[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290494-105":59,"doc-detail-290494-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","machine-learning-optimization-of-lignin-properties-in-green-biorefineries","Machine Learning Optimization of Lignin Properties in Green Biorefineries","","Novel biorefineries can convert lignin, an abundant biopolymer, from side-stream waste into high-value products with minimal experiments. The study optimizes the AquaSolv Omni biorefinery using Bayesian optimization, enabling sample-efficient, guided data collection that links processing conditions (e.g., hydrothermal pretreatment severity and temperature) to multiple experimental outputs. Lignin structural features are characterized with 2D NMR, and Pareto front analysis identifies conditions that jointly maximize lignin yield and β-O-4 linkages for depolymerization to platform chemicals.",{"@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/machine-learning-optimization-of-lignin-properties-in-green-biorefineries/290494/",{"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/machine-learning-optimization-of-lignin-properties-in-green-biorefineries/290494.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",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the study address in green biorefineries?","Question",{"text":113,"@type":114},"It addresses how to optimize lignin processing conditions in the AquaSolv Omni biorefinery to improve lignin yield and β-O-4 linkages for depolymerization into platform chemicals.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does Bayesian optimization improve experimental efficiency?",{"text":118,"@type":114},"It enables sample-efficient and guided data collection by building surrogate models of the experimental design target and selecting new samples through an acquisition function.",{"name":120,"@type":111,"acceptedAnswer":121},"Which experimental inputs and outputs are connected by the models?",{"text":122,"@type":114},"The models relate biorefinery conditions such as hydrothermal pretreatment severity and temperature to experimental outputs, including lignin structural features characterized using 2D nuclear magnetic resonance spectroscopy.","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},290494,1789641836,{"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":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"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","[pubs.acs.org/journal/ascecg](pubs.acs.org/journal/ascecg)  Research Article   \nMachine Learning Optimization of Lignin Properties in Green Biorefineries  \nJoakim Löfgren, Dmitry Tarasov, Taru Koitto, Patrick Rinke, Mikhail Balakshin,* and Milica Todorovíc*  \n Cite This: ACS Sustainable Chem. Eng. 2022, 10, 9469−9479  \nRead Online  \n\n| ACCESS   | Metrics & More |  |  Article Recommendations |  | *sı Supporting Information |\n| --- | --- | --- | --- | --- | --- |\n\nABSTRACT: Novel biorefineries could transform lignin, an abundant biopolymer, from side-stream waste to high-valueadded byproducts at their site of production and with minimal experiments. Here, we report the optimization of the AquaSolvomni biorefinery for lignin using Bayesian optimization, a machine learning framework for sample-efficient and guided data collection. This tool allows us to relate the biorefinery conditions like hydrothermal pretreatment reaction severity and temperature with multiple experimental outputs, such as lignin structural features characterized using 2D nuclear magnetic resonance spectroscopy. By applying a Pareto front analysis to our models, we can find the processing conditions that simultaneously optimize the lignin yield and the amount of β-O-4 linkages for the depolymerization of  \nlignin into platform chemicals. Our study demonstrates the potential of machine learning to accelerate the development of sustainable chemical processing techniques for targeted applications and products.  \nKEYWORDS: Biomass, Valorization, Lignin, Biorefinery, Machine learning, Bayesian optimization  \n■ INTRODUCTION  \nThe transition to a green and sustainable economy requires efficient utilization of our natural resources. Lignin, as a part of lignocellulosic biomatter, is an example of a naturally abundant but under-utilized resource.1,2 Lignin is currently produced in large quantities as a side stream of pulping processes. Valorization of lignin into high-value-added industrially relevant byproducts, materials,3,4 or chemicals5−8 can therefore substantially increase both the sustainability and revenue of biorefineries.4,9 Recently, some of us have developed AquaSolv Omni (AqSO), a green biorefinery for the integrated utilization of all biomass components, with special focus on the lignin-containing streams.10, 11 In the AqSO process, hydrothermal treatment (HTT) is first applied to the biomass feedstock, and the resulting solids are subsequently washed with a solvent to extract lignin. The aqueous environment of HTT eliminates the need for extra chemicals in the reaction medium, which makes AqSO a green process given a suitable choice of solvent.  \nKey strengths of the AqSO biorefinery are the highly tunable  \nknowledge of how the processing conditions relate to the product properties. The same issue is encountered during the development of new valorization approaches: learning the connections between processing conditions and product properties requires significant time and resources. In particular for the valorization of lignin, the situation is further exacerbated by its complex chemical structure.12  \nTo solve experimental optimization tasks, design of experiment (DOE) methods13, 14 are frequently employed. DOE methods provide general strategies for planning data collection and for modeling experimental output. In this context, we refer to the experimental output being modeled asthe design target, abbreviated as target, and the range of processing conditions being considered as the design space. Since laboratory-based experiments are often time consuming and costly, DOE also strives for efficient sampling of the design space. Conventional approaches to DOE include space-filling designs, 15, 16 factorial designs, 17 and response surface methods, 18, 19 where the latter category is frequently regarded as an industry standard. A shortcoming of many conventional DOE  \nDownloaded via UNIV OF TURKU on September 13, 2022 at 07:26:17 (UTC) . See [https://pubs","cbCairghj602mBxo","https://ap.wps.com/l/cbCairghj602mBxo","pdf",4574755,11,"English","# Introduction\n## Background on lignin valorization and the AquaSolv Omni process\n## Limitations of classical DOE approaches\n## Bayesian optimization and surrogate modeling","[{\"question\":\"What problem does the study address in green biorefineries?\",\"answer\":\"It addresses how to optimize lignin processing conditions in the AquaSolv Omni biorefinery to improve lignin yield and β-O-4 linkages for depolymerization into platform chemicals.\"},{\"question\":\"How does Bayesian optimization improve experimental efficiency?\",\"answer\":\"It enables sample-efficient and guided data collection by building surrogate models of the experimental design target and selecting new samples through an acquisition function.\"},{\"question\":\"Which experimental inputs and outputs are connected by the models?\",\"answer\":\"The models relate biorefinery conditions such as hydrothermal pretreatment severity and temperature to experimental outputs, including lignin structural features characterized using 2D nuclear magnetic resonance spectroscopy.\"}]","Machine Learning Optimization of Lignin Properties in Green Biorefineries | PDF",28]