f3nio Bernardino de Almeida 431, 4200-072 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5844-5393","authenticated-orcid":false,"given":"Jos\u00e9","family":"Almeida","sequence":"additional","affiliation":[{"name":"INESCTEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"},{"name":"ISEP\u2014School of Engineering, Polytechnic Institute of Porto, Rua Dr. Ant\u00f3nio Bernardino de Almeida 431, 4200-072 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3195-5638","authenticated-orcid":false,"given":"Alfredo","family":"Martins","sequence":"additional","affiliation":[{"name":"INESCTEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"},{"name":"ISEP\u2014School of Engineering, Polytechnic Institute of Porto, Rua Dr. Ant\u00f3nio Bernardino de Almeida 431, 4200-072 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7166-3459","authenticated-orcid":false,"given":"Eduardo","family":"Silva","sequence":"additional","affiliation":[{"name":"INESCTEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"},{"name":"ISEP\u2014School of Engineering, Polytechnic Institute of Porto, Rua Dr. Ant\u00f3nio Bernardino de Almeida 431, 4200-072 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"42539","DOI":"10.1007\/s11356-022-19718-6","article-title":"A review of the global climate change impacts, adaptation, and sustainable mitigation measures","volume":"29","author":"Abbass","year":"2022","journal-title":"Environ. Sci. Pollut. Res."},{"key":"ref_2","unstructured":"Parmesan, C., Morecroft, M.D., and Trisurat, Y. (2022). Climate Change 2022: Impacts, Adaptation and Vulnerability, UNESCO. Research Report."},{"key":"ref_3","first-page":"2","article-title":"Paris agreement","volume":"Volume 4","author":"Agreement","year":"2015","journal-title":"Proceedings of the Report of the Conference of the Parties to the United Nations Framework Convention on Climate Change (21st Session, 2015: Paris)"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1093\/yiel\/yvab060","article-title":"14. United Nations Environment Programme (UNEP)","volume":"31","author":"Desai","year":"2020","journal-title":"Yearb. Int. Environ. Law"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Watari, T., Nansai, K., and Nakajima, K. (2020). Review of critical metal dynamics to 2050 for 48 elements. Resour. Conserv. Recycl., 155.","DOI":"10.1016\/j.resconrec.2019.104669"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1038\/s43017-020-0027-0","article-title":"Deep-ocean polymetallic nodules as a resource for critical materials","volume":"1","author":"Hein","year":"2020","journal-title":"Nat. Rev. Earth Environ."},{"key":"ref_7","first-page":"842","article-title":"A historical perspective on deep-sea mining for manganese nodules, 1965\u20132019","volume":"6","author":"Sparenberg","year":"2019","journal-title":"Extr. Ind. Soc."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Miller, K.A., Thompson, K.F., Johnston, P., and Santillo, D. (2018). An overview of seabed mining including the current state of development, environmental impacts, and knowledge gaps. Front. Mar. Sci., 4.","DOI":"10.3389\/fmars.2017.00418"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1016\/j.scitotenv.2018.01.221","article-title":"The last frontier: Coupling technological developments with scientific challenges to improve hazard assessment of deep-sea mining","volume":"627","author":"Santos","year":"2018","journal-title":"Sci. Total Environ."},{"key":"ref_10","unstructured":"Minar, M.R., and Naher, J. (2018). Recent advances in deep learning: An overview. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Silva, E., Viegas, D., Martins, A., Almeida, J., Almeida, C., Neves, B., Madureira, P., Wheeler, A.J., Salavasidis, G., and Phillips, A. (2023, January 5\u20138). TRIDENT\u2013Technology based impact assessment tool foR sustaInable, transparent Deep sEa miNing exploraTion and exploitation: A project overview. Proceedings of the OCEANS 2023-Limerick, Limerick, Ireland.","DOI":"10.1109\/OCEANSLimerick52467.2023.10244429"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"35479","DOI":"10.1109\/ACCESS.2023.3266093","article-title":"Object detection using deep learning, CNNs and vision transformers: A review","volume":"11","author":"Amjoud","year":"2023","journal-title":"IEEE Access"},{"key":"ref_13","first-page":"1649","article-title":"Review of Nodule Mineral Image Segmentation Algorithms for Deep-Sea Mineral Resource Assessment","volume":"73","author":"Song","year":"2022","journal-title":"Comput. Mater. Contin."