BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:America/Los_Angeles X-WR-TIMEZONE:America/Los_Angeles BEGIN:VEVENT UID:91@escience.washington.edu DTSTART;TZID=America/Los_Angeles:20240528T100000 DTEND;TZID=America/Los_Angeles:20240528T110000 DTSTAMP:20240523T204231Z URL:https://escience.washington.edu/events/guest-seminar-chaopeng-shen/ SUMMARY:Guest Seminar: Chaopeng Shen\, Pennsylvania State University DESCRIPTION:Please join us for a special guest seminar by Dr. Chaopeng Shen \, Professor in Civil Engineering at The Pennsylvania State University\, i n the WRF Data Science Studio Seminar Room or online via zoom\, https://wa shington.zoom.us/j/97451365866.\n"Differentiable modeling and the Genes of AI for Water and Global sustainability" \nAbstract. Big data and artific ial intelligence (AI) methods are revolutionizing how knowledge is gained and predictions are made for sustainability sciences and the global enviro nment. AI methods\, especially deep networks\, have strong predictive skil ls yet are limited in interpretability and cannot alone answer specific sc ientific questions. Here we argue that the genes of AI\, meaning its most transformative core ideas bringing forth favorable traits\, can be absorbe d into traditional modeling domains to give us new ways of making inquirie s. For example\, a genre of physics-informed machine learning\, called “ differentiable” modeling (DM\, https://t.co/qyuAzYPA6Y)\, trains neural networks (NNs) with process-based equations (priors) together in one stag e (called “end-to-end”) to benefit from the best aspects of both parad igms. DM can produce state-of-the-art predictions\, inherently enable phys ical interpretation\, extrapolate well in space and time\, and leverage ef ficient AI computing infrastructure. We demonstrate the power of DM in hyd rologic\, river flow &\; transport\, ecosystem\, and water quality mode ling\, and use it to learn robust scientific answers from big data. As ano ther example of AI “genes”\, generative AI can capture the conditional joint distribution of multiple variables\, depositing knowledge from all forms of observations and informing on scarcely observed processes - thus it can be leveraged to capture the coevolution of environmental variables. Tools with AI genes can serve as the basic infrastructure that democratiz es access to reliable predictions and gives wings to solutions for some of the most elusive and important environmental modeling problems.\n\nBio: C haopeng Shen is Professor in Civil Engineering at The Pennsylvania State U niversity. He received the Ph.D. degree in environmental engineering from Michigan State University\, East Lansing\, MI\, USA\, in 2009. His PhD res earch focused on computational hydrology and he developed the hydrologic m odel Process-based Adaptive Watershed Simulator(PAWS)\, which was later co upled to the community land model to study the interactions between hydrol ogy and ecosystem. He was a Post-Doctoral Research Associate with the Lawr ence Berkeley National Laboratory\, Berkeley\, CA\, USA\, from 2011 to 201 2\, working on high-performance computational geophysics. His recent effor ts focused on harnessing the big data and machine learning (ML) and physic s-informed ML opportunities in advancing hydrologic predictions and unders tanding. As an early advocate for ML in geosciences\, he has written techn ical\, editorial\, review and collective opinion papers on hydrologic deep learning to call to attention the emerging opportunities for scientific a dvances. He currently promotes differentiable modeling which seamlessly i ntegrates neural networks and physics for knowledge discovery. In additi on\, his research interests also include floodplain systems\, scaling issu es\, process-based hydrologic modeling\, and hydrologic data mining. He is currently Editor of Journal of Geophysical Research - Machine Learning & amp\; Computation\, an Associate Editor of the Water Resources Research  and Chief Special Editor for Frontiers in AI: Water and AI.\nThe Universi ty of Washington is committed to providing access\, equal opportunity and reasonable accommodation in its services\, programs\, activities\, educati on and employment for individuals with disabilities. To request disability accommodation contact the Disability Services Office at least ten days in advance at: 206.543.6450/V\, 206.543.6452/TTY\, 206.685.7264 (FAX)\, or e -mail at dso@uw.edu LOCATION:WRF Data Science Studio Seminar Room\, Seattle\, WA\, 98195\, X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Seattle\, WA\, 98195\, ;X-A PPLE-RADIUS=100;X-TITLE=WRF Data Science Studio Seminar Room:geo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:America/Los_Angeles X-LIC-LOCATION:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 TZNAME:PDT END:DAYLIGHT END:VTIMEZONE END:VCALENDAR