{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T23:50:36Z","timestamp":1776469836598,"version":"3.51.2"},"reference-count":35,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>This study aims to enhance the efficiency of hydrogen production through alkaline water electrolysis by analyzing hydrogen bubble dynamics using high-speed image processing and machine learning algorithms. The experiments were conducted to evaluate the effects of electrical current and ultrasound oscillations on the system performance. The bubble formation and detachment process were recorded and analyzed using two segmentation models: Ilastik, a GUI-based tool, and U-Net, a deep learning convolutional network implemented in PyTorch. v. 2.9.0. Both models were trained on a dataset of 24 images under varying experimental conditions. The evaluation metrics included Intersection over Union (IoU), Root Mean Square Error (RMSE), and bubble diameter distribution. Ilastik achieved better accuracy and lower RMSE, while U-Net. U-Net offered higher scalability and integration flexibility within Python environments. Both models faced challenges when detecting small bubbles and under complex lighting conditions. Improvements such as expanding the training dataset, increasing image resolution, and adopting patch-based processing were proposed. Overall, the result demonstrates the automated image segmentation can provide reliable bubble characterization, contributing to the optimization of electrolysis-based hydrogen production.<\/jats:p>","DOI":"10.3390\/a19010077","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:27:53Z","timestamp":1768570073000},"page":"77","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Image-Based Segmentation of Hydrogen Bubbles in Alkaline Electrolysis: A Comparison Between Ilastik and U-Net"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7244-8611","authenticated-orcid":false,"given":"Jos\u00e9","family":"Pereira","sequence":"first","affiliation":[{"name":"IN+ Center for Innovation, Technology and Policy Research, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Avenida Rovisco Pais, 1049-001 Lisboa, Portugal"}]},{"given":"Reinaldo","family":"Souza","sequence":"additional","affiliation":[{"name":"IN+ Center for Innovation, Technology and Policy Research, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Avenida Rovisco Pais, 1049-001 Lisboa, Portugal"}]},{"given":"Arthur","family":"Normand","sequence":"additional","affiliation":[{"name":"Institut Sup\u00e9rieur de L\u2019A\u00e9ronautique et de l\u2019Espace-\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et d\u00b4A\u00e9rotechnique Poitiers Futuroscope, T\u00e9l\u00e9port 2-1 Avenue Cl\u00e9ment Ader BP 40109, 86961 Futuroscope Chasseneuil Cedex, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9801-7617","authenticated-orcid":false,"given":"Ana","family":"Moita","sequence":"additional","affiliation":[{"name":"IN+ Center for Innovation, Technology and Policy Research, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Avenida Rovisco Pais, 1049-001 Lisboa, Portugal"},{"name":"CINAMIL\u2014Military Academy Research Center, Department of Exact Sciences and Engineering, Portuguese Military Academy, 2720-113 Amadora, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"key":"ref_1","unstructured":"(2026, January 11). Part D\u2019\u00e9nergie Renouvelable Dans la Consommation Finale Brute D\u2019energie en France en 2023. Available online: https:\/\/batizoom.ademe.fr\/indicateurs\/part-des-energies-renouvelables-dans-la-consommation-finale-brute-delectricite."},{"key":"ref_2","unstructured":"IEA (2026, January 11). Share of Renewables in Energy Consumption. Available online: https:\/\/www.iea.org\/countries\/france\/renewables."},{"key":"ref_3","unstructured":"CEA (2026, January 11). CLEFS CEA\u2014Number 50\/51\u2014HIVER 2004-2005 P25. Available online: https:\/\/www.cea.fr\/multimedia\/Documents\/publications\/clefs-cea\/archives\/fr\/024a025alleau.pdf."},{"key":"ref_4","unstructured":"(2026, January 11). Production De L\u2019Hydrogene. Available online: https:\/\/www.connaissancedesenergies.org\/fiche-pedagogique\/production-de-lhydrogene."