[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291137-105":59,"doc-detail-291137-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","correlating-structure-loss-and-operational-conditions-in-czochralski-silicon-ingot-growth-using-machine-learning","Correlating Structure Loss and Operational Conditions in Czochralski Silicon Ingot Growth Using Machine Learning","","This work investigates relationships between process parameters and structure loss occurrence in Czochralski silicon ingots using machine learning. Feature subsets extracted from a dataset of over 14,000 ingots train random forests to predict structure loss with high accuracy. Multiple rounds of feature-importance analysis refine the parameter set, and partial dependence analysis evaluates how parameter variations affect structure-loss likelihood. Predictive features mainly appear late in the process and are often tied to manual interventions or reflect the structure loss outcome itself.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/correlating-structure-loss-and-operational-conditions-in-czochralski-silicon-ingot-growth-using-machine-learning/291137/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/correlating-structure-loss-and-operational-conditions-in-czochralski-silicon-ingot-growth-using-machine-learning/291137.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What does the study aim to predict regarding Czochralski silicon ingots?","Question",{"text":113,"@type":114},"It predicts the occurrence of structure loss (SL) by learning correlations between process parameters and SL occurrence.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How are machine learning models trained in this work?",{"text":118,"@type":114},"The study identifies feature subsets from a dataset of over 14,000 ingots and trains random forests to predict structure loss.",{"name":120,"@type":111,"acceptedAnswer":121},"Which process stage provides the most predictive information for structure loss?",{"text":122,"@type":114},"The most predictive features are recorded primarily late in the process.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291137,1789643540,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":144,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","SiliconPV 2025, 15th International Conference on Crystalline Silicon Photovoltaics Characterisation, Modelling and Simulation  \n[https://doi.org/10.52825/siliconpv.v3i.2682](https://doi.org/10.52825/siliconpv.v3i.2682)  \n© Authors. This work is licensed under a Creative Commons Attribution 4.0 International License Published: 06 Jan. 2026  \nCorrelating Structure Loss and Operational Conditions in Czochralski Silicon Ingot Growth Using Machine Learning  \nAlfredo Sanchez Garcia1  , Rania Hendawi2 , Hendrik Schön3 , and Marisa Di Sabatino2   \n1Sustainable Energy Technology, SINTEF AS, Norway  \n2Department of Material Science and Engineering, Norwegian University of Science and Technology (NTNU), Norway  \n3NorSun, Norway  \n*Correspondence: Alfredo Sanchez Garcia, [alfredo.sanchez@sintef.no](alfredo.sanchez@sintef.no)  \nAbstract. This work investigates the relationships between process parameters and the occurrence of structure loss in Czochralski silicon ingots using machine learning. Subsets of features are identified from a dataset of over 14,000 ingots and are used to train random forests to predict structure loss with high accuracy. Multiple rounds of feature importance analysis and refinement are conducted to isolate the process parameters that may have the most significant impact in the occurrence of structure loss. Partial dependence analysis is employed to examine how variations in particular parameters might affect the likelihood of structure loss happening. The results show that the most predictive features of structure loss are primarily recorded late in the process. These features are often influenced by manual interventions or reflect the outcome of structure loss itself. In contrast, early-stage parameters exhibit limited predictive power, suggesting that either early indicators of structure loss are not captured in the available data or that structure loss originates from events occurring later in the growth process. While not predictive in a preventive sense, the model effectively detects deviations from normal operation, thereby demonstrating the value of machine learning for uncovering complex patterns in manufacturing processes data.  \nKeywords: Machine Learning, Structure Loss, Czochralski Silicon Ingots  \n1. Introduction  \nSilicon-based photovoltaics hold 95% of the solar energy market share, with over 96% of these silicon solar cells being monocrystalline due to their higher efficiency and lower defects level [1] . Monocrystalline wafers are sliced from single-crystal silicon ingots produced via the Czochralski (Cz) process [2], a method for silicon growth that has experienced considerable progress in recent years.  \nThe increasing demand for silicon has created a requirement for larger ingot diametersand crucible sizes, presenting challenges in the Czochralski silicon growth method. A considerable number of Czochralski silicon ingots is remelted primarily due to dislocations formed during growth, a phenomenon often referred to as structure loss (SL) [3, 4] . Understanding how SL relates to operational conditions and process parameters during the crystal pulling is crucial, as even small increments in yield can have significant economic benefits. To achieve this, the present work proposes the use of machine learning (ML) to perform a correlation study  \nand investigate whether certain process parameters are associated with an increased likelihood of SL. The goal of this study is to understand which parameters, or combinations of parameters, contribute to a higher risk of SL. This will ultimately enable better control of the Cz process and reduce the occurrence of structure loss.  \nThis work is structured as follows: section 2 introduces the problem of structure loss during the Cz process. Section 3 presents the workflow and methodology employed in the correlation study. Section 4 highlights the findings obtained with the methodology. Finally, Section 5 gives the main conclusions.  \n2. Solar Cell Silicon Ingot","cbCaimLJUzAnQaSo","https://ap.wps.com/l/cbCaimLJUzAnQaSo","pdf",1024560,"English","# 1. Introduction\n# 2. Solar Cell Silicon Ingot Production and Structure Loss\n# 3. Machine Learning Methodology for Czochralski Process Analysis\n# 4. Findings\n# 5. Main Conclusions","[{\"question\":\"What does the study aim to predict regarding Czochralski silicon ingots?\",\"answer\":\"It predicts the occurrence of structure loss (SL) by learning correlations between process parameters and SL occurrence.\"},{\"question\":\"How are machine learning models trained in this work?\",\"answer\":\"The study identifies feature subsets from a dataset of over 14,000 ingots and trains random forests to predict structure loss.\"},{\"question\":\"Which process stage provides the most predictive information for structure loss?\",\"answer\":\"The most predictive features are recorded primarily late in the process.\"}]","Correlating Structure Loss and Operational Conditions in Czochralski Silicon Ingot Growth Using Machine Learning | PDF",25]