Ask a Librarian

Threre are lots of ways to contact a librarian. Choose what works best for you.

HOURS TODAY

10:00 am - 4:00 pm

Reference Desk

CONTACT US BY PHONE

(802) 656-2022

Voice

(802) 503-1703

Text

MAKE AN APPOINTMENT OR EMAIL A QUESTION

Schedule an Appointment

Meet with a librarian or subject specialist for in-depth help.

Email a Librarian

Submit a question for reply by e-mail.

WANT TO TALK TO SOMEONE RIGHT AWAY?

Library Hours for Thursday, November 21st

All of the hours for today can be found below. We look forward to seeing you in the library.
HOURS TODAY
8:00 am - 12:00 am
MAIN LIBRARY

SEE ALL LIBRARY HOURS
WITHIN HOWE LIBRARY

MapsM-Th by appointment, email govdocs@uvm.edu

Media Services8:00 am - 7:00 pm

Reference Desk10:00 am - 4:00 pm

OTHER DEPARTMENTS

Special Collections10:00 am - 6:00 pm

Dana Health Sciences Library7:30 am - 11:00 pm

 

CATQuest

Search the UVM Libraries' collections

UVM Theses and Dissertations

Browse by Department
Format:
Print
Author:
Doris, Jeffrey J.
Dept./Program:
Civil and Environmental Engineering
Year:
2006
Degree:
MS
Abstract:
A counterpropagation Artificial Neural Network (ANN) has been applied to three separate problems in civil and environmental engineering: stream reach classification, field site soil shnking/swelling forecasting, and basin-scale erosion rate classification. An ANN is a biologically inspired, flexible mathematical structure that is capable of mapping complex nonlinear relationships between input and output data sets. ANNs are programmed with a variety of architectures that generally have the following attributes in common: the ability to model complex nonlinear behavior, the ability to easily incorporate large and growing data sets, and a parallel computational structure that enables rapid data processing. In contrast to the neural structure of the human brain, with more than 100 billion neurons and trillions of interconnections, the structures of most ANNs are quite simple.
Firstly, stream reach classification is performed with geostatistical-based ANNs to enhance existing geographic information system (GIs)-based watershed management tools for diagnosing geomorphic instability at various sub-basin and watershed scales. Two ANNs have been developed for the classification of reach-scale inherent vulnerability and geomorphic condition and have been tested (in concert with best judgment by experts) using existing data for two Vermont watersheds. These ANNs will support future development of modules to enhance land use management at the watershed scale to better predict geomorphic instability and sediment transport in response to natural and anthropogenic stresses.
Secondly, predictions of vertical ground surface movement from the shrinking and swelling of soils are needed for engineers to prevent or mitigate the estimated $15 billion in damage to infrastructure they cause in the U.S. each year. An ANN system is used to forecast this movement based on site characterization (relevant soil properties in the depth of influence) and climate data (temperature and rainfall); and soil water content data, when available. Analysis was conducted on data sets from field sites in Arlington, Texas (Texas) and near Newcastle, Australia (Australia) to demonstrate several ANN approaches for mapping from climate data to vertical ground surface movement. Lastly, an ANN has been used to classify erosion rates at the basin scale determined from beryllium-10 dating. The ANN uses basin characteristics such as slope, elevation, seismic activity, and precipitation seasonality to the classify erosion rates of basins from regions around the world.