[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119464-en":3,"doc-seo-119464-105":30,"detail-sidebar-cat-0-en-105":90},{"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},119464,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Synthesis of Ag-Sn Phases Predicted with Machine Learning","The poster presents a research workflow for discovering and validating Ag–Sn alloy phases for next-generation electronic interconnects. It motivates the study with thermal and electromigration limits in miniaturized devices and highlights the advantages of Ag–Sn over Sn–Pb alloys. Machine-learning screening using MAISE accelerates ab initio searches, yielding predicted stable compounds (e.g., AgSn2 and AgSn4). A flux-growth synthesis strategy is paired with vapor-pressure estimation via Antoine/ideal-gas methods, and preliminary compositional analysis indicates AgSn4 and AgSn2 presence.","Binghamton University  \nThe Open Repository @ Binghamton (The ORB)  \n\n| Research Days Posters 2025 | Division of Research |\n| --- | --- |\n| 2025\u003Cbr>Synthesis of Ag-Sn Phases Predicted with Machine Learning\u003Cbr>Jeff Lam\u003Cbr>Binghamton University--SUNY\u003Cbr>Olesya Gorbunova\u003Cbr>Binghamton University--SUNY\u003Cbr>Md Ariful Islam\u003Cbr>Binghamton University--SUNY\u003Cbr>Ganesh Tiwari\u003Cbr>Binghamton University--SUNY\u003Cbr>Tibendra Adhikari\u003Cbr>Binghamton University--SUNY\u003Cbr>Follow this and additional works at: [https://orb.binghamton.edu/research_days_posters_2025](https://orb.binghamton.edu/research_days_posters_2025) |  |\n\nRecommended Citation  \nLam, Jeff; Gorbunova, Olesya; Islam, Md Ariful; Tiwari, Ganesh; and Adhikari, Tibendra, \"Synthesis of AgSn Phases Predicted with Machine Learning\" (2025) . Research Days Posters 2025. 94.  \n[https://orb.binghamton.edu/research_days_posters_2025/94](https://orb.binghamton.edu/research_days_posters_2025/94)  \nThis Book is brought to you for free and open access by the Division of Research at The Open Repository @ Binghamton (The ORB) . It has been accepted for inclusion in Research Days Posters 2025 by an authorized administrator of The Open Repository @ Binghamton (The ORB) . For more information, please contact [ORB@binghamton.edu](ORB@binghamton.edu).  \nSynthesis of Ag-Sn Phases Predicted with Machine Learning  \nJ. Lam,  O. Gorbunova, M. Islam, G. Tiwari, and T. Adhikari  \nPhysics faculty: Z. Lin and A.N. Kolmogorov  \nGrand Challenges  \n• Chip miniaturization limitations  \n◦ Heat flux > 350 W/cm 2 impairs cooling in compact systems  \n◦ Joint current density > 104 A/cm ² accelerates device failure rates  \n◦ Junction T ≈ 250 °C must be tolerated while resisting thermal and electromigration stress  \n• Ag-Sn alloys as novel interconnects  \n◦ Up to 4 times greater thermal fatigue resistance vs Sn-Pb alloys  \n◦ Better ductility, EM and creep resistance vs Sn-Pb alloys  \n◦ RoHS-compliant: ≤ 0 . 1% Pb  \nGrowth of transistor density  \nHeterogenous integration  \nDo any Ag-Sn alloys remain undiscovered?  \nMachine Learning (ML) Predictions  \n• Standard ab initio search strategy (accurate but cost demanding)  \n◦ Define the chemical space  \n◦ Employ global search engine  \n◦ Check T=0 K stability with DFT  \n• ML screening with MAISE [1, 2](accelerated by a factor of 102-103)  \n◦ Build MLPs for selected species  \n◦ Perform evolutionary searches  \n◦ Use MLPs to select candidates  \n◦ Check for high-T ground states  \n◦ Check all results with DFT  \n• Predicted Ag-Sn compounds (brand-new crystal structures shown stable at the DFT level )  \n◦ AgSn 2 : may form above 360 K  \n◦ AgSn4 : may form above 570 K  \nPotential energy surface sampling  \nML-based Sn alloy predictions  \nCa2 Sn NaSn4  \nCuSn2 AgSn2  \nPdSn2  \n29 new stable M-Sn phases  \n14,000 structures examined with DFT  \n2,000,000 structures screened with MLPs  \nCalculated Ag-Sn stability at high T  \nCan the predicted Ag-Sn alloys be synthesized?  \nSynthesis Strategy  \nCrystal synthesis via the Ag-Sn binary phase diagram [3]  \nflux growth method  \nAgSn2  \nStart AgSn4  \nEnd  \n• Tin flux acts as solvent for dissolving raw materials at high temperature  \n• As the solution slowly cools, the solubility decreases, leading to the gradual crystallization of the Ag-Sn phases  \nHow to ensure the synthesis is safe and efficient?  \nVapor Pressure Estimation  \nManaging the vapor pressure is crucial at high temperatures  \nWe estimate vapor pressure via:  \n1 . Antoine equation (best case) 2 . Ideal gas law (otherwise)  \nlog 10 􀝌 = 􀜣 − 􀜥~~ ~~~~ ~~􀜶~~ ~~ 􀜲􀜸 = 􀝊􀜴􀜶  \n􀝌: absolute vapor pressure (mmHg) 􀜴: gas constant  0 . 0821 􀯅􀯠∙~~ ~~􀯔􀯢􀯧􀯟.􀯠∙~~ ~~􀯄. 􀜶: temperature (○C) 􀜣 , 􀜤 , 􀜥: element-specific Antoine coefficients  \nAntoine coefficients and valid temperature values specific to Ag and Sn [4] .  \n|  | A | B | C | Tmin | Tmax |\n| --- | --- | --- | --- | --- | --- |\n| Ag | 8 . 992 | 1 . 5884E+4 | 387 . 39 | 960 . 85 | 6, 136 . 85 |\n| Sn | 8 . 549 | 1 .6656E+4 | 336 .40 | 1, 150 . 00 | 2, 800 . 00 ","cbCaiiQJ4OzsmAdZ","https://ap.wps.com/l/cbCaiiQJ4OzsmAdZ","pdf",1087983,1,2,"English","en",105,"# Grand Challenges\n## Chip miniaturization limitations\n## Ag-Sn alloys as novel interconnects\n# Machine Learning (ML) Predictions\n## Standard ab initio search strategy\n## ML screening with MAISE\n## Predicted Ag-Sn compounds\n# Synthesis Strategy\n## Crystal synthesis via Ag-Sn binary phase diagram\n## Flux growth method\n## Vapor Pressure Estimation\n# Preliminary Results\n## Compositional analysis via EDS","[{\"question\":\"Why are Ag–Sn alloys considered for interconnects instead of Sn–Pb?\",\"answer\":\"The poster links device reliability problems to heat flux, current density, and thermal/electromigration stress. It states Ag–Sn alloys offer up to 4× greater thermal fatigue resistance and improved ductility, as well as EM and creep resistance, while being RoHS-compliant (≤0.1% Pb).\"},{\"question\":\"How does the work use machine learning to predict Ag–Sn phases?\",\"answer\":\"It starts from an ab initio strategy to define chemical space and check stability with DFT, then applies ML screening using MAISE. MLPs are trained for selected species, evolutionary searches generate candidates, high-temperature ground states are checked, and all results are verified with DFT.\"},{\"question\":\"What synthesis and validation approach is used for the predicted compounds?\",\"answer\":\"Synthesis uses the Ag–Sn binary phase diagram and a tin-flux growth method: tin acts as a solvent at high temperature, and gradual cooling drives crystallization as solubility decreases. Vapor pressure is estimated using Antoine equation (best case) or ideal-gas law, and preliminary EDS compositional analysis suggests AgSn4 and likely AgSn2 are present.\"}]","Synthesis of Ag-Sn Phases Predicted with Machine Learning | PDF",1785724433,5,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":28},"synthesis-of-ag-sn-phases-predicted-with-machine-learning","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":21},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/synthesis-of-ag-sn-phases-predicted-with-machine-learning/119464/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why are Ag–Sn alloys considered for interconnects instead of Sn–Pb?","Question",{"text":74,"@type":75},"The poster links device reliability problems to heat flux, current density, and thermal/electromigration stress. It states Ag–Sn alloys offer up to 4× greater thermal fatigue resistance and improved ductility, as well as EM and creep resistance, while being RoHS-compliant (≤0.1% Pb).","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the work use machine learning to predict Ag–Sn phases?",{"text":79,"@type":75},"It starts from an ab initio strategy to define chemical space and check stability with DFT, then applies ML screening using MAISE. MLPs are trained for selected species, evolutionary searches generate candidates, high-temperature ground states are checked, and all results are verified with DFT.",{"name":81,"@type":72,"acceptedAnswer":82},"What synthesis and validation approach is used for the predicted compounds?",{"text":83,"@type":75},"Synthesis uses the Ag–Sn binary phase diagram and a tin-flux growth method: tin acts as a solvent at high temperature, and gradual cooling drives crystallization as solubility decreases. Vapor pressure is estimated using Antoine equation (best case) or ideal-gas law, and preliminary EDS compositional analysis suggests AgSn4 and likely AgSn2 are present.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":29,"slug":136},19,"General","general"]