TY - JOUR
T1 - Modeling multidimensional flow in wettable and water-repellent soils using artificial neural networks
AU - Xiong, Yunwu
AU - Wallach, Rony
AU - Furman, Alex
N1 - Funding Information: This research was supported by research Grant US-3662-05R from BARD , the United States–Israel Binational Agricultural Research and Development Fund.
PY - 2011/11/15
Y1 - 2011/11/15
N2 - This study examined the use of three different classes of artificial neural networks for modeling water flow in wettable and water-repellent soils, using both synthetic numerical data and experimentally measured data. The 1D self-organizing maps (SOM) successfully rendered the moisture contour in the transition zone of the wetting plumes for all soil types at different flow rates. Due to SOMs inability to generate external output data, multilayer perceptrons (MLP) and modular neural networks (MNN), respectively, were combined with SOM to predict the moisture contour for both wettable and water-repellent soils. Due to dimensionality reduction, the 1D SOM failed to capture high moisture content classes of water-repellent soils with anomalous wetting patterns, whereas spatial moment analysis succeeded in providing an accurate, albeit indirect, description. Hence, the MLP and MNN networks were applied to predict the spatial moments. The comparison between the predicted and the experimental measures demonstrated the capability of the MLP and SOM to predict the spatial moments. Comparison of the two different artificial neural networks indicated no significant difference between their results.
AB - This study examined the use of three different classes of artificial neural networks for modeling water flow in wettable and water-repellent soils, using both synthetic numerical data and experimentally measured data. The 1D self-organizing maps (SOM) successfully rendered the moisture contour in the transition zone of the wetting plumes for all soil types at different flow rates. Due to SOMs inability to generate external output data, multilayer perceptrons (MLP) and modular neural networks (MNN), respectively, were combined with SOM to predict the moisture contour for both wettable and water-repellent soils. Due to dimensionality reduction, the 1D SOM failed to capture high moisture content classes of water-repellent soils with anomalous wetting patterns, whereas spatial moment analysis succeeded in providing an accurate, albeit indirect, description. Hence, the MLP and MNN networks were applied to predict the spatial moments. The comparison between the predicted and the experimental measures demonstrated the capability of the MLP and SOM to predict the spatial moments. Comparison of the two different artificial neural networks indicated no significant difference between their results.
KW - Modular neural networks
KW - Multilayer perceptrons
KW - Self-organizing maps
KW - Spatial moment analysis
KW - Water-repellent soil
UR - http://www.scopus.com/inward/record.url?scp=80054853904&partnerID=8YFLogxK
U2 - https://doi.org/10.1016/j.jhydrol.2011.09.019
DO - https://doi.org/10.1016/j.jhydrol.2011.09.019
M3 - مقالة
SN - 0022-1694
VL - 410
SP - 92
EP - 104
JO - Journal of Hydrology
JF - Journal of Hydrology
IS - 1-2
ER -