BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20251114T001550Z UID:F745DD81-F675-4BFA-9CC6-E8D0E7154377 DTSTART;TZID=America/Los_Angeles:20251113T120000 DTEND;TZID=America/Los_Angeles:20251113T130000 DESCRIPTION:The rapid growth of 3D advanced packaging introduces new challe nges in inspection and failure analysis\, where complex structures such as microbumps\, redistribution layers (RDLs)\, and through-silicon vias (TSV s) demand reliable non-destructive testing (NDT). Conventional approaches\ , including Scanning Acoustic Microscopy (SAM) and X-ray imaging\, are lim ited by noise\, resolution\, and defect visibility\, creating barriers for reproducible and scalable analysis. To address these challenges\, our wor k advances an AI-powered multimodal inspection framework that couples phys ics-informed machine learning with structured data infrastructure. A Physi cs-Informed Neural Network (PINN) approach enhances SAM imaging by embeddi ng acoustic wave physics into reconstructions\, producing higher-fidelity images validated through structural similarity and physical accuracy metri cs. Complementing this\, multimodal data fusion across SAM\, X-ray laminog raphy\, optical microscopy\, and CT establishes richer defect detection an d cross-validation. Central to this effort is the creation of multimodalit y benchmark datasets built on standardized acquisition protocols\, structu red metadata schemas\, and annotation pipelines. These datasets provide no t only a foundation for AI model training but also enable reproducibility\ , traceability\, and interoperability across future programs.\n\nSpeaker(s ): Navid Asadi\, \n\nVirtual: https://events.vtools.ieee.org/m/498529 LOCATION:Virtual: https://events.vtools.ieee.org/m/498529 ORGANIZER:p.wesling@ieee.org SEQUENCE:11 SUMMARY:AI-Enhanced Multimodal Approaches for Electronics Metrology and Fai lure Analysis URL;VALUE=URI:https://events.vtools.ieee.org/m/498529 X-ALT-DESC:Description: <br /><p>The rapid growth of 3D advanced packaging introduces new challenges in inspection and failure analysis\, where compl ex structures such as microbumps\, redistribution layers (RDLs)\, and thro ugh-silicon vias (TSVs) demand reliable non-destructive testing (NDT). Con ventional approaches\, including Scanning Acoustic Microscopy (SAM) and X- ray imaging\, are limited by noise\, resolution\, and defect visibility\, creating barriers for reproducible and scalable analysis. To address these challenges\, our work advances an AI-powered multimodal inspection framew ork that couples physics-informed machine learning with structured data in frastructure. A Physics-Informed Neural Network (PINN) approach enhances S AM imaging by embedding acoustic wave physics into reconstructions\, produ cing higher-fidelity images validated through structural similarity and ph ysical accuracy metrics. Complementing this\, multimodal data fusion acros s SAM\, X-ray laminography\, optical microscopy\, and CT establishes riche r defect detection and cross-validation. Central to this effort is the cre ation of multimodality benchmark datasets built on standardized acquisitio n protocols\, structured metadata schemas\, and annotation pipelines. Thes e datasets provide not only a foundation for AI model training but also en able reproducibility\, traceability\, and interoperability across future p rograms.</p> END:VEVENT END:VCALENDAR