Bayesian modeling approach for characterizing groundwater arsenic contamination in the Mekong River basin

Coupled controls of the infiltration of rivers, urban activities and carbonate on trace elements in a karst groundwater system from Guiyang, Southwest China

Hydrogeochemical processes of trace elements (TEs) are of considerable significance to river water and groundwater resource assessment and utilization in the karst region. Therefore, seven TEs were analyzed to investigate their contents, spatial variations, sources, and controlling factors in Guiyang, a typical karst urban area in southwest China. The results showed that the average content of TEs in river water (e.g., As = 1.44 ± 0.47 μg/L andCo = 0.15 ± 0.06 μg/L) was higher than that of groundwater (e.g., As = 0.51 ± 0.42 μg/L andCo = 0.09 ± 0.05 μg/L). The types of groundwater samples were dominated by Ca/Mg-HCO₃ and Ca/Mg-Cl types, while those of the river water samples were Ca-Cl and Ca/Mg-Cl types. Principal component analysis (PCA) and correlation analysis (CA) analyses indicated that As and Mn in the groundwater of the study area were related to river infiltration. The end-member analysis further revealed that river infiltration (As = 0.86-1.81 μg/L, Cl/SO₄^2- = 0.62-0.89) and urban activities (As = 0.21-0.32 μg/L, Cl/SO₄^2- = 0.51-0.89) were two main controlling factors of TEs (e.g., As, Co, and Mn) in the study area. In addition, the ion ratios in river and groundwater samples indicated that the weathering of carbonates was also an important control on the hydrogeochemistry of TEs (e.g., Fe and Mn) in Guiyang waters. This study showed that the trace element (TE) contents of groundwater in the Guiyang area were greatly associated with urban input and river recharge, and provided a new perspective for understanding the geochemical behavior of TEs in urban surface and groundwater bodies, which will help the protection of groundwater in the karst areas of southwest China.

Assessment of groundwater arsenic contamination using machine learning in Varanasi, Uttar Pradesh, India

This paper presents a machine learning approach for classification of arsenic (As) levels as safe and unsafe in groundwater samples collected from the Indo-Gangetic region. As water is essential for sustaining life, heavy metals like arsenic pose a public health concern. In this study, various tree-based machine learning models namely Random Forest, Optimized Forest, CS Forest, SPAARC, and REP Tree algorithms have been applied to classify water samples. As per the guidelines of the World Health Organization (WHO), the arsenic concentration in water should not exceed 10 μg/L. The groundwater quality parameter was ranked using a classifier attribute evaluator for training and testing the models. Parameters obtained from the confusion matrix, such as accuracy, precision, recall, and FPR, were used to analyze the performance of models. Among all models, Optimized Forest outperforms other classifier as it has a high accuracy of 80.64%, a precision of 80.70%, recall of 97.87%, and a low FPR of 73.33%. The Optimized Forest model can be used to test new water samples for classification of arsenic in groundwater samples.

Machine learning in natural and engineered water systems

Water resources of desired quality and quantity are the foundation for human survival and sustainable development. To better protect the water environment and conserve water resources, efficient water management, purification, and transportation are of critical importance. In recent years, machine learning (ML) has exhibited its practicability, reliability, and high efficiency in numerous applications; furthermore, it has solved conventional and emerging problems in both natural and engineered water systems. For example, ML can predict various water quality indicators in situ and real-time by considering the complex interactions among water-related variables. ML approaches can also solve emerging pollution problems with proven rules or universal mechanisms summarized from the related research. Moreover, by applying image recognition technology to analyze the relationships between image information and physicochemical properties of the research object, ML can effectively identify and characterize specific contaminants. In view of the bright prospects of ML, this review comprehensively summarizes the development of ML applications in natural and engineered water systems. First, the concept and modeling steps of ML are briefly introduced, including data preparation, algorithm selection and model evaluation. In addition, comprehensive applications of ML in recent studies, including predicting water quality, mapping groundwater contaminants, classifying water resources, tracing contaminant sources, and evaluating pollutant toxicity in natural water systems, as well as modeling treatment techniques, assisting characterization analysis, purifying and distributing drinking water, and collecting and treating sewage water in engineered water systems, are summarized. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of ML algorithms for different studies, as well as prospects on the application and development of ML in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.

