Use of Soil Property Data and Computer Models to Minimize Agricultural Impacts on Water Quality

2015 ◽  
pp. 287-292
Author(s):  
David I. Gustafson
Keyword(s):  
Water Quality ◽  
Soil Property ◽  
Computer Models ◽  
Agricultural Impacts ◽  
Property Data

scholarly journals A Comparative Study of Various Methods of Handling Missing Data in UNSODA

Agriculture ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 727
Author(s):  
Yingpeng Fu ◽  
Hongjian Liao ◽  
Longlong Lv
Keyword(s):  
Missing Data ◽  
Missing Values ◽  
Soil Property ◽  
Particle Density ◽  
Organic Matter Content ◽  
Nonparametric Tests ◽  
Matter Content ◽  
Support Vector ◽  
Soil Database ◽  
Property Data

UNSODA, a free international soil database, is very popular and has been used in many fields. However, missing soil property data have limited the utility of this dataset, especially for data-driven models. Here, three machine learning-based methods, i.e., random forest (RF) regression, support vector (SVR) regression, and artificial neural network (ANN) regression, and two statistics-based methods, i.e., mean and multiple imputation (MI), were used to impute the missing soil property data, including pH, saturated hydraulic conductivity (SHC), organic matter content (OMC), porosity (PO), and particle density (PD). The missing upper depths (DU) and lower depths (DL) for the sampling locations were also imputed. Before imputing the missing values in UNSODA, a missing value simulation was performed and evaluated quantitatively. Next, nonparametric tests and multiple linear regression were performed to qualitatively evaluate the reliability of these five imputation methods. Results showed that RMSEs and MAEs of all features fluctuated within acceptable ranges. RF imputation and MI presented the lowest RMSEs and MAEs; both methods are good at explaining the variability of data. The standard error, coefficient of variance, and standard deviation decreased significantly after imputation, and there were no significant differences before and after imputation. Together, DU, pH, SHC, OMC, PO, and PD explained 91.0%, 63.9%, 88.5%, 59.4%, and 90.2% of the variation in BD using RF, SVR, ANN, mean, and MI, respectively; and this value was 99.8% when missing values were discarded. This study suggests that the RF and MI methods may be better for imputing the missing data in UNSODA.

Agricultural Impacts on Lake and Stream Water Quality in Grand Lake St. Marys, Western Ohio

2008 ◽  
Vol 193 (1-4) ◽  
pp. 309-322 ◽  
Author(s):  
J. Hoorman ◽  
T. Hone ◽  
T. Sudman ◽  
T. Dirksen ◽  
J. Iles ◽  
...  
Keyword(s):  
Water Quality ◽  
Stream Water ◽  
Stream Water Quality ◽  
Agricultural Impacts

Comparison of Computer Models for Estimating Hydrology and Water Quality in an Agricultural Watershed

2017 ◽  
Vol 31 (11) ◽  
pp. 3641-3665 ◽  
Author(s):  
Yaoze Liu ◽  
Sisi Li ◽  
Carlington W. Wallace ◽  
Indrajeet Chaubey ◽  
Dennis C. Flanagan ◽  
...  
Keyword(s):  
Water Quality ◽  
Computer Models ◽  
Agricultural Watershed

Use of limited soil property data and modeling to estimate root zone soil water content

2003 ◽  
Vol 272 (1-4) ◽  
pp. 131-147 ◽  
Author(s):  
Patrick J. Starks ◽  
Gary C. Heathman ◽  
Lajpat R. Ahuja ◽  
Liwang Ma
Keyword(s):  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Soil Property ◽  
Root Zone ◽  
Property Data

Palæochannels in Northern New South Wales: Inversion of electromagnetic induction data to infer hydrologically relevant stratigraphy

Soil Research ◽  
2006 ◽  
Vol 44 (1) ◽  
pp. 35 ◽  
Author(s):  
R. W. Vervoort ◽  
Y. L. Annen
Keyword(s):  
Electromagnetic Induction ◽  
Soil Property ◽  
Interpolation Method ◽  
New South ◽  
New South Wales ◽  
Pedotransfer Functions ◽  
Earth Model ◽  
Deep Drainage ◽  
South Wales ◽  
Property Data

Palæochannels, or prior streams, are strings of sandier sediments that occur frequently in the irrigated alluvial plains of Northern New South Wales, Australia. These landscape features have been recognised as locations of substantial deep drainage losses, and are therefore target areas for water use efficiency. Electromagnetic induction (EM) measurements were used to identify the width and the depth of the palæochannel sediments in a 2-dimensional transect. Three different inversion techniques, Tikhonov regularisation, the McNeill layered earth model, and an optimal linear combination of EM measurements, were applied to a combination of EM-38 and EM-34 data. Using various kriging techniques, the resulting conductivity profiles were interpolated to soil property data and transformed to saturated hydraulic conductivities using pedotransfer functions. There were distinct differences in the resulting stratigraphies depending on the inversion and interpolation method employed. Trend kriging of the sampled soil property data using the Cook and Walker and Tikhonov inversion data as a trend surface gave the most consistent hydraulic conductivity values compared to the sampled soil property data. However, differences between inversion and interpolation methods were negated by uncertainties in the pedotransfer functions.

Agricultural impacts on water quality and implications for virtual water trading decisions

2009 ◽  
Vol 68 (4) ◽  
pp. 1074-1082 ◽  
Author(s):  
J.M. Dabrowski ◽  
K. Murray ◽  
P.J. Ashton ◽  
J.J. Leaner
Keyword(s):  
Water Quality ◽  
Virtual Water ◽  
Agricultural Impacts ◽  
Water Trading ◽  
Trading Decisions ◽  
Virtual Water Trading
Sign in / Sign up

Export Citation Format

Share Document