BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:America/New_York X-WR-TIMEZONE:America/New_York BEGIN:VEVENT UID:0-7697@eng.ufl.edu DTSTART;TZID=America/New_York:20250924T125000 DTEND;TZID=America/New_York:20250924T134000 DTSTAMP:20250829T154855Z URL:https://www.eng.ufl.edu/news-events/events/ees-seminar-leveraging-mach ine-learning-for-floodplain-wetland-identification-e-white-stanford/ SUMMARY:EES Seminar: Leveraging Machine Learning for Floodplain Wetland Ide ntification\, E. White\, Stanford DESCRIPTION:Coastal freshwater floodplain wetlands (CFFWs) are a critical c omponent of the coastal wetland mosaic and offer numerous ecosystem servic es (i.e. carbon sequestration\, storm surge attenuation\, groundwater rech arge)\, however they face an existential threat due to coastal climate cha nge (i.e. sea level rise\, storm surge\, hurricanes). Previous research do cumented nearly 14\,000 km of CFFWs loss in the North American Coastal Pla in from 1996 – 2016 with more than 75% being explained by climate and to pographic variables. However\, there are critical information gaps regardi ng the location of and habitat suitability for CFFWs. We leveraged publicl y available datasets with advances in machine learning to create the first maps of CFFW extent and climate integrated habitat suitability for the co ntiguous United States. Both maps used the NOAA Coastal Change Analysis Pr ogram 2016 palustrine forested wetland class as the locations for training data with the extent map using Landsat for optical imagery. Our extent ma p is based on a convolutional neural network with Inception-ResNet-V2 arch itecture best identifies large features (83% overall accuracy\, 0.66 F1- S core\, 0.54 Kappa Value) with most of the locations being in river valleys or protected areas. The random forest-based habitat suitability integrate s 2050 climate data and projected sea level rise with additional environme ntal data (e.g. physiography\, hydrology\, and hydrography) to predict whe re CFFWs can exist in the near future (86% overall accuracy\, 0.86 F1 Scor e\, and0.52 Kappa Value). These new maps are being put directly into actio n by being used to identify carbon credit opportunities to support small l andowners. Additionally\, our maps can be updated quickly as new data are made available\, which exceeds the current standard that is updated on a 5 -year basis. The temporally dynamic nature of our approach allows for rapi d assessment of CFFW change for acute events and should help constrain lon g-term estimates of change.\n\nElliott White Jr. is an Assistant Professor of Earth System Science in the Stanford Doerr School of Sustainability. H e is a coastal ecosystem scientist who leverages his domain expertise in w etland sciences with interdisciplinary training in remote sensing and ecoh ydrology to investigate climate change related challenges on coastal socio -environmental systems (cSES). Elliott has research on all three US coasts and has expanded internationally to include Bolivia\, The Gambia\, and Ca nada. Collaborators in his research include academics\, non-profits\, comm unity-based organizations\, and municipal departments. At Stanford\, he is an affiliate of the Center for Comparative Studies on Race and Ethnicity and a Center Fellow\, by courtesy\, of the Woods Institute for the Environ ment. Elliott has a PhD in Environmental Engineering Sciences from the Uni versity of Florida (2019) and a BS in Biology and Animal Ecology from Iowa State University (2015). CATEGORIES:Seminars LOCATION:Room 100\, Engineering Building (NEB)\, 1064 Center Drive\, Gaines ville\, Florida\, 32611\, United States X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=1064 Center Drive\, Gainesv ille\, Florida\, 32611\, United States;X-APPLE-RADIUS=100;X-TITLE=Room 100 \, Engineering Building (NEB):geo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 TZNAME:EDT END:DAYLIGHT END:VTIMEZONE END:VCALENDAR