Predicting groundwater redox status on a regional scale using linear discriminant analysis

Close, Murray E.; Abraham, Phillip; Humphries, Bronwyn; Lilburne, Linda; Cuthill, T.; Wilson, Scott R.

doi:10.1016/j.jconhyd.2016.04.006

Cited by 46 publications

(24 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Uncertainties and prediction errors may also arise from the underlying dependent variable. Investigations of the spatial distribution of redox conditions in aquifers have shown a decrease in aerobic conditions with depth (Close et al 2016, Rosecrans et al 2017. Due to this hydrogeochemical zoning of aquifers, the concentrations of the groundwater samples strongly depend on the horizon in which the wells are screened and generally the NO 3 concentrations decrease with increasing well depth (Wheeler et al 2015, Ransom et al 2017.…”

Section: Discussionmentioning

confidence: 99%

“…Such anaerobic conditions are characterised by an oxygen (O 2 ) concentration of ⩽1-2 mg l −1 and iron (Fe) concentration of ⩾0.1-0.2 mg l −1 (Kunkel et al 2004, Rivett et al 2008, Mcmahon and Chapelle 2008. Several studies dealt with the large-scale estimation of redox conditions in groundwater (Tesoriero et al 2015, Close et al 2016, Rosecrans et al 2017, Koch et al 2019 and Ransom et al (2017) identified it as one of the most important parameters for the estimation of nitrate concentrations.…”

Section: Introductionmentioning

confidence: 99%

“…Such tree-based ML techniques have already been used in several studies on large-scale prediction of groundwater nitrate concentrations (Nolan et al 2014, Rodriguez-Galiano et al 2014, 2018, Wheeler et al 2015, Ransom et al 2017, Tesoriero et al 2017, Knoll et al 2019, Ouedraogo et al 2019. In terms of the estimation of groundwater redox conditions, Close et al (2016) and Wilson et al (2018) performed linear discriminant analyses. Whereas, other studies also made use of ML for predicting groundwater redox conditions or the redox interface (Tesoriero et al 2015, Rosecrans et al 2017, Koch et al 2019, Friedel et al 2020.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Nation-wide estimation of groundwater redox conditions and nitrate concentrations through machine learning

Knoll

Bach

2020

Environ. Res. Lett.

View full text Add to dashboard Cite

The protection of water resources and development of mitigation strategies require large-scale information on water pollution such as nitrate. Machine learning techniques like random forest (RF) have proven their worth for estimating groundwater quality based on spatial environmental predictors. We investigate the potential of RF and quantile random forest (QRF) to estimate redox conditions and nitrate concentration in groundwater (1 km × 1 km resolution) using the European Water Framework Directive groundwater monitoring network as well as spatial environmental information available throughout Germany. The RF model for nitrate achieves a good predictive performance with an R 2 of 0.52. Dominant predictors are the redox conditions in the groundwater body, hydrogeological units and the percentage of arable land. An uncertainty assessment using QRF shows rather large uncertainties with a mean prediction interval (MPI) of 53.0 mg l −1 . This study represents the first nation-wide data-driven assessment of the spatial distribution of groundwater nitrate concentrations for Germany.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Nation-wide estimation of groundwater redox conditions and nitrate concentrations through machine learning

Knoll

Bach

2020

Environ. Res. Lett.

View full text Add to dashboard Cite

show abstract

“…In line with McMahon et al () and Hansen et al (), this potential can be estimated based on combined knowledge on subsurface flowpaths and the depth to the redox interface, that is, the location of the uppermost reduced (anaerobic) zone, below which denitrification takes place. Recent advances on how to model redox conditions in the subsurface were highlighted by Close et al (), Tesoriero et al (), and Hansen, Christensen, et al (). In the former, Close et al () simulated categorical redox conditions, that is, oxidized, mixed, and reduced, for two regions in New Zealand using a multivariate linear model.…”

Section: Introductionmentioning

confidence: 99%

Modeling Depth of the Redox Interface at High Resolution at National Scale Using Random Forest and Residual Gaussian Simulation

