BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.4.5//EN TZID:America/Los_Angeles X-WR-TIMEZONE:America/Los_Angeles BEGIN:VEVENT UID:268@escience.washington.edu DTSTART;TZID=America/Los_Angeles:20250507T163000 DTEND;TZID=America/Los_Angeles:20250507T172000 DTSTAMP:20250422T183711Z URL:https://escience.washington.edu/events/uw-data-science-seminar-ben-mak hlouf-and-masha-vernik/ SUMMARY:UW Data Science Seminar: Ben Makhlouf and Masha Vernik DESCRIPTION:Please join us for a UW Data Science Seminar featuring UW Aquat ic and Fisheries PhD student Ben Makhlouf and UW Environmental and Forest Sciences Masters student Masha Vernik on Wednesday\, May 7th from 4:30 to 5:20 p.m. PT. This seminar will feature two different research projects s upported by the eScience Data Science and AI Accelerator. \n\n\nThe semina r will be held in Electrical and Computer Engineering Building 125 – Ca mpus Map.\n"Developing machine learning models alongside multi-source biol ogical data to conserve Alaska Salmon"\n\nAbstract: Pacific salmon are vi tal to Alaskan communities\, serving as a key cultural\, subsistence\, and economic resource. However\, Chinook salmon populations in Western Alaska have declined sharply in recent years. While many hypotheses suggest mari ne mortality as a key factor\, identifying the specific origins of fish ca ught in the open ocean has been a challenge\, limiting the ability of rese archers to explore hypothesis which may provide valuable insight into the causal mechanisms of recent declines and potential adaptation strategies t o mitigate it. Isotopic markers in otoliths (ear stones) of pacific salmon offer a promising for estimating the location of origin for migratory fis hes. These structures grow sequentially over the lifetime of the individua l\, continually recording a sequential record of experienced isotopic valu es into a timeseries of experienced isotope values. By isolating a discret e value from this timeseries which corresponds to a period of interest (e. g. juvenile rearing)\, researchers can relate this ratio to those modeled across the landscape to provide a precise estimate of provenance. While th is method works well at relatively small spatial scales (within watershed) \, redundancy in isotope ratios at large spatial scales often fail to esti mate precise locations using a single discrete value.\n\nWhat has been rel atively unexplored is whether the full timeseries of otolith data from the lifespan of an individual can overcome this limitation to estimate the lo cation of origin. Because of the complex isotopic makeup of dendritic rive r systems\, the full timeseries may constrain patterns which indicate wate rshed specific migration pathways. Further\, the otolith shape itself may contain patterns which\, when combined\, aid in identifying the river-of-o rigin.\n\nHere\, we apply machine learning models to otolith timeseries da ta along with shape analysis using fourier transformations to explore the potential of building a model to distinguish river of origin in ocean-caug ht salmon. Preliminary analysis suggests otolith timeseries data\, when de ployed in Machine learning models such as Random Forest\, may be able to c orrectly classify >75% of individuals. In addition\, otolith shape analysi s shows promise to further improve on this classification accuracy\, parti cularly when both approaches are combined. If successful\, a working model which can be deployed in Alaskan fisheries to test valuable hypotheses am id an ongoing crisis. In addition\, this project highlights the potential of deploying machine learning and data science techniques alongside ecolog ical data and integrating multiple data sources and modeling approaches.\n \n\n Biography: Ben Makhlouf is a graduate student in the school of Aqua tic and Fisheries sciences researching the spatial ecology of Pacific Salm on in Western Alaska. Namely\, Ben is interested in developing and deployi ng new tools to address pressing conservation and research needs in the re gion by combining ecological datasets alongside emerging data science tool s. Before graduate school\, he worked for several years helping to run a f ield camp in southwest Alaska to help monitor salmon ecosystems.\n\n\n"Bay esian Modeling to Understand Climate Adaptation Among Organic Farmers in t he U.S."\n\nAbstract: As seasons become less predictable and extreme weat her events become more frequent and intense\, farmers learn to adapt. Howe ver\, context-specific constraints may differentiate the extent to which d ifferent farmers facing the same environmental exposures are able to adapt . Specifically\, results from a qualitative study with organic farmers in western Washington revealed that farmers with insecure land tenure are unl ikely to make infrastructure investments necessary to adapt to changing co nditions. This talk features preliminary results from a Bayesian approach to modeling the effect of land access on perceived adaptive capacity to cl imate change among organic farmers in the United States. The model is base d on survey data collected by the Organic Seed Alliance and Organic Farmin g Research Foundation integrated with meteorological data measuring drough t\, temperature extremes\, and climatic variability. The talk addresses ho w to incorporate results from qualitative studies into quantitative modeli ng approaches through variable and prior selection\, offering insight into mixed-method studies. \n\n Biography: Masha Vernik is a graduate studen t at the University of Washington’s School of Environmental and Forest S ciences. She studies the factors that influence how farmers are adapting t o climate change and is especially interested in the role of seed diversit y in climate resilience. She employs qualitative and quantitative methods that include conducting interviews\, evaluating survey data\, and analyzin g satellite imagery. Her learning extends beyond the classroom and into th e field as an avid gardener and part-time farmworker. Before graduate scho ol\, she did communications at FarmStand\, a legal advocacy organization f ocused on building a more just food system. She graduated from Boston Univ ersity in 2019 with a B.A. in International Relations and a minor in Biolo gy.\n\n\nThe 2024-2025 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/2025/04/SeminarPhotos_mashaben.png 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