BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Australia/Canberra BEGIN:DAYLIGHT DTSTART:20261004T030000 TZOFFSETFROM:+1000 TZOFFSETTO:+1100 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=10 TZNAME:AEDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20260405T020000 TZOFFSETFROM:+1100 TZOFFSETTO:+1000 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4 TZNAME:AEST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260626T022553Z UID:DE7916F8-38D2-4609-82F6-8D73BE34C9C1 DTSTART;TZID=Australia/Canberra:20260724T110000 DTEND;TZID=Australia/Canberra:20260725T120000 DESCRIPTION:Title:\n\nSpatiotemporal Learning for Urban Mobility and Exasca le Climate Emulation\n\nAbstract:\n\nThe proliferation of sensing modaliti es\, together with advances in machine learning and high-performance compu ting\, has opened new methodological questions at the intersection of sign al processing and large-scale modelling of complex physical and social sys tems. In this talk\, I will present recent work spanning urban mobility an d climate modelling. I will first discuss STEF-DHNet\, a spatiotemporal mo del for ride-hailing demand that combines convolutional and recurrent comp onents with exogenous signals\, and the Variational Mode Graph Convolution al Network\, which couples variational mode decomposition with graph neura l networks for interpretable traffic forecasting. I will then turn to our exascale climate emulator\, which combines spherical harmonic transforms w ith mixed-precision GPU computation to achieve high-fidelity climate model ling at unprecedented scale. I will close with reflections on the methodol ogical themes that recur across these problems\, including interpretabilit y\, multi-scale decomposition\, and the trade-offs between physical struct ure and learned representations.\n\nBio:\n\nDr. Zubair Khalid is an Associ ate Professor in the Department of Electrical Engineering and the Director of the Centre for Urban Informatics\, Technology\, and Policy (CITY) at t he Lahore University of Management Sciences (LUMS). His research sits at t he intersection of artificial intelligence\, climate science\, and sustain able urban development\, and centres on co developing decision support sys tems with city governments\, multilateral organisations\, and academic ins titutions to address challenges in urban mobility\, air quality\, and clim ate resilience. His broader interests include machine learning\, computer vision\, remote sensing\, and advanced signal processing\, with applicatio ns across cosmology\, medical imaging\, and urban systems. He received his Ph.D. from the Australian National University\, is a Senior Member of IEE E\, has served as an Associate Editor for IEEE Signal Processing Letters\, and is a recipient of the 2024 ACM Gordon Bell Prize. Further information is available at [www.zubairkhalid.org](http://www.zubairkhalid.org/) and [http://city.lums.edu.pk](http://city.lums.edu.pk/) and [ANU researchers w in Gordon Bell Prize for record-breaking algorithm | Research](https://res earch.anu.edu.au/research-innovation-news/anu-researchers-win-gordon-bell- prize-for-record-breaking-algorithm)\n\nRoom: 2.04\, Bldg: Birch Building - Seminar Room \, The Australian National University\, 35 Science Road\, A cton\, Australian Capital Territory\, Australia\, 2601\, Virtual: https:// events.vtools.ieee.org/m/565252 LOCATION:Room: 2.04\, Bldg: Birch Building - Seminar Room \, The Australian National University\, 35 Science Road\, Acton\, Australian Capital Territ ory\, Australia\, 2601\, Virtual: https://events.vtools.ieee.org/m/565252 ORGANIZER:Ambarish.natu@gmail.com SEQUENCE:9 SUMMARY:Spatiotemporal Learning for Urban Mobility and Exascale Climate Emu lation URL;VALUE=URI:https://events.vtools.ieee.org/m/565252 X-ALT-DESC:Description: <br /><p class="MsoNormal"><strong><span lang="EN-G B" data-removefontsize="true" data-originalcomputedfontsize="16">Title:</s pan></strong></p>\n<p class="MsoNormal"><span lang="EN-GB" data-removefont size="true" data-originalcomputedfontsize="16">Spatiotemporal