[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120494-en":3,"doc-seo-120494-105":30,"detail-sidebar-cat-0-en-105":95},{"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},120494,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Machine Learning for Inorganic Materials Synthesis from Scientific Literature","Scientific literature holds decades of practical knowledge for making inorganic materials, but relevant guidance is dispersed across unstructured text, figures, and tables. This dissertation builds machine-learning pipelines to convert such unstructured sources into structured, machine-readable datasets and then apply them to synthesis science. It evaluates domain-specific pretraining and fine-tuning for materials named-entity recognition and relation extraction using MatBERT NER, and introduces curated datasets for seed-mediated gold nanoparticle synthesis and solid-state synthesis with impurity phases, enabling analyses of morphology drivers and the value of negative outcomes for phase-pure routes.","UC Berkeley  \nUC Berkeley Electronic Theses and Dissertations  \nTitle  \nMachine Learning for Inorganic Materials Synthesis from Scientific Literature  \nPermalink  \n[https://escholarship.org/uc/item/8qj3z9zs](https://escholarship.org/uc/item/8qj3z9zs)  \nISBN  \n9798293892402  \nAuthor  \nLee, Sanghoon  \nPublication Date  \n2025-08-01  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nMachine Learning for Inorganic Materials Synthesis from Scientific Literature  \nby  \nSanghoon Lee  \nA dissertation submitted in partial satisfaction of the requirements for the degree of  \nDoctor of Philosophy  \nin  \nEngineering-Materials Science and Engineering and the Designated Emphasis  \nin  \nComputational and Data Science and Engineering  \nin the  \nGraduate Division  \nof the  \nUniversity of California, Berkeley  \nCommittee in charge:  \nDr. Anubhav Jain, Co-Chair  \nProfessor Gerbrand Ceder, Co-Chair  \nProfessor Mark Asta  \nProfessor Sandrine Dudoit  \nSummer 2025  \nMachine Learning for Inorganic Materials Synthesis from Scientific Literature  \nCopyright 2025  \nby  \nSanghoon Lee  \n1  \nAbstract  \nMachine Learning for Inorganic Materials Synthesis from Scientific Literature  \nby  \nSanghoon Lee  \nDoctor of Philosophy in Engineering-Materials Science and Engineering and the Designated Emphasis in  \nComputational and Data Science and Engineering  \nUniversity of California, Berkeley  \nDr. Anubhav Jain, Co-Chair  \nProfessor Gerbrand Ceder, Co-Chair  \nScientific literature contains decades of “how-to” knowledge on making inorganic materials, yet the information is locked in various forms of unstructured text, figures and tables. This dissertation develops machine-learning pipelines that convert unstructured text into structured, machine-readable data and then leverage it for synthesis science. First, I quantify how domain-specific pre-training and fine-tuning improve named-entity recognition and relation-extraction for materials science text, in MatBERT NER model development. Building on these models, I present two large, curated datasets and downstream analyses-seed-mediated gold nanoparticle synthesis and solid-state synthesis with impurity phases. For seed-mediated gold nanoparticle synthesis, a hybrid (rule-based and Machine Learning) parser, yields 492 fully validated recipes spanning spheres, rods, stars and other shapes. Statistical and interpretable ML models recover known morphology drivers—most notably the dominant role of the seed capping agent—and expose previously overlooked variability in reported aspect ratios. For solid-state inorganic synthesis with impurity phases, few-shot Large Language Model (LLM) extraction pipeline extracted 80,823 recipes, of which 18,874 explicitly report impurity (i.e., “failed”) products. The inclusion of negative outcomes provides new insights in synthesis routes and factors affecting phase pure syntheses. Together, these contributions show how LLMs can transform scattered resources of experimental data into comprehensive data, and learn rules and insights for targeted synthesis. Exploring many methods from rule-based Natural Language Processing (NLP) to fine-tuned LLM, this work advances data-driven materials discovery and opens new avenues for accelerating the design of inorganic materials.  \ni  \nTo my parents, my grandparents, and 20 kg of experience.  \nii  \nContents  \nContents ii  \nList of Figures iv  \nList of Tables vi  \n1 Introduction 1  \n1.1 Materials Discovery Aided by Computational Innovations ........... 