Neural Networks Prediction of Soil Hydraulic Functions for Alluvial Soils Using Multistep Outflow Data

Minasny, Budiman; Hopmans, Jan W.; Harter, Thomas; Eching, S. O.; Tuli, Ataç; Denton, Michelle

doi:10.2136/sssaj2004.0417

Cited by 63 publications

(82 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several large databases for the PTFs development have been built and are being updated on a national as well as international level. For example, one can cite the works by Nemes et al (2001), Nemes (2002), Minasny et al (2004), and Schindler and Müller (2010). The most important database for Europe is HYPRES, HYdraulic PRoperties of European Soils (Wösten et al 1999).…”

mentioning

confidence: 99%

HYPRESCZ - database of soil hydrophysical properties in the Czech Republic

Miháliková¹,

Matula²,

Dolezal³

2013

Soil Water Res.

View full text Add to dashboard Cite

Miháliková M., Matula S., Doležal F. (2013) The database of soil hydrophysical properties in the Czech Republic called HYPRESCZ was created. It is based on the European database HYPRES, HYdraulic PRoperties of European Soils, and follows its structure with few modifications. It collects the available data from the Czech Republic from which pedotransfer functions (PTFs) for the estimation of soil hydrophysical properties from easily available soil properties can be derived and 2101 database entries were collected. The entries have different quality of data, out of the total number of entries 707 entries were applicable to PTFs derivation for the estimation of soil water retention curves (SWRCs). After elimination of replicates, finally 159 unique soil horizons (arable land only) were used for PTFs derivation. The parametric continuous pedotransfer functions for estimation of SWRCs in the Czech Republic were derived within this study and are based on Wösten's model. The retention curves were estimated using both these newly derived PTFs and Wösten's original model, which was derived for European soils in general. The uncertainty of estimation was evaluated, employing the root mean squared error (RMSE) and the coefficient of determination (R 2 ) comparing the PTF-estimated and the directly fitted retention curves. The reliability of the newly derived PTFs for Czech soils was higher (RMSE = 0.059 cm 3 /cm 3 and R 2 = 71%) compared to Wösten's general PTFs (RMSE = 0.11 cm 3 /cm 3 and R 2 = 36%).

show abstract

mentioning

confidence: 99%

HYPRESCZ - database of soil hydrophysical properties in the Czech Republic

Miháliková¹,

Matula²,

Dolezal³

2013

Soil Water Res.

View full text Add to dashboard Cite

show abstract

“…Care must therefore be taken concerning the selection of soil parameters. Although parameter correlations are observed and may be strong in some cases, existing soil analysis methods typically adopt the assumption of independent parameters (van der Zee and van Riemsdijk, 1987;Andersen and Christensen, 1988;Streck and Richter, 1997;Römkens and Salomons, 1998;Tiktak et al, 1998;Elzinga et al, 1999;Annadurai and Lee, 2007;Sarmadian and Taghizadeh Mehrjardi, 2008;Minasny et al, 2004;McBratney et al, 2003;Behrens et al, 2005;Buszewski and Kowalkowski, 2006;Anagu et al, 2009 ;Gandhimathi and Meenambal, 2012).…”

Section: Selection Of Soil Factorsmentioning

confidence: 99%

“…Over the last few years ANNs have been widely used in the field of soil science for the prediction of soil hydraulic properties Minasny et al, 2004), the generation of digital soil maps (McBratney et al, 2003;Behrens et al, 2005) and the modeling of the behavior of trace metals (Buszewski and Kowalkowski, 2006;Anagu et al, 2009 ;Gandhimathi and Meenambal, 2012). In this case, the ANN is trained to find these relations using an iterative calibration process.…”

Section: Introductionmentioning

confidence: 99%

Application of an inverse neural network model for the identification of optimal amendment to reduce copper toxicity in phytoremediated contaminated soils

