BEGIN:VCALENDAR METHOD:REQUEST PRODID:Microsoft Exchange Server 2010 VERSION:2.0 BEGIN:VTIMEZONE TZID:Eastern Standard Time BEGIN:STANDARD DTSTART:16010101T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=11 END:STANDARD BEGIN:DAYLIGHT DTSTART:16010101T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=2SU;BYMONTH=3 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT ORGANIZER;CN=Michael McDonald:mailto:michael.mcdonald@fsu.edu DESCRIPTION;LANGUAGE=en-US:"Conservative cell-average-based neural network method for nonlinear conservation laws"\n\nJue Yan\nDepartment of Mathemat ics\nIowa State University\n\nPlease feel free to forward/share this invit ation with other groups/disciplines that might be interested in this talk/ topic. All are welcome to attend.\n\nNOTE: In-person attendance is request ed in our 499 Dirac Science Library (DSL) Seminar Room. Zoom access is int ended for external (non-departmental) participants only.\n\n\nhttps://fsu. zoom.us/j/94273595552\nMeeting # 942 7359 5552\n\n\nšŸŽ¦ Colloquium record ings will be made available here\, https://www.sc.fsu.edu/colloquium\n\n\nWed nesday\, Apr 1\, 2026\, Schedule:\n\n* 3:00 to 3:30 PM Eastern Time (US an d Canada)\nā˜• Nespresso & Teatime - 417 DSL Commons\n\n* 3:30 to 4:30 PM Eastern Time (US and Canada)\nšŸ•Ÿ Colloquium - 499 DSL Seminar Room\n\n\n Abstract:\nIn this talk\, we present the recently developed Cell-Average-B ased Neural Network (CANN) for time-dependent PDEs. Spatial and temporal d iscretization in conventional methods is replaced by training a simple fee dforward network to obtain an explicit one-step finite volume method. The well-trained network parameters function as the scheme coefficients. The n etwork method has a minimum number of unknowns\, which can be quickly trai ned on a small training dataset. Unlike conventional numerical methods\, t he CANN approach is not limited by the CFL conditions\, enabling the use o f significantly larger time steps. This leads to a highly efficient comput ational method for solving PDEs. The conservative version of the CANN meth od for nonlinear conservation laws will be discussed. The method\, trained on the smooth-solution data from ONE initial-value problem\, is verified to solve any initial-value problem involving shocks and rarefaction waves. The network can accurately learn a numerical flux\, such as the Lax-Fried richs flux\, thereby guaranteeing convergence to the physically relevant e ntropy solutions. The extension of the method to non-uniform meshes will b e considered. A bound-preserving version of the network method is presente d for linear Advection equations.\n\n\nAdditional colloquium details can b e found here.\nhttps://www.sc.fsu.edu/news-and-events/colloquium/1915-coll oquium-with-jue-yan-2026-04-01\n UID:040000008200E00074C5B7101A82E008000000005E5A00F99FBFDC01000000000000000 010000000DE7168C7E203B34B9D113F51AA9C6C12 SUMMARY;LANGUAGE=en-US:Scientific Computing Colloquium with Jue Yan DTSTART;TZID=Eastern Standard Time:20260401T153000 DTEND;TZID=Eastern Standard Time:20260401T162500 CLASS:PUBLIC PRIORITY:5 DTSTAMP:20260329T171752Z TRANSP:OPAQUE STATUS:CONFIRMED SEQUENCE:0 LOCATION;LANGUAGE=en-US:https://fsu.zoom.us/j/94273595552 X-MICROSOFT-CDO-APPT-SEQUENCE:0 X-MICROSOFT-CDO-OWNERAPPTID:2124672862 X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY X-MICROSOFT-CDO-ALLDAYEVENT:FALSE X-MICROSOFT-CDO-IMPORTANCE:1 X-MICROSOFT-CDO-INSTTYPE:0 X-MICROSOFT-DONOTFORWARDMEETING:FALSE X-MICROSOFT-DISALLOW-COUNTER:FALSE X-MICROSOFT-REQUESTEDATTENDANCEMODE:DEFAULT X-MICROSOFT-ISRESPONSEREQUESTED:FALSE X-MICROSOFT-LOCATIONDISPLAYNAME:https://fsu.zoom.us/j/94273595552 X-MICROSOFT-LOCATIONSOURCE:None X-MICROSOFT-LOCATIONS:[{"DisplayName":"https://fsu.zoom.us/j/94273595552"\, "LocationAnnotation":""\,"LocationUri":""\,"LocationStreet":""\,"LocationC ity":""\,"LocationState":""\,"LocationCountry":""\,"LocationPostalCode":"" \,"LocationFullAddress":""}] BEGIN:VALARM DESCRIPTION:REMINDER TRIGGER;RELATED=START:-PT5M ACTION:DISPLAY END:VALARM END:VEVENT END:VCALENDAR