1  \n1.2 Materials Synthesis Bottleneck .......................... 2  \n1.3 Leveraging Accumulated Synthesis Records and Knowledge from Literature . 4  \n1.4 Toward Machine Learning for Inorganic Synthesis ............... 7  \n2 Large Language Models for Materials Science 9  \n2.1 Introduction .................................... 9  \n2.2 Named Entity Recognition using MatBERT .................. 10  \n2.3 Structured I","cbCaija5Jluqw9Fy","https://ap.wps.com/l/cbCaija5Jluqw9Fy","pdf",3747447,1,104,"English","en",105,"# Introduction\n## Materials Discovery Aided by Computational Innovations\n## Materials Synthesis Bottleneck\n## Leveraging Accumulated Synthesis Records and Knowledge from Literature\n## Toward Machine Learning for Inorganic Synthesis\n# Large Language Models for Materials Science\n## Introduction\n## Named Entity Recognition using MatBERT\n## Structured Information Extraction using Fine-tuned LLM\n# Seed-mediated Growth of Gold Nanoparticles\n## Introduction\n## Methods\n## Results\n## Discussion\n## Conclusion\n## Supporting Information\n# Solid-state synthesis of Inorganic Materials\n## Introduction\n## Methods\n## Data Records\n## Technical Validation\n## Supporting Information\n# Conclusion and Outlook\n# Bibliography\n# List of Figures\n# List of Tables","[{\"question\":\"What problem does the dissertation address in inorganic materials synthesis?\",\"answer\":\"It addresses how decades of “how-to” knowledge in scientific literature are trapped in unstructured text, figures, and tables, limiting the ability to reuse experimental guidance for synthesis science.\"},{\"question\":\"How does the work extract information from materials science literature?\",\"answer\":\"It develops machine-learning pipelines that convert unstructured text into structured, machine-readable data, including a MatBERT-based approach for named-entity recognition and fine-tuned LLM extraction for structured information.\"},{\"question\":\"What datasets and synthesis targets are produced?\",\"answer\":\"It presents two large curated datasets: one for seed-mediated gold nanoparticle synthesis with 492 fully validated recipes, and another for solid-state inorganic synthesis including 80,823 extracted recipes where 18,874 explicitly report impurity products.\"},{\"question\":\"Why are negative outcomes important for solid-state synthesis?\",\"answer\":\"Including impurity-reporting “failed” products provides new insights into synthesis routes and factors that influence achieving phase-pure outcomes.\"}]","Machine Learning for Inorganic Materials Synthesis from Scientific Literature | PDF",1785730355,262,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"machine-learning-for-inorganic-materials-synthesis-from-scientific-literature","",{"@graph":36,"@context":89},[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/machine-learning-for-inorganic-materials-synthesis-from-scientific-literature/120494/",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",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the dissertation address in inorganic materials synthesis?","Question",{"text":75,"@type":76},"It addresses how decades of “how-to” knowledge in scientific literature are trapped in unstructured text, figures, and tables, limiting the ability to reuse experimental guidance for synthesis science.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the work extract information from materials science literature?",{"text":80,"@type":76},"It develops machine-learning pipelines that convert unstructured text into structured, machine-readable data, including a MatBERT-based approach for named-entity recognition and fine-tuned LLM extraction for structured information.",{"name":82,"@type":73,"acceptedAnswer":83},"What datasets and synthesis targets are produced?",{"text":84,"@type":76},"It presents two large curated datasets: one for seed-mediated gold nanoparticle synthesis with 492 fully validated recipes, and another for solid-state inorganic synthesis including 80,823 extracted recipes where 18,874 explicitly report impurity products.",{"name":86,"@type":73,"acceptedAnswer":87},"Why are negative outcomes important for solid-state synthesis?",{"text":88,"@type":76},"Including impurity-reporting “failed” products provides new insights into synthesis routes and factors that influence achieving phase-pure outcomes.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]