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:230@escience.washington.edu DTSTART:20241009T003000Z DTEND:20241009T012000Z DTSTAMP:20241004T183919Z URL:https://escience.washington.edu/events/uw-data-science-seminar-dssg-2/ SUMMARY:UW Data Science Seminar: Data Science for Social Good (session 2) DESCRIPTION:\n\nPlease join us for a UW Data Science Seminar event on Tues day\, October 8th from 4:30 to 5:20 p.m. PDT. The seminar will feature two projects from this past summer's UW Data Science for Social Good program. \n\nThe seminar will be held in the Physics/Astronomy Auditorium (PAA)\, R oom A118 – campus map.\n\n \;\n\n"Geo-indexing Water Reuse Potentia l...and beyond"\n\nTeam Project Leads: Carolyn Hayek\, Researcher and Tea ching Fellow\, Columbia University\, and Miriam Hacker\, Research Program Manager\, Water Research Foundation\nData Science Mentor: Curtis Atkisson \, eScience Institute\, University of Washington\nStudent Fellows: Daniel Vogler\, Jihyeon Bae\, Mbye Sallah\, Nora Povejsil\n\nAbstract:\n\nCommuni ties around the United States are thinking of alternative water systems to address local water challenges. One example of this is water reuse\, whic h is defined by the Environmental Protection Agency (EPA) as “the practi ce of reclaiming water from a variety of sources\, treating it\, and reusi ng it for beneficial purposes.” The current social problem is that commu nities only see water reuse as an opportunity for areas that are experienc ing water scarcity\, rather than realizing its full potential to address a wide range of water challenges\, like lowering flood risk\, reducing comb ined sewer overflows\, and minimizing the nutrients that are discharged to the environment.\n\nOur project aims to address this social problem by de veloping a framework for quantifying a community’s potential for water r euse based on various motivators—or drivers—to identify whether water reuse could be a local solution that merits further investigation. Using p ublicly available data across the US\, our project looks at the correlatio n between drivers (both presence and intensity) and characterizes the bene fits communities might find by exploring water reuse. Combining complex da ta into an informative index and displaying the results in a clear\, diges tible format will help assess water challenges and needs across the countr y\, as well as support local decision-making.\n\nBeyond the scope of water reuse specifically\, we also allow index-creators across disciplines to s eamlessly create their own indices and web pages using the same generalize d functions that we wrote and used in our process. You can think of our In teractive Water Reuse Website as a case study of an end-to-end index and w ebsite creation tool. The outputs of the project are an interactive web to ol that allows users to map the severity of water reuse drivers across the United States\, a geospatial data processing and conversion pipeline in t he R programming language\, and a general website creation (html file) tem plate and functions.\n\n\n \;\n\n"Measuring Fairness and Equity in Cro wd-Flow Generation Models"\n\nTeam Project Lead: Afra Mashhadi\, Assista nt Professor\, Computer Software and Systems\, University of Washington\, Bothell\, and Ekin Ugurel\, Ph.D. Candidate\, College of Engineering\, Uni versity of Washington\nData Science Mentor: Bernease Herman\, eScience Ins titute\, University of Washington\nStudent Fellows: Apoorva Sheera\, Jiaqi He\, Manurag Khullar\, Sakshi Charvan\n\nAbstract:\n\nGenerative crowd-fl ow models\, which simulate city population movements\, have advanced from physics-based to neural network-based models\, improving performance by in corporating city-specific features. However\, concerns about the equity of these models and the potential social biases brought by the models remain largely unaddressed\, which is critical for government planning\, pandemi c prevention\, and etc. This project aims to develop and implement new fai rness metrics for CF models to ensure equitable representation of each gro ups’ travel demands. The project involves exploring current equity dispa rities among different demographic groups\, reviewing fairness literature\ , engaging with stakeholders\, and creating a Python package to test CF mo dels. LOCATION:Physics/Astronomy Auditorium\, room A118\, Seattle\, WA\, X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Seattle\, WA\, ;X-APPLE-RAD IUS=100;X-TITLE=Physics/Astronomy Auditorium\, room A118:geo:0,0 END:VEVENT END:VCALENDAR