Koch

Stisen

Refsgaard

et al. 2019

Water Resources Research

View full text Add to dashboard Cite

The management of water resources needs robust methods to efficiently reduce nitrate loads.Knowledge on where natural denitrification takes place in the subsurface is thereby essential. Nitrate is naturally reduced in anoxic environments and high-resolution information of the redox interface, that is, the depth of the uppermost reduced zone is crucial to understand the variability of the denitrification potential. In this study we explore the opportunity to use random forest (RF) regression to model redox depth across Denmark at 100-m resolution based on~13,000 boreholes as training data. We highlight the importance of expert knowledge to guide the RF model in areas where our conceptual understanding is not represented correctly in the training data set by addition of artificial observations. We apply random forest regression kriging in which sequential Gaussian simulation models the RF residuals. The RF model reaches a R 2 score of 0.48 for an independent validation test. Including sequential Gaussian simulation honors observations through local conditioning, and the spread of 800 realizations can be utilized to map uncertainty. Emphasis is put on adequate handling of nonstationarities in variance and spatial correlation of the RF residuals. The RF residuals show no spatial correlation for large parts of the modeling domain, and a local variance scaling method is applied to account for the nonstationary variance. Moreover, we present and exemplify a framework where newly acquired field data can easily be integrated into random forest regression kriging to quickly update local models.Plain Language Summary Nutrients, such as nitrogen in form of nitrate are essential for plant growth. Despite their benefits, nutrient surplus can cause adverse health and ecological effects. In fact, nitrate leaching from agricultural fields is one of the major water resources management challenges in today's agricultural landscapes. During the transport through the subsurface, nitrate can potentially be degraded in anoxic layers below the redox interface. This is referred to as denitrification and its potential varies spatially depending on the local landscape. The location of the redox interface is thus essential knowledge toward a spatially differentiated water resources management. We applied a machine learning method to model the redox depth at 100m spatial resolution across Denmark, based on redox data obtained from~13,000 boreholes and environmental variables that explain redox variability. We highlight the importance of expert knowledge in guiding the machine learning model by adding artificial observations in underrepresented landscapes. As an add-on, a geostatistical model is used to honor local data at grid scale and quantify the spatial uncertainty elsewhere. Lastly, we outline and exemplify a framework that allows an easy integration of newly acquired field data for updating local models of the depth to the redox interface.

show abstract

“…For example, Haghizadeh et al [17] utilized spring locations in two bivariate techniques (i.e., Dempster-Shafer theory and Statistical Index) to analyze potential groundwater zones. Other recent works used machine learning, namely K-nearest Neighbors (KNN) [21], Linear Discriminant Analysis (LDA) [22], multivariate adaptive regression splines [23], quadratic discriminant analysis [21], Support Vector Machine (SVM) [24], Random Forest (RF) [23] and Decision Trees [25]. Also, the author of [26] investigated the use of models including SVM, flexible discriminant analysis (FDA), boosted regression trees (BRT), Artificial Neural Networks (ANN), and RF for GPM in the Beheshtabad watershed, Iran.…”

Section: Introductionmentioning

confidence: 99%

Optimized Conditioning Factors Using Machine Learning Techniques for Groundwater Potential Mapping

Kalantar

Al-Najjar

Pradhan

et al. 2019

Water

View full text Add to dashboard Cite

Assessment of the most appropriate groundwater conditioning factors (GCFs) is essential when performing analyses for groundwater potential mapping. For this reason, in this work, we look at three statistical factor analysis methods-Variance Inflation Factor (VIF), Chi-Square Factor Optimization, and Gini Importance-to measure the significance of GCFs. From a total of 15 frequently used GCFs, 11 most effective ones (i.e., altitude, slope angle, plan curvature, profile curvature, topographic wetness index, distance from river, distance from fault, river density, fault density, land use, and lithology) were finally selected. In addition, 917 spring locations were identified and used to train and test three machine learning algorithms, namely Mixture Discriminant Analysis (MDA), Linear Discriminant Analysis (LDA) and Random Forest (RF). The resultant trained models were then applied for groundwater potential prediction and mapping in the Haraz basin of Mazandaran province, Iran. MDA has been successfully applied for soil erosion and landslide mapping, but has not yet been fully explored for groundwater potential mapping (GPM). Although other discriminant methods, such as LDA, exist, MDA is worth exploring due to its capability to model multivariate nonlinear relationships between variables; it also undertakes a mixture of unobserved subclasses with regularization of non-linear decision boundaries, which could potentially provide more accurate classification. For the validation, areas under Receiver Operating Characteristics (ROC) curves (AUC) were calculated for the three algorithms. RF performed better with AUC value of 84.4%, while MDA and LDA yielded 75.2% and 74.9%, respectively. Although MDA performance is lower than RF, the result is satisfactory, because it is within the acceptable standard of environmental modeling. The outcome of factor analysis and groundwater maps emphasizes on optimization of multicolinearity factors for faster spatial modeling and provides valuable information for government agencies and private sectors to effectively manage groundwater in the region.

show abstract

Predicting groundwater redox status on a regional scale using linear discriminant analysis

Cited by 46 publications

References 21 publications

Nation-wide estimation of groundwater redox conditions and nitrate concentrations through machine learning

Nation-wide estimation of groundwater redox conditions and nitrate concentrations through machine learning

Modeling Depth of the Redox Interface at High Resolution at National Scale Using Random Forest and Residual Gaussian Simulation

Optimized Conditioning Factors Using Machine Learning Techniques for Groundwater Potential Mapping

Contact Info

Product

Resources

About