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, X., Zhang, Z., and Deng, F. (2023). Deep learning in image segmentation for mineral production: A review. Comput. Geosci., 180.","DOI":"10.1016\/j.cageo.2023.105455"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Savaliya, J., Prabhakaran, K., Muthuvel, P., Meenakshi, S., Varshney, N., and Sankar, P. (2023, January 14\u201316). Underwater Resource Detection Using Image Processing. Proceedings of the 2023 International Conference on Next Generation Electronics (NEleX), Vellore, India.","DOI":"10.1109\/NEleX59773.2023.10421038"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Loureiro, G., Dias, A., Almeida, J., Martins, A., Hong, S., and Silva, E. (2024). A Survey of Seafloor Characterization and Mapping Techniques. Remote Sens., 16.","DOI":"10.3390\/rs16071163"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Quintana, J., Garcia, R., Neumann, L., Campos, R., Weiss, T., K\u00f6ser, K., Mohrmann, J., and Greinert, J. (2018, January 22\u201325). Towards automatic recognition of mining targets using an autonomous robot. Proceedings of the OCEANS 2018 MTS\/IEEE Charleston, Charleston, SC, USA.","DOI":"10.1109\/OCEANS.2018.8604491"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sartore, C., Campos, R., Quintana, J., Simetti, E., Garcia, R., and Casalino, G. (2019, January 3\u20138). Control and perception framework for deep sea mining exploration. Proceedings of the 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China.","DOI":"10.1109\/IROS40897.2019.8967599"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1109\/TMECH.2020.3025973","article-title":"Sea mining exploration with an UVMS: Experimental validation of the control and perception framework","volume":"26","author":"Simetti","year":"2020","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sun, K., Wu, Z., Wang, M., Shang, J., Liu, Z., Zhao, D., and Luo, X. (2024). Accurate Identification Method of Small-Size Polymetallic Nodules Based on Seafloor Hyperspectral Data. J. Mar. Sci. Eng., 12.","DOI":"10.3390\/jmse12020333"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Cui, C., Ma, P., Zhang, Q., Liu, G., and Xie, Y. (2024). Grabbing Path Extraction of Deep-Sea Manganese Nodules Based on Improved YOLOv5. J. Mar. Sci. Eng., 12.","DOI":"10.3390\/jmse12081433"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Dong, L., Wang, H., Song, W., Xia, J., and Liu, T. (August, January 30). Deep sea nodule mineral image segmentation algorithm based on Mask R-CNN. Proceedings of the ACM Turing Award Celebration Conference-China (ACM TURC 2021), Hefei, China.","DOI":"10.1145\/3472634.3474302"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Tomczak, A., Kogut, T., Kaba\u0142a, K., Abramowski, T., Ci\u0105\u017cela, J., and Giza, A. (2024). Automated estimation of offshore polymetallic nodule abundance based on seafloor imagery using deep learning. Sci. Total Environ., 956.","DOI":"10.1016\/j.scitotenv.2024.177225"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"82744","DOI":"10.1109\/ACCESS.2019.2923753","article-title":"An improved u-net convolutio nal networks for seabed mineral image segmentation","volume":"7","author":"Song","year":"2019","journal-title":"IEEE Access"},{"key":"ref_25","first-page":"429","article-title":"Correction of nodule abundance using image analysis technique on manganese nodule deposits","volume":"29","author":"Park","year":"1996","journal-title":"Econ. Environ. Geol."},{"key":"ref_26","first-page":"511","article-title":"Image processing of manganese nodules based on background gray value calculation","volume":"65","author":"Mao","year":"2020","journal-title":"Comput. Mater. Contin."},{"key":"ref_27","unstructured":"Schoening, T., Steinbrink, B., Br\u00fcn, D., Kuhn, T., and Nattkemper, T.W. (2013, January 21\u201325). Ultra-fast segmentation and quantification of poly-metallic nodule coverage in high-resolution digital images. Proceedings of the UMI, Rio de Janeiro, Brazil."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Schoening, T., Jones, D.O., and Greinert, J. (2017). Compact-morphology-based poly-metallic nodule delineation. Sci. Rep., 7.","DOI":"10.1038\/s41598-017-13335-x"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Kuhn, T., Wegorzewski, A., R\u00fchlemann, C., and Vink, A. (2017). Composition, formation, and occurrence of polymetallic nodules. Deep-Sea Mining: Resource Potential, Technical and Environmental Considerations, Springer.","DOI":"10.1007\/978-3-319-52557-0_2"},{"key":"ref_30","unstructured":"Purser, A., Bodur, Y.V., Ramalo, S., Stratmann, T., and Schoening, T. (2021). Seafloor Images of Undisturbed and Disturbed Polymetallic Nodule Province Seafloor Collected During RV SONNE Expeditions SO268\/1+2, PANGAEA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Haeckel, M., and Linke, P. (2021). RV SONNE Fahrtbericht\/Cruise Report SO268-Assessing the Impacts of Nodule Mining on the Deep-Sea Environment: NoduleMonitoring, Manzanillo (Mexico)\u2013Vancouver (Canada), 17.02.