Learning for Urban Mobility and Exascale Climate Emulation</span></p>\n<p class="MsoNo rmal"><span lang="EN-GB">&nbsp\;</span></p>\n<p class="MsoNormal"><strong> <span lang="EN-GB" data-removefontsize="true" data-originalcomputedfontsiz e="16">Abstract:</span></strong></p>\n<p class="MsoNormal" data-removefont size="true" data-originalcomputedfontsize="16">The proliferation of sensin g modalities\, together with advances in machine learning and high-perform ance computing\, has opened new methodological questions at the intersecti on of signal processing and large-scale modelling of complex physical and social systems. In this talk\, I will present recent work spanning urban m obility and climate modelling. I will first discuss STEF-DHNet\, a spatiot emporal model for ride-hailing demand that combines convolutional and recu rrent components with exogenous signals\, and the Variational Mode Graph C onvolutional Network\, which couples variational mode decomposition with g raph neural networks for interpretable traffic forecasting. I will then tu rn to our exascale climate emulator\, which combines spherical harmonic tr ansforms with mixed-precision GPU computation to achieve high-fidelity cli mate modelling at unprecedented scale. I will close with reflections on th e methodological themes that recur across these problems\, including inter pretability\, multi-scale decomposition\, and the trade-offs between physi cal structure and learned representations.</p>\n<p class="MsoNormal">&nbsp \;</p>\n<p class="MsoNormal"><strong><span lang="EN-US" data-removefontsiz e="true" data-originalcomputedfontsize="16">Bio:</span></strong></p>\n<p c lass="MsoNormal"><span lang="EN-US" data-removefontsize="true" data-origin alcomputedfontsize="16">Dr. Zubair Khalid is an Associate Professor in the Department of Electrical Engineering and the Director of the Centre for U rban Informatics\, Technology\, and Policy (CITY) at the Lahore University of Management Sciences (LUMS). His research sits at the intersection of a rtificial intelligence\, climate science\, and sustainable urban developme nt\, and centres on co developing decision support systems with city gover nments\, multilateral organisations\, and academic institutions to address challenges in urban mobility\, air quality\, and climate resilience. His broader interests include machine learning\, computer vision\, remote sens ing\, and advanced signal processing\, with applications across cosmology\ , medical imaging\, and urban systems. He received his Ph.D. from the Aust ralian National University\, is a Senior Member of IEEE\, has served as an Associate Editor for IEEE Signal Processing Letters\, and is a recipient of the 2024 ACM Gordon Bell Prize. Further information is available at <a href="http://www.zubairkhalid.org/" target="_blank" rel="noopener" data-sa feredirecturl="https://www.google.com/url?q=http://www.zubairkhalid.org/&a mp\;source=gmail&amp\;ust=1782518704106000&amp\;usg=AOvVaw0CKg4bxZqV5bixna QyX9Bb" data-removefontsize="true" data-originalcomputedfontsize="16">www. zubairkhalid.org</a> and <a href="http://city.lums.edu.pk/" target="_blank " rel="noopener" data-saferedirecturl="https://www.google.com/url?q=http:/ /city.lums.edu.pk/&amp\;source=gmail&amp\;ust=1782518704106000&amp\;usg=AO vVaw3AGkdDcWN-otxogoIcrFAT" data-removefontsize="true" data-originalcomput edfontsize="16">http://city.lums.edu.pk</a> and </span><a href="https://re search.anu.edu.au/research-innovation-news/anu-researchers-win-gordon-bell -prize-for-record-breaking-algorithm" target="_blank" rel="noopener" data- saferedirecturl="https://www.google.com/url?q=https://research.anu.edu.au/ research-innovation-news/anu-researchers-win-gordon-bell-prize-for-record- breaking-algorithm&amp\;source=gmail&amp\;ust=1782518704106000&amp\;usg=AO vVaw1v0OQOptAoJ69k1mrnJA1_" data-removefontsize="true" data-originalcomput edfontsize="16">ANU researchers win Gordon Bell Prize for record-breaking algorithm | Research</a></p> END:VEVENT END:VCALENDAR