Hattab

Motelica-Heino

2014

Journal of Geochemical Exploration

View full text Add to dashboard Cite

To cite this version:Nour Hattab, Mikael Motelica-Heino. Application of an inverse neural network model for the identification of optimal amendment to reduce Copper toxicity in phytoremediated contaminated soils. Journal of Geochemical Exploration, Elsevier, 2014, 136, pp.14-23 AbstractArtificial neural network ANN prediction approaches applied to the modeling of soil behavior are often solved in the forward direction, by measuring the response of the soil (outputs) to a given set of soil inputs. Conversely, one may be interested in the assessment of a given set of soil inputs that leads to given (target) soil outputs. This is the inverse of the former problem. In this study, we develop and test an inverse artificial neural network model for the prediction of the optimal soil treatment to reduce copper ( Cu) toxicity assessed by a given target concentration of Cu in dwarf bean leaves (BL) from selected soil inputs. In this study the inputs are the soil pH, electrical conductivity (EC), dissolved organic carbon (DOC) and a given target toxicity value of Cu, whereas the output is the best treatment to reduce the given toxicity level. It is shown that the proposed method can successfully identify the best soil treatment from the soil properties (inputs).Two important challenges for optimal treatment prediction using neural networks are the nonuniqueness of the solution of the inverse problem and the inaccuracies in the measurement of the soil properties (inputs). It is shown that the neural network prediction model proposed can overcome both these challenges. It is also shown that the proposed inverse neural network method 2 can potentially be applied with a high level of success to the phytoremediation of contaminated soils. Before large-scale application, further validation is needed by performing several experiments and investigations including additional factors and their combinations to capture the complex soil behavior.

show abstract

“…With MLR methods, the relationships between soil inputs (properties) and soil output characteristics have to be stated a priori in the regression models. An alternative to MLR is the application of ANN models where such relationships do not need to be formulated beforehand (Anagu et al, 2009;Sarmadian and Taghizadeh Mehrjardi, 2008;Hambli et al, 2006;Hambli, 2009;Minasny et al, 2004;McBratney et al, 2003;Behrens et al, 2005;Buszewski and Kowalkowski, 2006;Gandhimathi and Meenambal, 2012).…”

mentioning

confidence: 99%

“…ANNs have been widely used in the field of soil science for prediction of soil hydraulic properties Minasny et al, 2004) generation of digital soil maps (McBratney et al, 2003;Behrens et al, 2005) and modeling of the behavior of trace metals (Buszewski and Kowalkowski, 2006;Anagu et al, 2009;Gandhimathi and Meenambal, 2012).…”

mentioning

confidence: 99%

Application of neural network model for the prediction of chromium concentration in phytoremediated contaminated soils

Hattab

Hambli

Motelica-Heino

et al. 2013

Journal of Geochemical Exploration

View full text Add to dashboard Cite

The assessment of chromium concentrations in plants requires the quantification of a large number of soil factors that affect their potential availability and subsequent toxicity and a mathematical model that predicts their relative concentrations. Many soil characteristics can change the availability of chromium (Cr) to plants in soils. However, accurate, rapid and simple predictive models of metal concentrations are still lacking in soil and plant analysis. In the present work a novel artificial neural network (ANN) model was developed as an alternative rapid and accurate tool for the prediction of Cr concentration in dwarf bean leaves grown in the laboratory on phytoremediated contaminated soils treated with different amendments. First, sixteen (4x4) soil samples were harvested from a phytoremediated contaminated site located in south-western France. Second, a series of measurements were performed on the soil samples.The inputs are the soil amendment, the soil pH, the soil electrical conductivity and the dissolved organic carbon of the soil and the output is the concentration of Cr in the dwarf bean 2 leaves. Third, an ANN model was developed and its performance was evaluated using a test data set and then applied to predict the exposition of the bean leaves to the Cr concentration versus the soil inputs. The performance of the ANN method was compared with the traditional multi linear regressions method using the training and test data sets. The results of this studyshow that the ANN model trained on experimental measurements can be successfully applied to the rapid prediction of plant exposition to Cr.

show abstract

Neural Networks Prediction of Soil Hydraulic Functions for Alluvial Soils Using Multistep Outflow Data

Cited by 63 publications

References 0 publications

HYPRESCZ - database of soil hydrophysical properties in the Czech Republic

HYPRESCZ - database of soil hydrophysical properties in the Czech Republic

Application of an inverse neural network model for the identification of optimal amendment to reduce copper toxicity in phytoremediated contaminated soils

Application of neural network model for the prediction of chromium concentration in phytoremediated contaminated soils

Contact Info

Product

Resources

About