{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T05:15:43Z","timestamp":1764998143529,"version":"3.46.0"},"reference-count":46,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Sichuan Science and Technology program","award":["2025YFHZ0140"],"award-info":[{"award-number":["2025YFHZ0140"]}]},{"name":"China Postdoctoral Science Foundation Funded Project","award":["2024M762265"],"award-info":[{"award-number":["2024M762265"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["32502596"],"award-info":[{"award-number":["32502596"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Funds by FCT\u2013Portuguese Foundation for Science and Technology","award":["UID\/04033\/2023"],"award-info":[{"award-number":["UID\/04033\/2023"]}]},{"DOI":"10.13039\/501100024791","name":"Centre for the Research and Technology of Agro-Environmental and Biological Sciences","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100024791","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Agronomy"],"abstract":"<jats:p>Root system analysis remains methodologically challenging in plant research: traditional soil cultivation obstructs comprehensive root observation, whereas hydroponic visualization lacks ecological relevance due to soil environment exclusion\u2014a critical limitation for crops like soybean. This manuscript developed a cost-effective hybrid imaging system integrating transparent acrylic plates, semi-permeable membranes, and natural soil substrates with high-resolution imaging and controlled illumination, enabling non-destructive root monitoring in quasi-natural soil conditions. Complementing this hardware innovation, this manuscript proposed an unsupervised semantic segmentation algorithm that synergizes path planning with an enhanced DBSCAN framework, achieving the precise extraction of primary and lateral root architectures. Experimental validation demonstrated superior performance in soybean root analysis, with segmentation metrics reaching 0.8444 accuracy, 0.9203 recall, 0.8743 F1-score, and 0.7921 mIoU\u2014significantly outperforming existing unsupervised methods (p&lt;0.01). Strong correlations (R2 &gt; 0.94) with WinRHIZO in quantifying root length, projected area, dimensional parameters, and lateral root counts confirmed system reliability. This soil-compatible phenotyping platform establishes new opportunities for root research, with future developments targeting multi-crop adaptability and complex soil condition applications through modular hardware redesign and 3D reconstruction algorithm integration.<\/jats:p>","DOI":"10.3390\/agronomy15122794","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T15:14:06Z","timestamp":1764861246000},"page":"2794","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Novel Semi-Hydroponic Root Observation System Combined with Unsupervised Semantic Segmentation for Root Phenotyping"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5708-1812","authenticated-orcid":false,"given":"Kunhong","family":"Li","sequence":"first","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University, Ya\u2019an 625000, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7676-349X","authenticated-orcid":false,"given":"Siyue","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University, Ya\u2019an 625000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5127-1554","authenticated-orcid":false,"given":"Christoph","family":"Menz","sequence":"additional","affiliation":[{"name":"Potsdam Institute for Climate Impact Research e. V. (PIK), Telegrafenberg A 31, 14473 Potsdam, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1435-6169","authenticated-orcid":false,"given":"Feng","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Agronomy, Sichuan Agricultural University, Ya\u2019an 625000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7946-8786","authenticated-orcid":false,"given":"Helder","family":"Fraga","sequence":"additional","affiliation":[{"name":"Centre for the Research and Technology of Agroenvironmental and Biological Sciences (CITAB), Inov4Agro, Universidade de Tr\u00e1s-os-Montes e Alto Douro (UTAD), Quinta de Prados, 5000-801 Vila Real, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8135-5078","authenticated-orcid":false,"given":"Jo\u00e3o A.","family":"Santos","sequence":"additional","affiliation":[{"name":"Centre for the Research and Technology of Agroenvironmental and Biological Sciences (CITAB), Inov4Agro, Universidade de Tr\u00e1s-os-Montes e Alto Douro (UTAD), Quinta de Prados, 5000-801 Vila Real, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5046-7029","authenticated-orcid":false,"given":"Bing","family":"Liu","sequence":"additional","affiliation":[{"name":"Sanya Institute of Nanjing Agricultural University, Nanjing Agricultural University, Sanya 572025, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6079-8689","authenticated-orcid":false,"given":"Chenyao","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Agronomy, Sichuan Agricultural University, Ya\u2019an 625000, China"},{"name":"Centre for the Research and Technology of Agroenvironmental and Biological Sciences (CITAB), Inov4Agro, Universidade de Tr\u00e1s-os-Montes e Alto Douro (UTAD), Quinta de Prados, 5000-801 Vila Real, Portugal"},{"name":"Key Laboratory of Agricultural Bioinformatics, Ministry of Education, Sichuan Agricultural University, Chengdu 625014, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s11104-009-9929-9","article-title":"Plant root growth, architecture and function","volume":"321","author":"Hodge","year":"2009","journal-title":"Plant Soil"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yung, W.S., Gao, Y., Huang, C., Zhao, X., Chen, Y., Li, M.W., and Lam, H.M. (2024). From phenotyping to genetic mapping: Identifying water-stress adaptations in legume root traits. BMC Plant Biol., 24.","DOI":"10.1186\/s12870-024-05477-8"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Khan, M., Gemenet, D.C., and Villordon, A. (2016). Root system architecture and abiotic stress tolerance: Current knowledge in root and tuber crops. Front. Plant Sci., 7.","DOI":"10.3389\/fpls.2016.01584"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1111\/tpj.15669","article-title":"Root system architecture in cereals: Progress, challenges and perspective","volume":"110","author":"Maqbool","year":"2022","journal-title":"Plant J."