},{"key":"ref_5","unstructured":"CEA (2026, January 11). CLEFS CEA\u2014Number 50\/51\u2014HIVER 2004-2005 P31. Available online: https:\/\/www.cea.fr\/multimedia\/Documents\/publications\/clefs-cea\/archives\/fr\/031a033baudouin.pdf."},{"key":"ref_6","unstructured":"ADEME (2026, January 11). La France Pourra-T-Elle Produire Son Propre Hydrog\u00e8ne Vert De Fa\u00e7on Comp\u00e9titive?. Available online: https:\/\/hydrogentoday.info\/ademe-france-produire-hydrogene-vert\/."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"104169","DOI":"10.1016\/j.ijmultiphaseflow.2022.104169","article-title":"Bubble identification from images with machine learning methods","volume":"155","author":"Hessenkemper","year":"2022","journal-title":"Int. J. Multiph. Flow"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Navab, N., Hornegger, J., Wells, W., and Frangi, A. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015; Lecture Notes in Computer Science, Springer.","DOI":"10.1007\/978-3-319-24571-3"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"14529","DOI":"10.1039\/D3CP05869G","article-title":"Deep learning-enhanced characterization of bubble dynamics in proton exchange membrane water electrolyzers","volume":"26","author":"Gompou","year":"2024","journal-title":"Phys. Chem. Chem. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Shi, X., Chen, X., Cen, L., Xie, Y., and Yin, Z. (2025). Aluminum Electrolysis Fire-Eye Image Segmentation Based on the Improved U-Net Under Carbon Slag Interference. Electronics, 14.","DOI":"10.3390\/electronics14020336"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104336","DOI":"10.1016\/j.ijmultiphaseflow.2022.104336","article-title":"Automated bubble analysis of high-speed subcooled flow boiling images using U-net transfer learning and global optical flow","volume":"159","author":"Seong","year":"2023","journal-title":"Int. J. Multiph. Flow"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"036105","DOI":"10.1063\/5.0274266","article-title":"A comparative analysis of YOLOv8 and U-Net image segmentation approaches for transmission electron micrographs of polycrystalline thin films","volume":"3","author":"Patrick","year":"2025","journal-title":"APL Mach. Learn."},{"key":"ref_13","unstructured":"Xu, Y., Zhang, H., and Li, X. (2020). Recent Progress in Electrocatalysts for Water Electrolysis. Catalysts, 10."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Goudula-Jopek, A. (2015). Hydrogen Production: By Electrolysis, John Wiley and Sons.","DOI":"10.1002\/9783527676507"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"F3197","DOI":"10.1149\/2.0271611jes","article-title":"Acidic or alkaline? towards a new perspective on the efficiency of water electrolysis","volume":"163","author":"Schalenbach","year":"2016","journal-title":"J. Electrochem. Soc."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Stolten, D., and Emonts, B. (2016). Hydrogen Science and Engineering: Materials, Processes, Systems and Technology, Wiley-VCH.","DOI":"10.1002\/9783527674268"},{"key":"ref_17","first-page":"133","article-title":"Effect of bubbles attached to an electrode on electrical resistance and dissolved gas concentration","volume":"387","author":"Wilson","year":"1983","journal-title":"Proc. R. Soc. Lond. Ser. A Math. Phys. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4119","DOI":"10.1016\/S0013-4686(03)00579-6","article-title":"Water electrolysis under microgravity: Part 1. Experimental technique","volume":"48","author":"Matsushima","year":"2003","journal-title":"Electrochim. Acta"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"238575","DOI":"10.1016\/j.jpowsour.2025.238575","article-title":"Scanning Acoustic Microscopy for Quantifying Two-phase Transfer in Operando Alkaline Water Electrolyzer","volume":"660","author":"Dou","year":"2025","journal-title":"J. Power Sources"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rox, H., Bashkatov, A., Yang, X., Loos, S., Mutschke, G., Gerbeth, G., and Eckert, K. (2022). Bubble size distribution and electrode coverage at porous nickel electrodes in a novel 3-electrode flow-through cell. arXiv.","DOI":"10.1016\/j.ijhydene.2022.10.165"},{"key":"ref_21","first-page":"104667","article-title":"Synergistic effects of piezoelectric actuators and electrode architecture in alkaline water electrolysis","volume":"83","author":"Silva","year":"2025","journal-title":"Sustain. Energy Technol. Assess."