Prediction of water retention curves using neural networks

Download

12625619.pdf

Date

2020-8

Author

Türkmen, Melek

Metadata

Show full item record

Item Usage Stats

286
views

110
downloads

Soil water-retention curve (WRC) relates tension in soil water to soil suction. WRC information has pivotal importance for revealing the behavior of unsaturated soils. Methods for obtaining retention curves are either too expensive or time consuming. Instigated by the demand on fast predictions, this study expressed a composition of a 88 NN designs opened up with (i) hyperparameter tuning, (ii) reexamination of expressions of WRC and GSD. The data was extracted from UNSODA database which encompasses a broad type of soils and widely varied suction ranges, without excluding or subsampling any of the textural group or suction ranges of observations as most of the existing studies did. This inclusive approach rendered the originality of the study and yet spawned a series of problems in methodology and low accuracy in predictions. Among those models, Fredlund and Xing (1994) model held the highest accuracy measure, , which varied from 0.51 to 0.85.

Subject Keywords

Unsaturated Soils, Water-Retention Curves, Neural Networks, Parameter Optimization

URI

https://hdl.handle.net/11511/68995

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Obtaining soil-water characteristic curves by numerical modeling of drainage in particulate media / Shoarian Sattari, Amir; Toker, Nabi Kartal; Department of Civil Engineering (2014) The soil water characteristic curve (SWCC) reflects fundamental drainage properties of partially saturated soils by revealing the relation between soil suction and water content. Although during the past decades, various experimental methods have been proposed for obtaining the SWCC, these approaches are generally time consuming, expensive and highly dependent on operator skills. One solution to this has been sought through various empirical or physico-empirical formulations that link the SWCC to common soi...
Mathematical modeling of steam assisted gravity drainage Akın, Serhat (2004-06-22) A mathematical model for gravity drainage in heavy-oil reservoirs and tar sands during steam injection in linear geometry is proposed. The mathematical model is based on the experimental observations that the steam zone shape is an inverted triangle with the vertex fixed at the bottom production well. Both temperature and asphaltene content dependence of viscosity of the drained heavy oil is considered. The developed model has been validated using experimental data presented in the literature. The heavy oil...
Mathematical modeling of steam-assisted gravity drainage Akın, Serhat (Elsevier BV, 2006-03-01) A mathematical model for gravity drainage in heavy-oil reservoirs and tar sands during steam injection in linear geometry is proposed. The mathematical model is based on experimental observations that the steam zone shape is an inverted triangle with the vertex fixed at the bottom production well. Both temperature and asphaltene content dependence of viscosity of the drained heavy oil and their impact on heavy oil production are considered. The developed model has been validated using experimental data pres...
Mathematical modeling of steam-assisted gravity drainage Akın, Serhat (Society of Petroleum Engineers (SPE), 2005-01-01) A mathematical model for gravity drainage in heavy-oil reservoirs and tar sands during steam injection in linear geometry is proposed. The mathematical model is based on the experimental observations that the steam-zone shape is an inverted triangle with the vertex fixed at the bottom production well. Both temperature and asphaltene content dependence on the viscosity of the drained heavy oil are considered. The developed model has been validated with experimental data presented in the literature. The heavy...
Composite landfill liner design with Ankara clay, Turkey Met, İlker; Akgün, Haluk (Springer Science and Business Media LLC, 2005-04-01) This study presents an overview of the geotechnical properties of the clayey soils, referred to as "Ankara clay", at two sites of the Ankara region in an attempt to design a landfill profile composed of a high density polyethylene (HDPE) geomembrane/clay composite liner through the Hydrologic Evaluation of Landfill Performance (HELP) model and the Water Balance Method. The geotechnical properties of the landfill layers along with the water balance factors (i.e., evapotranspiration, precipitation, temperatur...

Citation Formats

M. Türkmen, “Prediction of water retention curves using neural networks,” M.S. - Master of Science, Middle East Technical University, 2020.