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Afonso, P., Castro, I., Couto, P., Leal, F., Carnide, V., Rosa, E., and Carvalho, M. (2025). Root Phenotyping: A Contribution to Understanding Drought Stress Resilience in Grain Legumes. Agronomy, 15.","DOI":"10.3390\/agronomy15040798"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s13007-019-0414-z","article-title":"Adaptive minirhizotron for pepper roots observation and its installation based on root system architecture traits","volume":"15","author":"Lu","year":"2019","journal-title":"Plant Methods"},{"key":"ref_7","first-page":"10","article-title":"Minirhizotron as an in-situ tool for assessing sugarcane root system growth and distribution","volume":"22","author":"Ohashi","year":"2019","journal-title":"Agric. Res. Technol."},{"key":"ref_8","first-page":"429","article-title":"Progresses in methods for observing crop root pattern system","volume":"36","author":"Liao","year":"2008","journal-title":"Meteorol. Sci. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Adeleke, E., Millas, R., McNeal, W., Faris, J., and Taheri, A. (2020). Variation analysis of root system development in wheat seedlings using root phenotyping system. Agronomy, 10.","DOI":"10.3390\/agronomy10020206"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Passot, S., Gnacko, F., Moukouanga, D., Lucas, M., Guyomarc\u2019h, S., Ortega, B.M., Atkinson, J.A., Belko, M.N., Bennett, M.J., and Gantet, P. (2016). Characterization of pearl millet root architecture and anatomy reveals three types of lateral roots. Front. Plant Sci., 7.","DOI":"10.3389\/fpls.2016.00829"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1186\/s13007-016-0135-5","article-title":"An automated, cost-effective and scalable, flood-and-drain based root phenotyping system for cereals","volume":"12","author":"Slota","year":"2016","journal-title":"Plant Methods"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1104\/pp.109.150748","article-title":"Imaging and analysis platform for automatic phenotyping and trait ranking of plant root systems","volume":"152","author":"Symonova","year":"2010","journal-title":"Plant Physiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1186\/s13007-020-00631-3","article-title":"The platform GrowScreen-Agar enables identification of phenotypic diversity in root and shoot growth traits of agar grown plants","volume":"16","author":"Nagel","year":"2020","journal-title":"Plant Methods"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"334","DOI":"10.3390\/plants4020334","article-title":"Root traits and phenotyping strategies for plant improvement","volume":"4","author":"Motes","year":"2015","journal-title":"Plants"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s13007-015-0055-9","article-title":"High-throughput phenotyping of seminal root traits in wheat","volume":"11","author":"Richard","year":"2015","journal-title":"Plant Methods"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1071\/FP12023","article-title":"GROWSCREEN-Rhizo is a novel phenotyping robot enabling simultaneous measurements of root and shoot growth for plants grown in soil-filled rhizotrons","volume":"39","author":"Nagel","year":"2012","journal-title":"Funct. Plant Biol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11104-011-1039-9","article-title":"Developing X-ray computed tomography to non-invasively image 3-D root systems architecture in soil","volume":"352","author":"Mooney","year":"2012","journal-title":"Plant Soil"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhou, X., Cao, X., Zhang, C., Yan, H., Li, Y., and Luo, X. (2014, January 14\u201316). A method of 3D nondestructive detection for plant root in situ based on CBCT imaging. Proceedings of the 2014 7th International Conference on Biomedical Engineering and Informatics, Dalian, China.","DOI":"10.1109\/BMEI.2014.7002753"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s13007-015-0084-4","article-title":"Rapid phenotyping of crop root systems in undisturbed field soils using X-ray computed tomography","volume":"11","author":"Pfeifer","year":"2015","journal-title":"Plant Methods"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2283","DOI":"10.1093\/jxb\/erv006","article-title":"Phenotyping pipeline reveals major seedling root growth QTL in hexaploid wheat","volume":"66","author":"Atkinson","year":"2015","journal-title":"J. Exp. Bot."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.1104\/pp.15.01388","article-title":"Quantitative 3D analysis of plant roots growing in soil using magnetic resonance imaging","volume":"170","author":"Metzner","year":"2016","journal-title":"Plant Physiol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1186\/s13007-017-0252-9","article-title":"Non-invasive imaging of plant roots in different soils using magnetic resonance imaging (MRI)","volume":"13","author":"Pflugfelder","year":"2017","journal-title":"Plant Methods"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/S0168-1699(02)00100-X","article-title":"Machine vision technology for agricultural applications","volume":"36","author":"Chen","year":"2002","journal-title":"Comput. Electron. Agric."