},{"key":"ref_22","unstructured":"(2026, January 11). Ilastik. Available online: https:\/\/www.ilastik.org\/documentation\/pixelclassification\/pixelclassification."},{"key":"ref_23","unstructured":"H\u00e9bert, P., and Laurendeau, D. (2026, January 11). Traitement Des Images (Part 1: Pretreatment). Available online: https:\/\/www.scribd.com\/document\/498672954\/Resume-Rtrait-Ement-Image."},{"key":"ref_24","unstructured":"IBM (2026, January 11). Qu\u2019est Ce Qu\u2019une For\u00eat D\u2019Arbres D\u00e9cisionnels. 59 Analysis of Bubble Dynamics on Electrodes via High-Speed Image Processing. Available online: https:\/\/www.ibm.com\/frfr\/think\/topics\/random-forest."},{"key":"ref_25","unstructured":"(2026, January 11). Les R\u00e9seaux De Neurones Convolutifs. Available online: https:\/\/datasciencetoday.net\/index.php\/en-us\/deep-learning\/173-les-reseaux-de-neuronesconvolutifs."},{"key":"ref_26","unstructured":"Taparia, A. (2026, January 11). U-Net Architecture Explained. Available online: https:\/\/www.geeksforgeeks.org\/machine-learning\/u-net-architecture-explained\/."},{"key":"ref_27","unstructured":"ImageJ Official Website (2026, January 11). TrackMate LAP Trackers. Available online: https:\/\/imagej.net\/plugins\/trackmate\/trackers\/lap-trackers."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1007\/s12650-022-00849-4","article-title":"Deep learning-assisted segmentation of bubble image shadowgraph","volume":"25","author":"Chen","year":"2022","journal-title":"J. Vis."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"013011","DOI":"10.1103\/PRXEnergy.4.013011","article-title":"Oxygen versus Hydrogen Bubble Dynamics during Water Electrolysis at Microelectrodes","volume":"4","author":"Babich","year":"2025","journal-title":"PRX Energy"},{"key":"ref_30","first-page":"22-00325","article-title":"Deep learning-based bubble detection with automatic training data generation: Application to the PEM water electrolysis","volume":"89","author":"Asaoka","year":"2023","journal-title":"Trans. JSME"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"556","DOI":"10.3390\/hydrogen4030036","article-title":"Oxygen Bubble Dynamics in PEM Water Electrolyzers with a Deep-Learning-Based Approach","volume":"4","author":"Sinapan","year":"2023","journal-title":"Hydrogen"},{"key":"ref_32","unstructured":"Craye, E.J.B. (2026, January 11). Bubble Quantification in the Near Electrode Region in Alkaline Water Electrolysis. TU Delft Repository. Available online: https:\/\/resolver.tudelft.nl\/uuid:f85ef347-0207-4481-999e-a0c87d7a0ca1."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1007\/s00348-019-2804-4","article-title":"Study on bubble visualization of gas-evolving electrolysis in forced convective electrolyte","volume":"60","author":"Lee","year":"2019","journal-title":"Exp. Fluids"},{"key":"ref_34","unstructured":"Park, J. (2024). Study of Bubble Dynamics and Mass Transport in Alkaline Water Electrolysis: Insights from Event-Based Imaging. UC Irvine Electronic Theses and Dissertations. [Master\u2019s Thesis, University of California, Irvine]. Available online: https:\/\/escholarship.org\/uc\/item\/6dh3w0ds."},{"key":"ref_35","unstructured":"Zerrougui, I., Li, Z., and Hissel, D. (2023, January 25\u201327). Comprehensive Modeling and Analysis of Bubble Dynamics and its Impact on PEM Water Electrolysis Performance. Proceedings of the International Conference on Fundamentals and Development of Fuel Cells, Ulm, Germany."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/1\/77\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T05:27:24Z","timestamp":1768714044000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/1\/77"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["a19010077"],"URL":"https:\/\/doi.org\/10.3390\/a19010077","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,16]]}}}