HR: 1340h
AN: H23A-1126 [Abstracts]
TI: Estimating Vertical Surface Movement using Artificial Neural Networks
AU: Doris, J J
EM: jdoris@emba.uvm.edu
AF: University of Vermont, 213 Votey Bldg, Burlington, VT 05405
United States
AU: * Rizzo, D M
EM: drizzo@emba.uvm.edu
AF: University of Vermont, 213 Votey Bldg, Burlington, VT 05405
United States
AU: Dewoolkar, M
EM: mandar@emba.uvm.edu
AF: University of Vermont, 213 Votey Bldg, Burlington, VT 05405
United States
AB:
Artificial Neural Networks (ANNs) are used to predict vertical surface movement when soils expand and contract with changes
in soil moisture caused by climatic conditions. Temperature and rainfall data, soil property data, and soil moisture
measurements are used for training ANNs to simulate the movement of spread footings at a field site in Arlington, Texas. A
research team from Texas A&M University surveyed the footing movement monthly over a two-year period. The performance of the
ANNs is evaluated by comparing the predictions to the observed movements. Data for temperature and rainfall are available
for each month of the two-year field study, but soil moisture data (on which soil shrinking/swelling is predominantly
dependent) is only available for seven of those months. Therefore, two ANNs were used in series. The first ANN estimates soil
moisture for the months when data are not available, while the second ANN uses both measured and estimated soil moisture as
training input to estimate vertical movement.
DE: 1866 Soil moisture
SC: Hydrology [H]
MN: 2004 AGU Fall Meeting