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.copbio.2018.06.002","article-title":"Uncovering the hidden half of plants using new advances in root phenotyping","volume":"55","author":"Atkinson","year":"2019","journal-title":"Curr. Opin. Biotechnol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1016\/j.fcr.2011.01.015","article-title":"Comparison of threshold algorithms for automatic image processing of rice roots using freeware ImageJ","volume":"121","author":"Tajima","year":"2011","journal-title":"Field Crops Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1186\/s13007-018-0352-1","article-title":"Hyperspectral imaging: A novel approach for plant root phenotyping","volume":"14","author":"Bodner","year":"2018","journal-title":"Plant Methods"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s00138-020-01088-z","article-title":"Root identification in minirhizotron imagery with multiple instance learning","volume":"31","author":"Yu","year":"2020","journal-title":"Mach. Vis. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.aca.2012.03.008","article-title":"A density-based segmentation for 3D images, an application for X-ray micro-tomography","volume":"725","author":"Tran","year":"2012","journal-title":"Anal. Chim. Acta"},{"key":"ref_29","unstructured":"Lamine, B., and Nadia, B. (2016, January 21\u201322). Image segmentation using clustering methods. Proceedings of the SAI Intelligent Systems Conference, London, UK."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5933","DOI":"10.1109\/TIP.2016.2616302","article-title":"Real-time superpixel segmentation by DBSCAN clustering algorithm","volume":"25","author":"Shen","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2015.04.006","article-title":"A survey on skeletonization algorithms and their applications","volume":"76","author":"Saha","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"ref_32","first-page":"59","article-title":"Morphological image processing","volume":"2","author":"Goyal","year":"2011","journal-title":"IJCST"},{"key":"ref_33","unstructured":"Ester, M., Kriegel, H.P., Sander, J., and Xu, X. (1996, January 2\u20134). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the KDD, Portland, OR, USA."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Khan, K., Rehman, S.U., Aziz, K., Fong, S., and Sarasvady, S. (2014, January 17\u201319). DBSCAN: Past, present and future. Proceedings of the Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014), Chennai, India.","DOI":"10.1109\/ICADIWT.2014.6814687"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Bundy, A. (1986). Catalogue of artificial intelligence tools. Catalogue of Artificial Intelligence Tools, Springer.","DOI":"10.1007\/978-3-642-96964-5"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1109\/83.935035","article-title":"Breadth-first search and its application to image processing problems","volume":"10","author":"Silvela","year":"2001","journal-title":"IEEE Trans. Image Process."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"012092","DOI":"10.1088\/1757-899X\/420\/1\/012092","article-title":"Comparison analysis of K-means and K-medoid with Ecluidience distance algorithm, Chanberra distance, and Chebyshev distance for big data clustering","volume":"Volume 420","author":"Gultom","year":"2018","journal-title":"IOP Conference Series: Materials Science and Engineering"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ahmed, M., Seraj, R., and Islam, S.M.S. (2020). The k-means algorithm: A comprehensive survey and performance evaluation. Electronics, 9.","DOI":"10.3390\/electronics9081295"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1002\/widm.53","article-title":"Algorithms for hierarchical clustering: An overview","volume":"2","author":"Murtagh","year":"2012","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1094\/PDIS-01-11-0026","article-title":"Comparison of water displacement and WinRHIZO software for plant root parameter assessment","volume":"95","author":"Pang","year":"2011","journal-title":"Plant Dis."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"3007","DOI":"10.2134\/agronj2017.03.0187","article-title":"WinRHIZO technology for measuring morphological traits of bermudagrass stolons","volume":"109","author":"Pornaro","year":"2017","journal-title":"Agron. J."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Liu, S., Begum, N., An, T., Zhao, T., Xu, B., Zhang, S., Deng, X., Lam, H.-M., Nguyen, H.T., and Siddique, K.H.M. (2021). Characterization of root system architecture traits in diverse soybean genotypes using a semi-hydroponic system. Plants, 10.","DOI":"10.3390\/plants10122781"},{"key":"ref_43","first-page":"232","article-title":"Research on Curing Tobacco Image Segmentation Based on K-means Clustering Algorithm","volume":"52","author":"Zhou","year":"2024","journal-title":"J. Anhui Agric. Sci."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, Y., Wang, M., and Zhao, Y. (2023). An improved U-Net-based in situ root system phenotype segmentation method for plants. Front. Plant Sci., 14.","DOI":"10.3389\/fpls.2023.1115713"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1016\/j.compag.2019.05.017","article-title":"SegRoot: A high throughput segmentation method for root image analysis","volume":"162","author":"Wang","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1071\/FP10241","article-title":"Development of a novel semi-hydroponic phenotyping system for studying root architecture","volume":"38","author":"Chen","year":"2011","journal-title":"Funct. Plant Biol."}],"container-title":["Agronomy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-4395\/15\/12\/2794\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T05:12:44Z","timestamp":1764997964000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-4395\/15\/12\/2794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":46,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["agronomy15122794"],"URL":"https:\/\/doi.org\/10.3390\/agronomy15122794","relation":{},"ISSN":["2073-4395"],"issn-type":[{"type":"electronic","value":"2073-4395"}],"subject":[],"published":{"date-parts":[[2025,12,4]]}}}