A Generalized Method for Modeling the Adsorption of Heavy Metals with Machine Learning Algorithms

Applications of machine learning algorithms (MLAs) to modeling the adsorption efficiencies of different heavy metals have been limited by the adsorbate–adsorbent pair and the selection of specific MLAs. In the current study, adsorption efficiencies of fourteen heavy metal–adsorbent (HM-AD) pairs were modeled with a variety of ML models such as support vector regression with polynomial and radial basis function kernels, random forest (RF), stochastic gradient boosting, and bayesian additive regression tree (BART). The wet experiment-based actual measurements were supplemented with synthetic data samples. The first batch of dry experiments was performed to model the removal efficiency of an HM with a specific AD. The ML modeling was then implemented on the whole dataset to develop a generalized model. A ten-fold cross-validation method was used for the model selection, while the comparative performance of the MLAs was evaluated with statistical metrics comprising Spearman’s rank correlation coefficient, coefficient of determination (R2), mean absolute error, and root-mean-squared-error. The regression tree methods, BART, and RF demonstrated the most robust and optimum performance with 0.96 ⫹ R2 ⫹ 0.99. The current study provides a generalized methodology to implement ML in modeling the efficiency of not only a specific adsorption process but also a group of comparable processes involving multiple HM-AD pairs.

A Hybrid Bayesian Network Framework for Risk Assessment of Arsenic Exposure and Adverse Reproductive Outcomes

Arsenic contamination of drinking water affects more than 137 million people and has been linked to several adverse health effects. The traditional toxicological approach, "dose-response" graphs, are limited in their ability to unveil the relationships between potential risk factors of arsenic exposure for adverse human health outcomes, which are critically important to understanding the risk at low exposure levels of arsenic. Therefore, to provide insight on the potential interactions of different variables of the arsenic exposure network, this study characterizes the risk factors by developing a hybrid Bayesian Belief Network (BBN) model for health risk assessment. The results show that the low inorganic arsenic concentration increases the risk of low birth weight even for low gestational age scenarios. While increasing the mother's age does not increase the low birthweight risk, it affects the distribution between other categories of baby weight. For low MMA% (<4%) in the human body, increasing gestational age decreases the risk of having low birthweight. The proposed BBN model provides 82% sensitivity and 72% specificity in average for different states of birthweight.

Predicting groundwater arsenic contamination: Regions at risk in highest populated state of India

Arsenic (As) contamination of groundwater is a public health concern, impacting the lives of approximately 100 million people in India. Chronic exposure to As significantly increases mortality due to the occurrence of several types of cancer, respiratory and cardiac diseases. Uttar Pradesh is a part of the middle Indo-Gangetic plains and has been found to be severely affected by As contamination of groundwater, as established by several small-scale studies. The current study incorporates a hybrid method based on a random forest ensemble algorithm and univariate feature selection using 1473 data points for predicting As in the region. Twenty direct/proxy predictor variables were considered to describe the geochemical environment, aquifer conditions and topography that are responsible for As enrichment in groundwater. The map of As predicted through the hybrid random forest ensemble model shows an overall accuracy of 84.67%. The hybrid random forest model performs better than the univariate, logistic, fuzzy, adaptive fuzzy and adaptive neuro fuzzy inference systems, which have been widely used for As prediction. The projected number of rural populations at risk due to high As exposure is 12% of the total population of the region, which accounts for 23.48 million people who are at risk. The predictive map provides insight for the regions where future testing campaigns and interventions for mitigation should be prioritized by policymakers.