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:292@escience.washington.edu DTSTART;TZID=America/Los_Angeles:20251028T163000 DTEND;TZID=America/Los_Angeles:20251028T172000 DTSTAMP:20251021T210648Z URL:https://escience.washington.edu/events/uw-data-science-seminar-amelia- keyser-gibson-and-will-von-geldernon/ SUMMARY:UW Data Science Seminar: Amelia Keyser-Gibson and Will von Gelderno n DESCRIPTION:Please join us for a UW Data Science Seminar featuring Amelia K eyser-Gibson and Will von Geldernon Tuesday\, October 21st from 4:30 to 5: 20 p.m. PT. The seminar will be held in IEB G109.\n\n \;\n"Thermal Ana lysis of Climate Ready Vines"\nAbstract: The Climate Ready Vines project is a multi-state collaborative research effort to evaluate and monitor pot ential energy saving\, water use\, ecological\, physiological and horticul tural characteristics of vine plants across different climates and latitud es in the Western U.S. Vine taxa with differing growing habits\, performan ce\, rate of growth and leaf morphology have been selected and assigned on e of four irrigation deficit treatments based on reference evapotranspirat ion\, soil and weather conditions. Plants in urban landscapes fulfill impo rtant ecosystem services such as shading and cooling buildings\, and other infrastructure. Experimental plants are grown on standardized trellises a nd receive one year of establishment irrigation followed by two years of d eficit irrigation. Thermal imagery is collected monthly following the init iation of irrigation treatments to quantify leaf temperature across taxa\, irrigation treatment and site. We are currently developing a convolutiona l neural network model for the extraction of temperature data correspondin g to plant material to allow for evaluation of if the amount of irrigation has significant implications for vine cooling potential and use to make t axa and irrigation recommendations.\n\n \;\n\nBiography: Amelia is a P hD student in the School of Environmental and Forest Sciences interested i n how plants and ecosystems are and will be impacted by climate change. He r current research project investigates plant acclimation to decreased wat er availability\, shifts in performance across a growing season and betwee n plant types by measuring physiological traits across a climatic gradient . Broadly\, she hopes to understand more about how the variation and diver sity across the plant kingdom influences ability to acclimate (and long te rm\, adapt) to stressors from changing environmental conditions.\n\n \ ;\n\n"Using Retrieval-Augmented Generation to Analyze Evictions"\nAbstract : I will present preliminary results from a project that uses computer vis ion and natural language processing to document tenant responses to evicti on summonses and connect tenants' response patterns to subsequent case out comes. As a part of the eScience Institute's Data Science and AI Accelerat or\, I worked with eScience Data Scientist Curtis Atkisson to measure tena nt behavior and case outcomes using text extracted from ~195\,000 pdf docu ments from ~8\,500 eviction cases in Pierce County\, WA filed between 2022 and 2024. Using retrieval-augmented generation (RAG) including LLM analys is\, we documented the links between tenants' submission of written respon ses\, attendance at show cause hearings\, and access to legal assistance f rom Washington's right to counsel (RTC) program. This novel data also allo ws us to examine the relationship between legal representation and case ou tcomes. Results show that legal representation is provided to less than 50 % of tenant households facing an eviction despite the broad eligibility cr iteria in Washington's RTC program. Our findings also highlight the import ance of several critical "administrative checkpoints" during eviction case s and suggest possible reforms that could increase tenants' access to lega l representation.\n\n \;\n\nBiography: Will von Geldern (he/him) is a PhD candidate at the UW Evans School of Public Policy & Governance. He use s mixed methods to examine the effects of public policies and legal system s on the health and wellbeing of marginalized communities. His dissertatio n uses qualitative analysis\, data science\, and experimental methods to s tudy the barriers that prevent tenants from accessing legal assistance dur ing evictions.\n\n \;\nThe 2025-2026 seminars will be held in person\, and are free and open to the public. ATTACH;FMTTYPE=image/jpeg:https://escience.washington.edu/wp-content/uploa ds/2025/10/Seminar_10.28.jpg END:VEVENT BEGIN:VTIMEZONE TZID:America/Los_Angeles X-LIC-LOCATION:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 TZNAME:PDT END:DAYLIGHT END:VTIMEZONE END:VCALENDAR