College of LAS Events

View Full Calendar

If you will need disability-related accommodations in order to participate, please email the contact person for the event.
Early requests are strongly encouraged to allow sufficient time to meet your access needs.

Automated Geospatial Analysis of Watershed Characteristics to Evaluate Reservoir Sedimentation

Event Type
Seminar/Symposium
Sponsor
Department of Geography & GIS
Location
Lecture Hall 2079 Natural History Buildubg
Date
Oct 29, 2021   3:00 - 4:00 pm  
Speaker
Dr. Amanda Cox, Civil Engineering, Saint Louis University
Cost
This event is free and open to public
Contact
Department of Geography & GIS
E-Mail
geography@illinois.edu
Views
11
Originating Calendar
Geography and Geographic Information Science

Reservoirs are vital components of our nation’s water-resources infrastructure; however, many reservoirs across the nation are slowly being filled with sediment, which reduces their effectiveness, increases maintenance costs, and compromises dam safety. The U.S. Army Corps of Engineers (USACE) has developed the Reservoir Sedimentation Information (RSI) database to help evaluate reservoir aggradation trends, life expectancy, and vulnerabilities to climate change. The objectives of this study are to 1) develop machine learning algorithms to estimate reservoir sedimentation rates using the RSI data coupled and supplementary data and 2) develop methods to identify anomalous data within the RSI system using machine learning algorithms. A composite dataset (RSI and supplemental data) was developed using data from 184 reservoirs and 642 surveys.  Several watershed and reservoir parameters that affect reservoir sedimentation (e.g., watershed area and cumulative precipitation between surveys) were identified and quantified. Due to the large number of reservoirs and reservoir surveys several automated geospatial analysis methods were developed and employed.  This presentation will focus on the automated geospatial analyses, initial statistical trends observed in the composite dataset, and current machine learning activities. 

link for robots only