[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120762-en":3,"doc-seo-120762-105":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},120762,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Aqueous dissolution of Li-Na borosilicates - insights from machine learning and experiments","Previously acquired data could be used to predict glass dissolution kinetics at long times, yet the effectiveness of machine learning approaches must be evaluated. Dissolution of two Li-Na borosilicate base glasses at 40 and 90 °C was studied using SEM-EDS, NMR, and Raman spectroscopy. Boron and sodium predictions were strong with properly normalized release features, but extrapolation across the training feature space reduced accuracy and omitted waste elements lowered long-term lithium and silicon estimates.","1 Title: Aqueous dissolution of Li-Na borosilicates: insights from machine learning and  \n2 experiments  \n3 Authors: Thomas L. Goût ¹,*, Joseph N. P. Lillington ¹, James Walden ¹, 4 Christina Boukouvala¹,², Emilie Ringe¹,², Mike T. Harrison³, Ian Farnan ¹  \n5 ¹Department of Earth Sciences, University of Cambridge, Downing Street, Cambridge, CB2  \n6 3EQ, UK.  \n7 ²Department of Materials Science and Metallurgy, University of Cambridge, 27 Charles  \n8 Babbage Road, Cambridge, CB3 0FS, UK.  \n9 ³National Nuclear Laboratory, Central Laboratory, Sellafield, Seascale, Cumbria, CA20 1PG,  \n10 UK.  \n11 *Corresponding author: T.L. Goût ([tlg29@cam.ac.uk](tlg29@cam.ac.uk))  \n12 Declarations of interest: none  \n13 Keywords  \n14 Machine learning; Aqueous dissolution; Nuclear; Borosilicate glass; Nuclear magnetic  \n15 resonance  \n16 Abstract  \n17 Previously acquired data could be utilised in predicting glass dissolution kinetics at long times, 18 but the application of machine learning methods needs to be assessed. Here, the dissolution  \n19 processes of two Li-Na borosilicate ‘base glasses’ at 40 and 90 °C were investigated by SEM- 20 EDS, NMR and Raman spectroscopy. Boron and sodium machine learning predictions were  \n21 excellent when considering other normalised releases as features. However, extrapolating the  \n22 training feature space yielded poorer performance and the absence of incorporated waste  \n23 elements resulted in underestimated predicted long-term lithium and silicon releases. Faster 24 dissolution kinetics were observed for MW than MW-½Li but the MW-½Li gel layer at 40 °C 25 trapped more water. Whilst BO3 rings leached preferentially at 90 °C, surface enrichment of 26 BO3 at 40 °C suggested [BO4] - transformed prior to dissolution. Results were consistent with 27 interdiffusion being significant at 40 °C and interface-coupled dissolution precipitation beyond 28 7 days at 90 °C.  \n29 1. Introduction  \n30 Quaternary mixed-alkali borosilicate glasses are of particular interest to the nuclear industry, 31 being used in the UK as ‘base glass frits’ to which calcined high-level waste (HLW), arising  \n32 from spent nuclear fuel reprocessing activities, is added during vitrification [1–6] . The Li-Na  \n33 borosilicate base glass composition used for HLW vitrification in the UK, MW-½Li, and its  \n34 original formulation, MW, are presented in Table 1. MW has an equimolar Li/Na ratio to  \n35 optimise transport properties important to the vitrification process, such as melt viscosity, and  \n36 its B contents provides a compromise between optimising waste loading, as limited by Mo  \n37 solubility, and aqueous durability [7–10] . As the addition of LiNO3 to the liquid waste  \n38 improves its reactivity during calcination, half the molar Li of MW was removed (MW-½Li)  \n39 to yield an equimolar Li/Na ratio in the final glass at a HLW loading of 25 wt.%[1,10] .  \n40 Investigations which aim to constrain compositional and environmental effects on the  \n41 dissolution of simulant HLW glasses are rendered difficult as the product HLW glasses  \n42 typically comprise over 20 elements [11–14]. As such, simplified analogues are frequently used  \n43 in mechanistic studies to better constrain these effects (e.g. [15–20]) . In this view, dissolution  \n44 experiments on MW and MW-½Li can provide valuable insights into the effects of varying the  \n45 concentration of total alkalis (Li+Na) and the Li/Na ratio on pristine glass structure and  \n46 dissolution behaviour without convoluting effects, such as complex altered layer structures and  \n47 secondary phase precipitate assemblages. Indeed, in the absence of gel-forming species which  \n48 require charge compensation, such as Al or Zr, alkali metals are solely removed from solution  \n49 through secondary phase precipitation [21] . However, predicting compositional effects on  \n50 chemical durability at long times remains a significant challenge in glass science [22] .  \n51 Recent advances in machine l","cbCaijSr3uWpjrX5","https://ap.wps.com/l/cbCaijSr3uWpjrX5","pdf",1712733,1,55,"English","en",105,"# Introduction\n## Study aims and background on HLW glass dissolution\n## Machine learning approaches and limitations for long-term prediction\n## Experimental and ML methodology","[{\"question\":\"What was investigated in the dissolution study of Li-Na borosilicate base glasses?\",\"answer\":\"The dissolution processes of two Li-Na borosilicate base glasses were investigated at 40 and 90 °C using SEM-EDS, NMR, and Raman spectroscopy.\"},{\"question\":\"How did machine learning predictions perform for boron and sodium?\",\"answer\":\"Predictions for boron and sodium were excellent when other normalized releases were used as input features.\"},{\"question\":\"Why were long-term lithium and silicon releases underestimated by the model?\",\"answer\":\"Underestimation occurred because the training feature space was extrapolated and incorporated waste elements were absent from the features, reducing accuracy at long times.\"}]","Aqueous dissolution of Li-Na borosilicates - insights from machine learning and experiments | PDF",1785731898,139,{"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},"aqueous-dissolution-of-li-na-borosilicates-insights-from-machine-learning-and-experiments","",{"@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/aqueous-dissolution-of-li-na-borosilicates-insights-from-machine-learning-and-experiments/120762/",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","2026-08-03",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 was investigated in the dissolution study of Li-Na borosilicate base glasses?","Question",{"text":75,"@type":76},"The dissolution processes of two Li-Na borosilicate base glasses were investigated at 40 and 90 °C using SEM-EDS, NMR, and Raman spectroscopy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How did machine learning predictions perform for boron and sodium?",{"text":80,"@type":76},"Predictions for boron and sodium were excellent when other normalized releases were used as input features.",{"name":82,"@type":73,"acceptedAnswer":83},"Why were long-term lithium and silicon releases underestimated by the model?",{"text":84,"@type":76},"Underestimation occurred because the training feature space was extrapolated and incorporated waste elements were absent from the features, reducing accuracy at long times.","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"]