[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123775-en":3,"doc-seo-123775-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123775,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Rough Surface Reconstruction with Machine Learning Methods - Doctor of Philosophy Thesis","Article-based doctoral thesis investigating machine learning for nonintrusive recovery of surface and flow parameters from acoustic and optical measurements. The work targets amplitudes, wavelengths, and phases for static surface reconstruction, and mean surface velocity and water depth for dynamic rough river free-surfaces. A Kirchhoff approximation acoustic scattering model generates training data, enabling uncertainty-aware inference. Methods include random forests for harmonic surfaces and Metropolis-Hastings for stochastic recovery, with extensions to stochastic multi-harmonic roughness and frequency-wavenumber spectrum features from image sequences. Velocity is well recovered while depth remains challenging.","University of Sheffield  \nRough Surface Reconstruction with Machine Learning Methods  \nMichael-David Johnson  \nA thesis submitted in partial fulfilment of the requirements for the degree of  \nDoctor of Philosophy  \nThe University of Sheffield  \nFaculty of Engineering  \nDepartment of mechanical engineering  \nSubmission Date  \nAutumn 2023  \nDedicated to my Nan,  \nthank you for making me the person I am today.  \nAcknowledgements  \nFirstly, I would like to acknowledge my supervisors, Dr. Anton Krynkin and Dr. Artur Gower. Anton, I highly appreciated working with you throughout my years as a PhD student, the countless hours standing over a whiteboard will be missed greatly. Artur, thank you for being a good friend, and for keeping me sane. I would also like to acknowledge all the people that I have collaborated with. Special mention to Jacques Cuenca, Timo Lahivaara, Fabio Muraro, Simon Tait, and Giulio Dolcetti. Thank you all for the great discussions and patience that all of you have had with me, you truly have made my experience throughout my PhD an enjoyable one.  \nI would like to thank my friends and family who have supported me throughout my PhD, especially due to the extra strain that COVID caused on all of our health. I would especially like to thank Joanna and the entire Watts household. Your care, sympathy, and willingness to listen has been fundamental in giving me the support to be able to complete this research.  \nAbstract  \nThis article-based thesis consists of a collection of four journal papers (one accepted, one submitted pending reviews, two in the process of submission), and one conference paper (accepted and presented at InterNoise 2022) . Each article relates to a chapter written and formatted in manuscript form. The purpose of this work is to investigate the validity of using Machine Learning to deal with recovering parameters nonintrusively. These parameters range from estimating the amplitudes, wavelengths and phases for direct surface reconstruction for static surface recovery, and the average surface velocity, and water depth for dynamic river free-surfaces. This is done both acoustically on a rough surface, and optically on dynamic rough surfaces. Treating the inverse problem with a machine learning approach allows for further analysis of the problem. For example, getting spatial uncertainty for a given reconstruction, or analysing the behaviour of the trained model as opposed to more traditional approaches. Within this thesis, the Kirchhoff Approximation is used as the underlying acoustic scattering model due to the types of surfaces investigated, the accuracy of the model, and the fast computation time. This model is then used to generate the data required for training. Further to this, the frequency-wavenumber spectrum of dynamic free-surface fluctuations of shallow turbulent flow is exploited.  \nFirstly, a random forest is trained on data generated from the Kirchhoff approximation in order to recover parameters of a harmonic surface at a given acoustic frequency. It is shown that this generalises well to unseen surfaces, and out-competes methods that utilise the small amplitude assumption. Different metrics are presented to show the applicability of the random forest framework over different source incident angles, and source frequencies.  \nAn acoustic source with a broadband nature was exploited to get some estimation of prediction error. For each frequency, data was generated and models were trained. This allowed for the spread of predicted parameters to be estimated.  \nIn order to recover a wider range of rough surfaces, as well as to get statistical information, a stochastic method named Metropolis-Hastings was introduced to the problem. This competed well with the random forest predictions for the single harmonic, while giving spatial uncertainty. This was extended to a more complicated roughness profile consisting of a summation of many harmonics at different wavelengths. It was found that the p","cbCaiszHVzcWOHlt","https://ap.wps.com/l/cbCaiszHVzcWOHlt","pdf",40606184,1,274,"English","en",105,"# Abstract\n## Purpose and scope\n## Acoustic and optical recovery framework\n## Random forest approach for harmonic surfaces\n## Broadband error estimation and uncertainty spread\n## Metropolis-Hastings for stochastic roughness and credible intervals\n## Velocity and depth recovery for shallow turbulent flows\n# Statement of Originality\n## Author contribution and credit","[{\"question\":\"What parameters does the thesis aim to recover nonintrusively?\",\"answer\":\"It recovers static surface amplitudes, wavelengths, and phases for direct reconstruction, and for dynamic river free-surfaces it targets average surface velocity and water depth.\"},{\"question\":\"Which acoustic scattering model is used to generate training data?\",\"answer\":\"The Kirchhoff approximation is used as the underlying acoustic scattering model to produce the data required for training.\"},{\"question\":\"How do the main machine-learning approaches differ in the thesis?\",\"answer\":\"Random forests are trained to recover parameters of a harmonic surface and generalize to unseen cases, while Metropolis-Hastings is introduced for stochastic recovery and provides spatial uncertainty via credible intervals.\"}]","Rough Surface Reconstruction with Machine Learning Methods - Doctor of Philosophy Thesis | PDF",1785818497,690,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"rough-surface-reconstruction-with-machine-learning-methods-doctor-of-philosophy-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/rough-surface-reconstruction-with-machine-learning-methods-doctor-of-philosophy-thesis/123775/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What parameters does the thesis aim to recover nonintrusively?","Question",{"text":75,"@type":76},"It recovers static surface amplitudes, wavelengths, and phases for direct reconstruction, and for dynamic river free-surfaces it targets average surface velocity and water depth.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which acoustic scattering model is used to generate training data?",{"text":80,"@type":76},"The Kirchhoff approximation is used as the underlying acoustic scattering model to produce the data required for training.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the main machine-learning approaches differ in the thesis?",{"text":84,"@type":76},"Random forests are trained to recover parameters of a harmonic surface and generalize to unseen cases, while Metropolis-Hastings is introduced for stochastic recovery and provides spatial uncertainty via credible intervals.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]