Groundwater risk assessment based on optimization framework using DRASTIC method

Jafari, Seyedeh Mahboobeh; Nikoo, Mohammad Reza

doi:10.1007/s12517-016-2756-4

Cited by 52 publications

(17 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previously, the DRASTIC method, which is an index method based on expert opinion, had been employed in the same study area by Maqsoom et al [3]. The biggest disadvantage of this method is subjectivity, as the rating values are assumed based on expert opinion [60]. However, this study focuses on the assessment of three ML models: multivariate discriminant analysis (MDA), boosted regression trees (BRT), and support-vector machines (SVM), to predict the incidence of groundwater contamination in the same area in northern Pakistan.…”

Section: Introductionmentioning

confidence: 99%

Assessing Nitrate Contamination Risks in Groundwater: A Machine Learning Approach

et al. 2021

View full text Add to dashboard Cite

Groundwater is one of the primary sources for the daily water requirements of the masses, but it is subjected to contamination due to the pollutants, such as nitrate, percolating through the soil with water. Especially in built-up areas, groundwater vulnerability and contamination are of major concern, and require appropriate consideration. The present study develops a novel framework for assessing groundwater nitrate contamination risk for the area along the Karakoram Highway, which is a part of the China Pakistan Economic Corridor (CPEC) route in northern Pakistan. A groundwater vulnerability map was prepared using the DRASTIC model. The nitrate concentration data from a previous study were used to formulate the nitrate contamination map. Three machine learning (ML) models, i.e., Support Vector Machine (SVM), Multivariate Discriminant Analysis (MDA), and Boosted Regression Trees (BRT), were used to analyze the probability of groundwater contamination incidence. Furthermore, groundwater contamination probability maps were obtained utilizing the ensemble modeling approach. The models were calibrated and validated through calibration trials, using the area under the receiver operating characteristic curve method (AUC), where a minimum AUC threshold value of 80% was achieved. Results indicated the accuracy of the models to be in the range of 0.82–0.87. The final groundwater contamination risk map highlights that 34% of the area is moderately vulnerable to groundwater contamination, and 13% of the area is exposed to high groundwater contamination risk. The findings of this study can facilitate decision-making regarding the location of future built-up areas properly in order to mitigate the nitrate contamination that can further reduce the associated health risks.

show abstract

Section: Introductionmentioning

confidence: 99%

Assessing Nitrate Contamination Risks in Groundwater: A Machine Learning Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The values of the decision variables are optimized and updated after successive iterations in which the appropriate constraints are considered. The objective function (Equation 3) increases the correlation coefficient between the vulnerability index and the NO 3 concentration to optimize the weights of the DRASTIC parameters (Jafari and Nikoo ; Barzegar et al ).

Max F = corr (X, Y)

\begin{matrix} F = \frac{\sum_{j = 1}^{n} ((), ((), X_{j} - \overset{X}{true}) - ((), Y_{j} - \overset{Y}{true}))}{\sqrt{\sum_{j = 1}^{n} {(X_{j} - \overset{true‾}{normalX})}^{2}} \sqrt{\sum_{j = 1}^{n} {(Y_{j} - \overset{true‾}{normalY})}^{2}}} \\ Constraint : 1 < W_{i} < 5, j = 1, 2, \dots, n \end{matrix}

where F is an objective function, n is the number of wells, Y j is the observed NO 3 concentration (mg/L),

\overset{true‾}{normalY}

is the mean observed NO 3 concentration (mg/L), X j is the vulnerability index (dimensionless),

\overset{true‾}{normalX}

is the mean vulnerability index, and W i is the weight of the DRASTIC parameters.…”

Section: Methodsmentioning

confidence: 99%

“…Some studies have used external parameters, such as land use and irrigation type and intensity, to improve the DRASTIC method (Secunda et al ; McLay et al ). Others have used the analytical hierarchy process (AHP), statistical methods, the Wilcoxon test, genetic algorithm (GA), and artificial intelligence (AI) (Panagopoulos et al ; Ahn et al ; Huan et al ; Barzegar et al ; Jafari and Nikoo ; Jang et al ; Kihumba et al ; Yang et al ) to overcome the limitations of the DRASTIC framework. In a study similar to the one presented here, Barzegar et al () used a multi‐model ensemble of machine learning algorithms in the Marand plain of northwest Iran to investigate vulnerability to contamination in multiple aquifers (e.g., unconfined, semiconfined, and confined).…”

