BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260930T131707Z UID:0BD0A925-A22B-4809-9B36-322F612EFD63 DTSTART;TZID=America/New_York:20260924T173000 DTEND;TZID=America/New_York:20260924T203000 DESCRIPTION:iMAPS New England\nAnnouncement of Chapter Business Meeting & E lection of Officers\nin collaboration with IEEE Microsystems & SMTA Boston Chapters\n\n“AI and Digital Twins for Microelectronics and Flexible Hyb rid Electronics:\nDesign\, Manufacturing\, and Testing “\nPresenter: Ben yamin Davaji\, Northeastern University\nDesign and manufacturing optimizat ion in microelectronics and flexible hybrid\nelectronics (FHE) still relie s heavily on costly\, time-consuming trial-and-error\nexperimentation. We ’ll introduce a physics-informed AI digital twin that predicts\ndevice s tructure and electrical performance directly from fabrication parameters\, \nenabling virtual process development before fabrication. The framework\n combines deep learning with physics-informed neural networks (PINNs) that\ nembed process-specific governing physics\, improving accuracy\, interpret ability\,\nand generalization across recipes\, materials\, and substrates. Validated on DUV\nphotolithography\, plasma etching\, and printed FHE pro cesses\, the models predict geometry\,\nmaterial properties\, conductivity \, and frequency response using quantitative metrology data.\nDesigned for bidirectional integration with EDA and TCAD workflows\, the digital twin can be\ninverted to identify fabrication recipes that meet target device s pecifications while prioritizing the\nmost informative experiments. The ap proach reduces development cycles and process exploration\ncosts\, enablin g a transition from empirical optimization to physics-guided\, AI-driven d esign\,\nmanufacturing\, and testing.\n\nCo-sponsored by: iMAPS New Englan d\n\nSpeaker(s): \, Ben\n\nAgenda: \n5:30 PM Registration\, Socializing\, Networking\, Casual Dinner\n6:45 PM Matt Bracy\, President - Chapter Busin ess Meeting - Introduction of Chapter Elections\n7:00 PM Dmitry Marchenko\ , Nominating Committee Chair - Election of Chapter Officers\nThe Chapter N ominating Committee Submits the following Candidates for Chapter Office fo r 2027:\nPresident: Richard Koba - Onto Technologies\nVice President: Sunn y Agarwal\, ITW EAE\nTreasurer: Michael Curley - TTM Technologies\n7:15 PM Matt Bracy\, President - Adjourn Business Meeting & Introduction of Prese ntation\n\nNew England Die Company\, 96 Milk St\, Methuen\, Massachusetts\ , United States\, 01844 LOCATION:New England Die Company\, 96 Milk St\, Methuen\, Massachusetts\, U nited States\, 01844 ORGANIZER:sbart@ieee.org SEQUENCE:17 SUMMARY:iMAPS New England Chapter Meeting in collaboration with IEEE Micros ystems & SMTA Boston Chapters URL;VALUE=URI:https://events.vtools.ieee.org/m/578899 X-ALT-DESC:Description: <br /><p>iMAPS New England<br>Announcement of Chapt er Business Meeting &amp\; Election of Officers<br>in collaboration with I EEE Microsystems &amp\; SMTA Boston Chapters</p>\n<p>&ldquo\;AI and Digita l Twins for Microelectronics and Flexible Hybrid Electronics:<br>Design\, Manufacturing\, and Testing &ldquo\;<br>Presenter: Benyamin Davaji\, North eastern University<br>Design and manufacturing optimization in microelectr onics and flexible hybrid<br>electronics (FHE) still relies heavily on cos tly\, time-consuming trial-and-error<br>experimentation. We&rsquo\;ll intr oduce a physics-informed AI digital twin that predicts<br>device structure and electrical performance directly from fabrication parameters\,<br>enab ling virtual process development before fabrication. The framework<br>comb ines deep learning with physics-informed neural networks (PINNs) that<br>e mbed process-specific governing physics\, improving accuracy\, interpretab ility\,<br>and generalization across recipes\, materials\, and substrates. Validated on DUV<br>photolithography\, plasma etching\, and printed FHE p rocesses\, the models predict geometry\,<br>material properties\, conducti vity\, and frequency response using quantitative metrology data.<br>Design ed for bidirectional integration with EDA and TCAD workflows\, the digital twin can be<br>inverted to identify fabrication recipes that meet target device specifications while prioritizing the<br>most informative experimen ts. The approach reduces development cycles and process exploration<br>cos ts\, enabling a transition from empirical optimization to physics-guided\, AI-driven design\,<br>manufacturing\, and testing.</p><br /><br />Agenda: <br /><p>5:30 PM Registration\, Socializing\, Networking\, Casual Dinner< br>6:45 PM Matt Bracy\, President - Chapter Business Meeting - Introductio n of Chapter Elections<br>7:00 PM Dmitry Marchenko\, Nominating Committee Chair - Election of Chapter Officers<br>The Chapter Nominating Committee S ubmits the following Candidates for Chapter Office for 2027:<br>President: Richard Koba - Onto Technologies<br>Vice President: Sunny Agarwal\, ITW E AE<br>Treasurer: Michael Curley - TTM Technologies<br>7:15 PM Matt Bracy\, President - Adjourn Business Meeting &amp\; Introduction of Presentation< /p> END:VEVENT END:VCALENDAR