[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119691-en":3,"doc-seo-119691-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},119691,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Machine Learning-Derived Correlations for Scale-Up and Technology Transfer of Primary Nucleation Kinetics - Study findings and modeling approach","Scaling up and technology transfer of crystallization processes face challenges stemming from the stochastic nature of primary nucleation, scale-dependent nucleation mechanisms, and diverse scale-up strategies. Isothermal induction-time experiments were conducted across vessel volumes, impeller types, and impeller speeds, enabling estimation of nucleation rate and growth time via an induction time distribution model. Machine learning then related CFD-derived hydrodynamic features to kinetic parameters, identifying two top models for nucleation rate and one for growth time, and ensembled them to predict nucleation probability.","[pubs.acs.org/crystal](pubs.acs.org/crystal)  Article   \nMachine Learning-Derived Correlations for Scale-Up and Technology Transfer of Primary Nucleation Kinetics  \nStephanie Yerdelen, Yihui Yang, Justin L. Quon, Charles D. Papageorgiou, Chris Mitchell, Ian Houson, Jan Sefcik, Joop H. ter Horst, Alastair J Florence, and Cameron J. Brown*  \n Cite This: [https://doi.org/10.1021/acs.cgd.2c00192](https://doi.org/10.1021/acs.cgd.2c00192)  \nRead Online  \nDownloaded via 86.134.239.238 on January 20, 2023 at 12:49:12 (UTC) . See [https://pubs.acs.org/sharingguidelines](https://pubs.acs.org/sharingguidelines) for options on how to legitimately share published articles.  \nACCESS  \n Metrics & More  \n Article Recommendations  \n*sı   \nSupporting Information  \nABSTRACT: Scaling up and technology transfer of crystallization processes have been and continue to be a challenge. This is often due to the stochastic nature of primary nucleation, various scale dependencies of nucleation mechanisms, and the multitude of scale-up approaches. To better understand these dependencies, a series of isothermal induction time studies were performed across a range of vessel volumes, impeller types, and impeller speeds. From these measurements, the nucleation rate and growth time were estimated as parameters of an induction time distribution model. Then using machine learning techniques, correlations between the vessel hydrodynamic features, calculated from computational flow dynamic simulations, and nucleation kinetic parameters were analyzed. Of the 18 machine  \nlearning models trained, two models for the nucleation rate were found to have the best performance (in terms of % of predictions within experimental variance): a nonlinear random Forest model and a nonlinear gradient boosting model. For growth time, anonlinear gradient boosting model was found to outperform the other models tested. These models were then ensembled to directly predict the probability of nucleation, at a given time, solely from hydrodynamic features with an overall root mean square error of 0.16. This work shows how machine learning approaches can be used to analyze limited datasets of induction times to provide insights into what hydrodynamic parameters should be considered in the scale-up of an unseeded crystallization process.  \n1. INTRODUCTION  \nSolution-based crystallization processes are implemented to obtain highly pure materials for use in industries such as pharmaceuticals and fine chemicals. Critical quality attributes (CQAs), including polymorphism, crystal shape, and size distribution, are primarily affected by the nucleation event for unseeded conditions. However, to gain further control over CQAs and because of the difficulties in controlling primary nucleation, seeded crystallization processes are often used. Under such conditions, growth, secondary nucleation, and other phenomena such as agglomeration can become dominant.1,2  \nPrimary nucleation is the formation of crystal nuclei from a crystal-free solution3 that is supersaturated (and thus thermodynamically metastable) with respect to a crystalline phase. Supersaturation can be induced by changing the solution temperature and/or composition through cooling, evaporation, mixing (e.g., in antisolvent or reactive crystallization),4 or a combination thereof. Homogeneous nucleation takes place in a clear supersaturated solution in the absence of any foreign material. Heterogeneous nucleation, generally regarded as the process of most practical relevance to industrial processes, involves the formation of the new solid phase as a result of the presence of interfaces present on other particles or equipment surfaces, which can reduce the energy barrier for nuclei forming on them in supersaturated solutions. In  \npractice, this means that lower supersaturations are needed for heterogeneous nucleation. Primary nucleation is a stochastic event strongly dependent on supersaturation, and the kinetics of this process can be invest","cbCaiqDhIkYdU088","https://ap.wps.com/l/cbCaiqDhIkYdU088","pdf",3217221,1,13,"English","en",105,"# ABSTRACT\n# INTRODUCTION\n## Primary nucleation and its stochastic dependence\n## Isothermal induction time measurements and modeling\n## Hydrodynamics, agitation, and scale-up relevance","[{\"question\":\"What measurements were used to study scale-up and technology transfer in primary nucleation?\",\"answer\":\"A series of isothermal induction time studies were performed across different vessel volumes, impeller types, and impeller speeds. Induction times were then used to estimate nucleation rate and growth time parameters.\"},{\"question\":\"How were nucleation kinetics linked to vessel and impeller conditions?\",\"answer\":\"Computational flow dynamics simulations generated vessel hydrodynamic features, which were used as inputs for machine learning models. These models learned correlations between hydrodynamics and nucleation kinetic parameters.\"},{\"question\":\"Which machine learning approaches performed best for nucleation rate and growth time?\",\"answer\":\"For nucleation rate, a nonlinear random forest model and a nonlinear gradient boosting model showed the best performance. For growth time, a nonlinear gradient boosting model outperformed the other tested models.\"}]","Machine Learning-Derived Correlations for Scale-Up and Technology Transfer of Primary Nucleation Kinetics - Study findings and modeling approach | PDF",1785725786,33,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-derived-correlations-for-scale-up-and-technology-transfer-of-primary-nucleation-kinetics-study-findings-and-modeling-approach","",{"@graph":36,"@context":86},[37,54,69],{"@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-derived-correlations-for-scale-up-and-technology-transfer-of-primary-nucleation-kinetics-study-findings-and-modeling-approach/119691/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What measurements were used to study scale-up and technology transfer in primary nucleation?","Question",{"text":76,"@type":77},"A series of isothermal induction time studies were performed across different vessel volumes, impeller types, and impeller speeds. Induction times were then used to estimate nucleation rate and growth time parameters.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How were nucleation kinetics linked to vessel and impeller conditions?",{"text":81,"@type":77},"Computational flow dynamics simulations generated vessel hydrodynamic features, which were used as inputs for machine learning models. These models learned correlations between hydrodynamics and nucleation kinetic parameters.",{"name":83,"@type":74,"acceptedAnswer":84},"Which machine learning approaches performed best for nucleation rate and growth time?",{"text":85,"@type":77},"For nucleation rate, a nonlinear random forest model and a nonlinear gradient boosting model showed the best performance. For growth time, a nonlinear gradient boosting model outperformed the other tested models.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]