Section: Introductionmentioning

confidence: 99%

Modification of the DRASTIC Framework for Mapping Groundwater Vulnerability Zones

et al. 2019

View full text Add to dashboard Cite

The DRASTIC technique is commonly used to assess groundwater vulnerability. The main disadvantage of the DRASTIC method is the difficulty associated with identifying appropriate ratings and weight assignments for each parameter. To mitigate this issue, ratings and weights can be approximated using different methods appropriate to the conditions of the study area. In this study, different linear (i.e., Wilcoxon test and statistical approaches) and nonlinear (Genetic algorithm [GA]) modifications for calibration of the DRASTIC framework using nitrate (NO 3 ) concentrations were compared through the preparation of groundwater vulnerability maps of the Meshqin-Shahr plain, Iran. Twenty-two groundwater samples were collected from wells in the study area, and their respective NO 3 concentrations were used to modify the ratings and weights of the DRASTIC parameters. The areas found to have the highest vulnerability were in the eastern, central, and western regions of the plain. Results showed that the modified DRASTIC frameworks performed well, compared to the unmodified DRASTIC. When measured NO 3 concentrations were correlated with the vulnerability indices produced by each method, the unmodified DRASTIC method performed most poorly, and the Wilcoxon-GA-DRASTIC method proved optimal. Compared to the unmodified DRASTIC method with an R 2 of 0.22, the Wilcoxon-GA-DRASTIC obtained a maximum R 2 value of 0.78. Modification of DRASTIC parameter ratings was found to be more efficient than the modification of the weights in establishing an accurately calibrated DRASTIC framework. However, modification of parameter ratings and weights together increased the R 2 value to the highest degree. Article impact statement: The results showed that both linear and nonlinear methods are useful in modifying the ratings and weights of the DRASTIC method for assessing the groundwater vulnerability.

show abstract

“…Hence the best groundwater management practice is to protect groundwater resources from contamination (Rezaeiet al, 2017). Identification of the areas that are highly susceptible to pollution is very important to prevent groundwater pollution (Jafari and Nikoo, 2016). For this purpose, groundwater vulnerability models are effective tools.…”

Section: Introductionmentioning

confidence: 99%

Ground Water Vulnerability Assessmentof Kodoor River Basin by Integrated Drastic Method

Simi¹,

K²,

Varghese³

et al. 2022

YMER

View full text Add to dashboard Cite

Groundwater vulnerability assessment techniques are useful tools in groundwater management. The purpose of the study is to assess the groundwater vulnerability of Kodoor river basin in Kerala by DRASTIC model and to modify the model to suit the regional scale by incorporating the land use and/ or land cover (LULC) pattern of the area of study in it to produce DRASTICA model. The interdependence of the nitrate concentration data and vulnerability indices from DRASTIC and DRASTICA models were calculated. Correlation coefficient values obtained for DRASTIC and DRASTICA model is 0.21 and 0.38 respectively which shows that the modified DRASTICA model suits the study area better. The study area was grouped into three zones based on the grades of vulnerability. The study also includes the sensitivity analysis of the DRASTICA model. The map removal sensitivity analysis and single parameter sensitivity analysis were carried out to validate the model results.

show abstract

Groundwater risk assessment based on optimization framework using DRASTIC method

Cited by 52 publications

References 38 publications

Assessing Nitrate Contamination Risks in Groundwater: A Machine Learning Approach

Assessing Nitrate Contamination Risks in Groundwater: A Machine Learning Approach

Modification of the DRASTIC Framework for Mapping Groundwater Vulnerability Zones

Ground Water Vulnerability Assessmentof Kodoor River Basin by Integrated Drastic Method

Contact Info

Product

Resources

About