An evaluation of nonlinear methods for estimating catchment-scale soil moisture patterns based on topographic attributes

被引:12
作者
Coleman, Michael L. [1 ]
Niemann, Jeffrey D. [1 ]
机构
[1] Colorado State Univ, Dept Civil & Environm Engn, Ft Collins, CO 80523 USA
关键词
cross-validation; mixture model; neural network; nonlinear; soil moisture; SPATIAL-DISTRIBUTION; WATER CONTENT; CROP YIELD; TERRAIN; INTERPOLATION; ORGANIZATION; VEGETATION; CLIMATE;
D O I
10.2166/hydro.2012.145
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Physical processes that impact soil moisture are typically expressed as nonlinear functions, but most previous research on the estimation of soil moisture has relied on linear techniques. In the present work, two machine learning techniques, a spatial artificial neural network (SANN) and a mixture model (MM), that can infer nonlinear relationships are compared to multiple linear regression (MLR) for estimating soil moisture patterns using topographic attributes as predictor variables. The methods are applied to time-domain reflectometry (TDR) soil moisture data collected at three catchments with varying characteristics (Tarrawarra, Satellite Station and Cache la Poudre) under different wetness conditions. The methods' performances with respect to the number of predictor attributes, the quantity of training data and the attributes employed are compared using the Nash Sutcliffe coefficient of efficiency (NSCE) as the performance measure. The performances of the methods are dependent on the site studied, the average soil moisture and the quantity of training data provided. Although the methods often perform similarly, the best performing method overall is the SANN, which incorporates additional predictor variables more effectively than the other methods.
引用
收藏
页码:800 / 814
页数:15
相关论文
共 61 条
[31]   DIGITAL TERRAIN MODELING - A REVIEW OF HYDROLOGICAL, GEOMORPHOLOGICAL, AND BIOLOGICAL APPLICATIONS [J].
MOORE, ID ;
GRAYSON, RB ;
LADSON, AR .
HYDROLOGICAL PROCESSES, 1991, 5 (01) :3-30
[32]  
MOORE ID, 1988, T ASAE, V31, P1098, DOI 10.13031/2013.30829
[33]  
Nadaraya E.A., 1964, Theory Prob. Appl, V9, P141, DOI DOI 10.1137/1109020
[34]  
Nash J. E., 1970, Journal of Hydrology, V10, P282, DOI DOI 10.1016/0022-1694(70)90255-6
[35]  
Nyberg L, 1996, HYDROL PROCESS, V10, P89, DOI 10.1002/(SICI)1099-1085(199601)10:1<89::AID-HYP303>3.0.CO
[36]  
2-W
[37]   Generation of soil moisture patterns at the catchment scale by EOF interpolation [J].
Perry, M. A. ;
Niemann, J. D. .
HYDROLOGY AND EARTH SYSTEM SCIENCES, 2008, 12 (01) :39-53
[38]   Analysis and estimation of soil moisture at the catchment scale using EOFs [J].
Perry, Mark A. ;
Niemann, Jeffrey D. .
JOURNAL OF HYDROLOGY, 2007, 334 (3-4) :388-404
[39]   A review of advances in dielectric and electrical conductivity measurement in soils using time domain reflectometry [J].
Robinson, D.A. ;
Jones, S.B. ;
Wraith, J.M. ;
Or, D. ;
Friedman, S.P. .
2003, Soil Science Society of America (02) :444-475
[40]   ON THE SPATIAL-ORGANIZATION OF SOIL-MOISTURE FIELDS [J].
RODRIGUEZ-ITURBE, I ;
VOGEL, GK ;
RIGON, R ;
ENTEKHABI, D ;
CASTELLI, F ;
RINALDO, A .
GEOPHYSICAL RESEARCH LETTERS, 1995, 22 (20) :2757-2760