On the application of Bayesian Networks in Digital Soil Mapping

Taalab, Khaled; Corstanje, Ron; Zawadzka, Joanna; Mayr, Thomas; Whelan, M. J.; Hannam, Jacqueline; Creamer, Rachel

doi:10.1016/j.geoderma.2015.05.014

Cited by 23 publications

(16 citation statements)

References 61 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since their introduction in the mid-80s, BBNs have been adopted in various scientific fields, and are becoming increasingly popular tools in environmental modeling (e.g., Sadoddin et al, 2009;Haines-Young, 2011;Farmani et al, 2012;Henriksen et al, 2012;Troldborg et al, 2013), in particular to quantify and map ecosystem services (Grêt-Regamey et al, 2013;Landuyt et al, 2013Landuyt et al, , 2015Celio et al, 2014;Rositano and Ferraro, 2014;Taalab et al, 2015). Formally, a BBN is a probabilistic model that represents graphically a set of random variables and their conditional dependencies via a network, referred to technically as a directed acyclic graph (DAG).…”

Section: Uncertainties Bayesian Belief Network and The Top-down Apmentioning

confidence: 99%

Soil “Ecosystem” Services and Natural Capital: Critical Appraisal of Research on Uncertain Ground

Baveye

Gowdy

2016

Front. Environ. Sci.

306

168

View full text Add to dashboard Cite

Section: Uncertainties Bayesian Belief Network and The Top-down Apmentioning

confidence: 99%

Soil “Ecosystem” Services and Natural Capital: Critical Appraisal of Research on Uncertain Ground

Baveye

Gowdy

2016

Front. Environ. Sci.

306

168

View full text Add to dashboard Cite

“…In cases of partial information and the probability distribution of input data, the Bayesian networks (BN) can work efficiently [44,45]. Some studies have explored the use of BN in predicting soil classes [46].…”

Section: Bayesian Network (Bn)mentioning

confidence: 99%

“…In a DAG, the nodes and links indicated random variables and direct connection between them, respectively. The relationships between cause and effect in BNs are shown through the connections [46]. Unlike deterministic models, BN is a flexible approach to deal with the random processes and can reveal the uncertainty in cause-effect relationships [46].…”

Section: Bayesian Network (Bn)mentioning

confidence: 99%

“…Unlike other network-based models (e.g., ANNs), in BNs, the user, by considering the main process underlain, can define the network and the interactions between the nodes. In terms of DSM, a BN could represent the probabilistic relationships between soil taxonomic class data and auxiliary variables, hence the probabilities of the presence of soil taxonomic classes could be predicted by a BN [46,47].…”

Section: Bayesian Network (Bn)mentioning

confidence: 99%

See 1 more Smart Citation

Digital Mapping of Soil Classes Using Ensemble of Models in Isfahan Region, Iran

et al. 2019

View full text Add to dashboard Cite

Digital soil maps can be used to depict the ability of soil to fulfill certain functions. Digital maps offer reliable information that can be used in spatial planning programs. Several broad types of data mining approaches through Digital Soil Mapping (DSM) have been tested. The usual approach is to select a model that produces the best validation statistics. However, instead of choosing the best model, it is possible to combine all models realizing their strengths and weaknesses. We applied seven different techniques for the prediction of soil classes based on 194 sites located in Isfahan region. The mapping exercise aims to produce a soil class map that can be used for better understanding and management of soil resources. The models used in this study include Multinomial Logistic Regression (MnLR), Artificial Neural Networks (ANN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Bayesian Networks (BN), and Sparse Multinomial Logistic Regression (SMnLR). Two ensemble models based on majority votes (Ensemble.1) and MnLR (Ensemble.2) were implemented for integrating the optimal aspects of the individual techniques. The overall accuracy (OA), Cohen's kappa coefficient index (κ) and the area under the curve (AUC) were calculated based on 10-fold-cross validation with 100 repeats at four soil taxonomic levels. The Ensemble.2 model was able to achieve larger OA, κ coefficient and AUC compared to the best performing individual model (i.e., RF). Results of the ensemble model showed a decreasing trend in OA from Order (0.90) to Subgroup (0.53). This was also the case for the κ statistic, which was the largest for the Order (0.66) and smallest for the Subgroup (0.43). Same decrease was observed for AUC from Order (0.81) to Subgroup (0.67). The improvement in κ was substantial (43 to 60%) at all soil taxonomic levels, except the Order level. We conclude that the application of the ensemble model using the MnLR was optimal, as it provided a highly accurate prediction for all soil taxonomic levels over and above the individual models. It also used information from all models, and thus this method can be recommended for improved soil class modelling. Soil maps created by this DSM approach showed soils that are prone to degradation and need to be carefully managed and conserved to avoid further land degradation.

show abstract

“…This is a step forward, but it still does not include interrelations between soil properties. More recently, Taalab et al (2015) implemented a Bayesian network approach to model soil-landscape relations and predict soil classes and bulk density. Although the authors acknowledge the limitations of the approach to model continuous soil variables, they stressed that the model is easily interpretable because it is based on cause-e ect relationships.…”

Section: Including Process Knowledge In Dsmmentioning

confidence: 99%

Structural equation modelling for digital soil mapping

Angelini¹

View full text Add to dashboard Cite

On the application of Bayesian Networks in Digital Soil Mapping

Cited by 23 publications

References 61 publications

Soil “Ecosystem” Services and Natural Capital: Critical Appraisal of Research on Uncertain Ground

Soil “Ecosystem” Services and Natural Capital: Critical Appraisal of Research on Uncertain Ground

Digital Mapping of Soil Classes Using Ensemble of Models in Isfahan Region, Iran

Structural equation modelling for digital soil mapping

Contact Info

Product

Resources

About