\u201327.05.2019, GEOMAR Helmholtz-Zentrum f\u00fcr Ozeanforschung Kiel.","DOI":"10.3289\/GEOMAR_REP_NS_59_20"},{"key":"ref_32","unstructured":"Supervisely (2023, July 20). Supervisely Computer Vision Platform. Available online: https:\/\/supervisely.com."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.Y. (2023). Segment Anything. arXiv.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Varghese, R., and Sambath, M. (2024, January 18\u201319). YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness. Proceedings of the 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), Chennai, India.","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_37","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., and Shum, H.Y. (2022). Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020, January 13\u201319). Efficientdet: Scalable and efficient object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2018). Mask R-CNN. arXiv.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_40","unstructured":"Wang, X., Zhang, R., Kong, T., Li, L., and Shen, C. (2020). SOLOv2: Dynamic and Fast Instance Segmentation. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., and Girshick, R. (2020). PointRend: Image Segmentation as Rendering. arXiv.","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., and Girdhar, R. (2022). Masked-attention Mask Transformer for Universal Image Segmentation. arXiv.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8\u201314). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the ECCV, Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_45","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Republic of Korea."},{"key":"ref_46","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., and Luo, P. (2021). SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. arXiv."},{"key":"ref_47","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., and Xu, J. (2019). MMDetection: Open MMLab Detection Toolbox and Benchmark. arXiv."},{"key":"ref_48","unstructured":"Contributors, M. (2025, February 01). MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark. Available online: https:\/\/github.com\/open-mmlab\/mmsegmentation."},{"key":"ref_49","unstructured":"Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv."},{"key":"ref_50","unstructured":"Loshchilov, I., and Hutter, F. (2019). Decoupled Weight Decay Regularization. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Padilla, R., Netto, S.L., and Da Silva, E.A. (2020, January 1\u20133). A survey on performance metrics for object-detection algorithms. Proceedings of the 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), Niteroi, Brazil.","DOI":"10.1109\/IWSSIP48289.2020.9145130"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015). Fully Convolutional Networks for Semantic Segmentation. arXiv.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Ogwok, D., and Ehlers, E.M. (2022, January 4\u20136). Jaccard index in ensemble image segmentation: An approach. Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems, Quzhou, China.","DOI":"10.1145\/3581792.3581794"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Shamir, R.R., Duchin, Y., Kim, J., Sapiro, G., and Harel, N. (2019). Continuous Dice Coefficient: A Method for Evaluating Probabilistic Segmentations. arXiv.","DOI":"10.1101\/306977"},{"key":"ref_55","unstructured":"Jocher, G., Qiu, J., and Chaurasia, A. (2025, February 02). Ultralytics YOLO. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Jie, W.L., Kalyan, B., Chitre, M., and Vishnu, H. (2017, January 19\u201322). Polymetallic nodules abundance estimation using sidescan sonar: A quantitative approach using artificial neural network. Proceedings of the OCEANS 2017-Aberdeen, Aberdeen, UK.","DOI":"10.1109\/OCEANSE.2017.8084857"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1109\/JOE.2020.2967108","article-title":"Acoustic assessment of polymetallic nodule abundance using sidescan sonar and altimeter","volume":"46","author":"Wong","year":"2020","journal-title":"IEEE J. Ocean. Eng."}],"container-title":["Journal of Marine Science and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-1312\/13\/2\/344\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:33:03Z","timestamp":1760027583000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-1312\/13\/2\/344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,13]]},"references-count":57,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["jmse13020344"],"URL":"https:\/\/doi.org\/10.3390\/jmse13020344","relation":{},"ISSN":["2077-1312"],"issn-type":[{"value":"2077-1312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,13]]}}}